No entries match these filters. Clear filters
Runlayer adds PGP PGP A public-key encryption standard for signing and encrypting data, originally by Phil Zimmermann; cyber tools use it to verify software authenticity and protect sensitive communications. private key detection, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. output blocking notices in Cursor, and session privacy improvements in Analytics︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Detect complete armored PGP private keys (BEGIN PGP PRIVATE KEY BLOCK-----, PGP SECRET KEY BLOCK) and private keys with dash-containing headers (GPGTools Comment: line, encrypted PEM DEK-Info:) in tool-call arguments, so the Mask, Block and Alert actions now apply to them.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Show a Runlayer notice to the agent in Cursor when an MCP tool's output is blocked in Protect mode (on Cursor 2.6.22 or later), replacing the previous silent omission; Sessions and the supported clients list now report Block bypassed for built-in tool output and Blocked for replaced MCP output. Not checked yet Show a Runlayer notice to the agent when Runlayer cannot be reached to scan an MCP tool's output in Protect mode, consistent with behaviour on other blocking clients. Not checked yet Hide other people's sessions from the timeline in an Analytics output's detail view when Session privacy is on, displaying a count of hidden sessions instead of their title, owner, cost or session link. Not checked yet Scale hidden-character, PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. and token-masking scanner time proportionally to tool-call or tool-result size instead of slowing down sharply on dense inputs. Not checked yet
+1 more
show less
Mask recognised credentials in audit payloads before they reach the audit database, payload archives and downstream exports; security approvals retain matching without copying detected credential values into approval evidence. Not checked yet
Mask recognised credentials in audit payloads before they reach the audit database, payload archives and downstream exports; security approvals retain matching without copying detected credential values into approval evidence. Not checked yet
5 more in Everything
Runlayer adds access-request workflows, reply-to-quote in chat, and a unified Procedures setting with auto-benchmarking and auto-promotion︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Grant a teammate access to an agent they cannot open, without leaving the product, by using the built-in request flow.
📍 In the Runlayer web app, open the agent, artifact, skill, or plugin page you cannot access, then click Request access . The owner sees the request under Approvals (and in Slack if connected) and can share it directly from there.
Quote a specific sentence from an agent response to ask a follow-up question without retyping the context.
📍 In agent chat, highlight the relevant words in the agent's answer, then click Reply — the quoted text appears in your message box and is sent with your next message.
Request access to any artifact, agent, skill, or plugin you lack permission to open by clicking Request access ; the owner receives the request in Approvals and in Slack, and approving it opens the page for you.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Reply to a specific part of an agent answer in chat by highlighting words and clicking Reply to quote them in your message box, available in agent chat, the Runlayer Assistant, and artifact chat. Not checked yet Enable a single Procedures setting that lets self-improving agents save their own procedures, triggers automatic benchmarking of drafts saved without named runs, and promotes a passing draft to live without waiting for approval. Not checked yet Stale procedure draft versions with no review decision after 30 days are now automatically sent back with a reason, their review requests closed, and any live version keeps running. Not checked yet Failed procedure benchmarks now retry daily automatically instead of waiting for a new version, within each version's test-run limit. Not checked yet
+3 more
show less
Skill risk policy blocks now also apply when skills are reached via @ mentions in agent chat or through skill distillation in self-improving agents, matching the behaviour already in place for agent runs. Not checked yet Token masking now fully hides a private key written right after password= with no END marker; previously only the first few characters were masked. Not checked yet PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. masking of large tool inputs and outputs with many personal-data matches is now much faster — a multi-megabyte response that previously took minutes now takes about a second. Not checked yet
Request access to any artifact, agent, skill, or plugin you lack permission to open by clicking Request access ; the owner receives the request in Approvals and in Slack, and approving it opens the page for you.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Reply to a specific part of an agent answer in chat by highlighting words and clicking Reply to quote them in your message box, available in agent chat, the Runlayer Assistant, and artifact chat. Not checked yet Stale procedure draft versions with no review decision after 30 days are now automatically sent back with a reason, their review requests closed, and any live version keeps running. Not checked yet
5 more in Everything
Runlayer adds per-virtual-key LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. Gateway routing, dynamic subagents, an agent kill switch, audit-logged grant refusals, tools/list policy enforcement, sort_by=recommended on the agents API, and HTML artifact publishing.
Give a virtual key its own LLM Gateway routing rules and fallbacks using runlayer_llm_gateway_usage_rule with scope = "virtual_key" and runlayer_llm_gateway_routing_rule in Terraform, or set both in the key's Edit dialog under Settings → LLM Gateway → Virtual keys. Not checked yet Manage MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. configurations as code with the new runlayer_mdm_configuration Terraform resource in the next Terraform provider release. Not checked yet Agents on the Pi harness can now start dynamic subagents using the new Agent tool, with read-only, planning, or general-purpose workers that run in the background and use the agent's connectors, skills, and identity, with at most two running at once. Not checked yet Sort agents by recent organizational usage with sort_by=recommended on the agents API and the list_agents MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool; the response also includes users_30d, runs_30d, and last_used_at per agent. Not checked yet An agent harness agent harness The software around an AI agent that manages its tools, execution loop, state and limits. It determines how the model's proposed actions are run and checked. can now request connector tools in a flat list by sending the X-Runlayer-Tool-Exposure: force-flat header, including on agent account endpoints and Plugins with Dynamic tools; force-nested keeps clients on search_tools and execute_tool. Not checked yet
+13 more
show less
Session search is now available to every organization with Sessions on the Sessions page and via the Runlayer MCP session search tools, with no separate opt-in required. Not checked yet Organizations with session topics now see a Session topics section on the Analytics page. Not checked yet New integration Turn off a model for all users in Settings → AI Providers by toggling the Enabled switch on any model under Model access, hiding it from all agent model pickers and rejecting new picks. Not checked yet The agent kill switch now stops agent tokens, OBO tokens, API keys, LLM gateway keys, upstream connector calls, and sandbox file operations when an agent is disabled; turning it back on restores all grants. Not checked yet The Runlayer Assistant now hands off work to connected-app agents (such as Notion) when used in web chat, Go, iMessage, or Microsoft Teams, as it already did in Slack. Not checked yet Agents can now publish a folder with an index.html as an artifact, with scripts, styles, images, fonts, and media combined into one page; screenshot_artifact previews the same page. Not checked yet A refused attempt to grant an agent or agent account more tools or resources than the person's own policy allows is now recorded in the audit log as agent_grant_refused, naming who tried and what was refused. Not checked yet Connector-condition policies (meta.server.*) are now applied in tools/list, omitting tools denied by connector-condition rules from the list rather than listing them and refusing at call time. Not checked yet The Google Workspace connector can now convert .pptx to Google Slides, .docx to a Google Doc, and .xlsx.xlsx The file format used by Microsoft Excel for spreadsheets, based on the Open XML standard. Cyber tools use it to ingest or export structured tabular data in a format analysts already work with. to a Google Sheet when creating files. Not checked yet The identity rebind API can now reset a user's sign-in binding and release the directory user held by a deactivated duplicate, letting a Super Admin resolve these cases without Runlayer support. Not checked yet Super Admins can now see a user's directory user ID and refused sync matches on the user's Manage tab, view all refused matches under Settings → Sign-in & provisioning, and look up the directory user for an email through the API. Not checked yet The sidebar is now an icon rail with a section panel; Home, Inbox, connectors, skills, assets, Teams, and Settings open from the rail, with new manage pages for connectors, skills, and endpoints for admins. Not checked yet Reviewers can now re-run a draft procedure's benchmark directly from the review drawer when it has failed or is waiting for a replay, without waiting for a new version. Not checked yet
18 details in Everything
└──▷ BREAKING ON UPGRADE
! Stdio connectors that run inside the Runlayer backend now run on Python 3.14 and start in /tmp instead of /app; a uv script whose requires-python excludes 3.14 no longer starts. If a connector relied on /app, set cwd in its config.! A uv stdio connector that runs its own project now builds a fresh environment on each start; set UV_ISOLATED=0 in its config to reuse the project's .venv again.! Any --python <version> or -p <version> argument must be removed from a uv stdio connector's args — ClickHouse connectors added from the catalog before this release include --python 3.13 and won't start until it's removed.! Sending plain text for Google Slides via the Google Workspace connector now fails with an error message instructing the caller to send a .pptx instead; previously it silently created a Google Doc. Existing Google Drive connectors need to be redeployed to receive file conversion.! The seen_by_user_count API field on connector tools now stops at 50 for tools seen by 50 or more users.! The deprecated connections API no longer widens an existing connection.! The session filter on the Audit Logs page is now offered only to organizations with Sessions.
Runlayer adds per-user Windows hook installs via runlayer setup hooks --install, a workspace Inbox for every user, faster in-place artifact edits with version history, and tighter agent connector-tool access controls.
Install per-user AI Watch hooks on Windows without MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. using runlayer setup hooks --install, which also preserves existing hook entries containing non-ASCII text. Not checked yet Updated integration Every workspace now has an Inbox with an updates bell that collects decisions, reconnect prompts, and pending access and connector requests. Not checked yet Agents can now change text, colors, or numbers in an existing artifact without downloading and re-uploading the whole file; each change is saved as a restorable version. Not checked yet Agent connector tools are now restricted so editors and importers can only add connector tools they can use themselves, with deny policies still applying to connector owners and admins. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! Existing Google Calendar connectors must be redeployed to receive event color data on read and list operations.
Runlayer adds an Auditor role, Terraform resources for binary and device-sync settings, editable approval-system request bodies, and Lean 4 in agent sandboxes.
Manage per-package update policies and skill device sync defaults as code using the new runlayer_binary_package_settings and runlayer_skill_device_sync_settings Terraform resources. Not checked yet New read-only Auditor role for compliance reviewers gives org-wide access to audit logs, session content, user info, metrics, Shadow AI and AI inventory, and usage export — assign it by setting role auditor in your identity provider identity provider A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. . Not checked yet Approval system request bodies now follow an editable template, letting you shape the payload Runlayer sends to Okta Workflows, ServiceNow, or a custom service to match the format your flow expects. Not checked yet Agent sandboxes now include the Lean 4 proof checker (lean) with its core library, so agents can machine-check proofs without downloading the toolchain first. Not checked yet Updated integration Enforce file-read blocking now also blocks built-in file search and listing tools grep, rg, glob, find, ls, and list_files in every client, including Claude Code's Grep and Glob . Not checked yet
+7 more
show less
Policy denials now appear in Sessions as Blocked by Access Policy alongside scanner blocks, with the reason the call was denied. Not checked yet Control Claude Desktop content capture on macOS and Windows devices via the otlpContentCapture device setting, now configured automatically by AI Watch for organizations with Claude Cowork enabled — turn it off with Claude Cowork content capture in AI Watch settings. Not checked yet Artifact folders now let users organize artifacts into folders shown as a grid or list, with drag-and-drop, card menus, and bulk selection, without affecting other users' organization. Not checked yet Slack messages to @runlayer are now routed to the workspace agent best suited to answer, falling back to accessible connectors when no agent fits. Not checked yet Agent runs on single-organization ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. Terraform deployments with the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway enabled now send model traffic through the gateway automatically, applying usage and spend limits. Not checked yet Analytics Spend tab now shows model cost and token usage as stacked bars for top models on daily ranges, with remaining models grouped as Other and legend click-to-highlight. Not checked yet Claude Cowork sessions whose content Claude Desktop withheld are now marked Redacted by source , with withheld prompts shown as a placeholder and a drawer explanation of how to enable content capture. Not checked yet
12 details in Everything
└──▷ BREAKING ON UPGRADE
! Legacy enrollment keys no longer issue a device credential to users who can manage admins, organization settings, or MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. configuration; those users must sign in with runlayer login instead.! The MDM configurations API now returns a masked enrollment key for legacy enrollment configurations instead of the full value.! Failed resource reads no longer forward structured error data larger than 64 KiB or nested more than 100 levels deep — applies to every organization including those with masking off.! A tool argument literally named __object_ref now appears as _escaped__object_ref in the audit log and SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. export.
Runlayer adds linked billing with Claude Platform: one-step approval, direct Anthropic billing, and spend-limit controls in the Claude Console.
New integration Connect a Claude Platform organization to Runlayer without an API key by clicking Link your Claude organization in Runlayer and approving the link once — an owner, admin, or billing admin of the Claude organization approves, Anthropic bills Claude API usage directly to that organization. Not checked yet Set a monthly spend limit for Runlayer inside the Claude Console, and unlink the Claude organization at any time. Not checked yet
2 details in Everything
Runlayer adds agent error notifications to Slack, Teams, and webhooks, and now logs refused OAuth token requests in audit trails︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Configure agent error notifications to Slack, Microsoft Teams, or signed HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. webhook destinations — with cooldowns and recent delivery history — for agent failures and unresolved tool errors.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Refused OAuth token requests now appear in audit logs with the client ID, agent or user involved, and the reason — covering wrong client secrets, failed PKCE PKCE Proof Key for Code Exchange, an OAuth safeguard that binds an authorization code to the client that requested it. An intercepted code cannot be redeemed without the client's matching verifier. checks, and replayed ID-JAGs. Not checked yet
Configure agent error notifications to Slack, Microsoft Teams, or signed HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. webhook destinations — with cooldowns and recent delivery history — for agent failures and unresolved tool errors.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 more in Everything
└──▷ BREAKING ON UPGRADE
! GET, POST, and PUT on /api/v1/policies now return scope.servers, scope.tools, and scope.resources as lists — "*" becomes ["*"]. Clients that compare a scope field to "*" must also accept ["*"].! A request scope or agent account connection policy with an unknown key (e.g. a misspelled tool) now returns HTTP 422 instead of being silently ignored.
Runlayer adds OpenCode session monitoring, Enforce test detections, and policy-aware agent connection UI︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
After a policy rollout, verify that Enforce and Protect are blocking on a device by printing the test prompts and checking results in Shadow AI Activity.
copy
$ aiwatch enforce-test
Run aiwatch enforce-test on a device to print a test MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server entry and two shell prompts that Enforce and Protect block, then confirm each block in the agent reply and in Shadow AI Activity.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Point a remote MCP entry at the Runlayer-hosted test server to verify that Enforce blocks remote MCP calls on devices that have no enforce-test command yet. Not checked yet AI Watch now records OpenCode sessions and applies Protect and Enforce to OpenCode tool calls on macOS and Windows, including MCP tools, via a Runlayer-installed OpenCode plugin (OpenCode 1.x, 1.18.29 or newer recommended; OpenCode 2 not yet supported). Not checked yet Managed email delivery for self-hosted deployments now reads exclusively from RESEND_API_KEY — set it in the provisioned tenant secret on ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. or in the runlayer-app Secret on Kubernetes before upgrading. Not checked yet Agent account connection cards now show deny policies that reach the agent, noting how many tools a policy denies and marking the connector Blocked by policy for blanket denies; denied tools appear first in the tool picker and cannot be selected. Not checked yet
+2 more
show less
AI Watch skill discovery and risk audit events, and audit log exports, now show ***REDACTED*** in place of sign-in details, query values, and recognized tokens in a skill's git remote URL. Not checked yet Error messages returned by local MCP servers run through the Runlayer CLI are now masked when PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. detection or token masking is set to mask, preventing personal data and credentials in errors from reaching the AI client. Not checked yet
Run aiwatch enforce-test on a device to print a test MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server entry and two shell prompts that Enforce and Protect block, then confirm each block in the agent reply and in Shadow AI Activity.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Point a remote MCP entry at the Runlayer-hosted test server to verify that Enforce blocks remote MCP calls on devices that have no enforce-test command yet. Not checked yet AI Watch now records OpenCode sessions and applies Protect and Enforce to OpenCode tool calls on macOS and Windows, including MCP tools, via a Runlayer-installed OpenCode plugin (OpenCode 1.x, 1.18.29 or newer recommended; OpenCode 2 not yet supported). Not checked yet
4 more in Everything
└──▷ BREAKING ON UPGRADE
!
Managed email delivery ('Let Runlayer handle email delivery') for self-hosted deployments no longer falls back to WorkOS Vault for its key — `RESEND_API_KEY` must be set in the ECS tenant secret or the `runlayer-app` Kubernetes Secret before upgrading, or organizations with managed delivery will fall back to custom SMTP or send no email at all, including security-violation alerts.
Our best guess
Runlayer 5.0.0 adds lossless SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. session export, agent eval scorers over MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. , and config-exception routing for admins︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Route agent configuration exception requests to your own form or repo instead of handling them in-app — set once in Terraform and all policy-blocked settings link there automatically.
main.tf
copy
resource "runlayer_organization" "main" {
agent_config_exception_request_url = "https://github.com/your-org/ai-policy-exceptions/issues/new"
}
Lock a devcontainer LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. Gateway to known-good URLs so developer keys and prompts never reach unexpected hosts.
.devcontainer/devcontainer.json
copy
{
"features": {
"ghcr.io/runlayer/devcontainer-features/llm-gateway:1": {
"host": "gateway.corp.example.com",
"gatewayUrl": "https://gateway.corp.example.com/v1"
}
}
}
Before upgrading, broaden your SIEM destination bucket policy to accept the new payload objects so full session event bodies export without permission errors.
copy
$ # Allow writes to all objects under the export prefix, not just *.jsonl.gz
# Then filter S3 notifications and dedupe on session_id + event_id + part_index
aws s3api put-bucket-policy --bucket my-siem-bucket --policy '{
"Statement": [{
"Effect": "Allow",
"Action": ["s3:PutObject"],
"Resource": "arn:aws:s3:::my-siem-bucket/runlayer-sessions/*"
}]
}'
Export full session event bodies to <prefix>/payloads/ via the new data_payload_uri field, so oversize and chunked events are no longer truncated in SIEM destinations.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Set a custom agent configuration exception URL with agent_config_exception_request_url on the Terraform organization resource, or in Settings > General under Agent configuration exceptions , to route policy-exception requests to your own GitHub repo or form instead of in-app requests. Not checked yet Pin the devcontainer LLM Gateway to specific URLs by setting both host and gatewayUrl on the llm-gateway Feature, so developer device keys and prompts go only to those URLs; setting only one now fails the build. Not checked yet Create, delete, and draft custom TypeScript eval scorers through the Runlayer Assistant or any MCP client using the Runlayer MCP server. Not checked yet Agent sandboxes now include the GitHub CLI (gh) and TLA+ tools (tlc, sany, pcal), so agents can script GitHub workflows and model-check specs without installing anything. Not checked yet
+5 more
show less
Session-based access policies now account for tool calls that reached a connector and then failed, so failed calls are included in session history. Not checked yet LLM routing rule changes now take effect the next time a device requests a gateway token, rather than waiting for its next check-in. Not checked yet Offline MCP call decisions made by AI Watch on a device are now reported once the device reconnects, producing an audit log entry marked Decided on the device . Not checked yet Sensitive data is now kept out of audit trails: MCP URL credentials (sign-in details and tokens) are hidden from audit-only viewers in Shadow AI listings and MCP discovery audit events, including previously recorded events, and agent environment variable values set through the update_agent Runlayer MCP tool no longer appear in tool-call audit rows or SIEM exports, with only variable names recorded. Not checked yet Connect multiple connectors in Go concurrently, with each connector card progressing from Add to Adding to Added independently and back-to-back additions batched into one reply. Not checked yet
Export full session event bodies to <prefix>/payloads/ via the new data_payload_uri field, so oversize and chunked events are no longer truncated in SIEM destinations.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Set a custom agent configuration exception URL with agent_config_exception_request_url on the Terraform organization resource, or in Settings > General under Agent configuration exceptions , to route policy-exception requests to your own GitHub repo or form instead of in-app requests. Not checked yet Pin the devcontainer LLM Gateway to specific URLs by setting both host and gatewayUrl on the llm-gateway Feature, so developer device keys and prompts go only to those URLs; setting only one now fails the build. Not checked yet Create, delete, and draft custom TypeScript eval scorers through the Runlayer Assistant or any MCP client using the Runlayer MCP server. Not checked yet Offline MCP call decisions made by AI Watch on a device are now reported once the device reconnects, producing an audit log entry marked Decided on the device . Not checked yet
5 more in Everything
└──▷ BREAKING ON UPGRADE
!
Scoped agent token audience enforcement is now always on: the `agent-token-audience-enforcement` flag is removed, `FF_DISABLE=agent-token-audience-enforcement` does nothing, and any scoped agent or on-behalf-of token used outside its scope is rejected with `403 invalid_target`. Clients must request a `resource` that matches every server they use the token on, or request a token without `resource`.
Our best guess
!
SIEM export destinations must allow writes to all of `<prefix>/*` in the destination role or bucket policy before upgrading, and consumers must filter S3-notification ingestion on `.jsonl.gz` (or `<prefix>/year=`) and dedupe on `session_id + event_id + part_index`.
Our best guess
!
Setting only `host` or only `gatewayUrl` on the `llm-gateway` Feature now fails the build; both must be set together.
Our best guess
!
Removing `icon_url` or `transport_config` from a `runlayer_server` Terraform config no longer clears those values; to clear them you must explicitly set `icon_url = ""` or `transport_config = {}`. Requires the next Terraform provider release.
Our best guess
!
The database migration in this release briefly locks the plugin table and does not support rollback; an older version cannot load the Runlayer Plugin after the migration runs. Roll forward to fix problems, or contact Runlayer support before attempting a rollback.
Our best guess
Runlayer adds agent configuration via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. , AI Watch Enforce coverage for unlisted MCP servers, and expanded audit logging for every MCP call AI Watch checks︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Install or upgrade the Runlayer CLI on a Python 3.14 environment to run agent and policy commands.
copy
$ uv tool install runlayer
Configure an agent's network access, environment variables, and collaboration settings directly from your MCP client using agent settings via MCP.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet AI Watch Enforce now makes and records block decisions for MCP servers not found in a client's configuration, surfacing calls in Shadow AI Activity and the audit log as an unidentified MCP server instead of blocking silently on the device. Not checked yet Every MCP call that AI Watch Protect or Enforce checks now gets an audit log entry, including blocked unreadable requests, error-state calls, calls from deactivated-user devices, and anonymous device calls recorded against the organization. Not checked yet Super Admins can now move an existing user to a new email address and/or directory identity via the API, preserving roles, teams, and history, with every rebind audit-logged. Not checked yet Agents start approximately 9 seconds sooner on a fresh sandbox on the OpenCode harness, and no longer stall for over a minute when their network policy blocks the npm registry. Not checked yet
+2 more
show less
Install the Runlayer CLI from PyPI with uv tool install runlayer on Python 3.14. Not checked yet A new guide explains how to bring servers, policies, and other app-created objects under Terraform using import blocks and generated configuration. Not checked yet
Configure an agent's network access, environment variables, and collaboration settings directly from your MCP client using agent settings via MCP.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Super Admins can now move an existing user to a new email address and/or directory identity via the API, preserving roles, teams, and history, with every rebind audit-logged. Not checked yet A new guide explains how to bring servers, policies, and other app-created objects under Terraform using import blocks and generated configuration. Not checked yet
4 more in Everything
Runlayer adds all-users/all-agents policies, private GitHub skill imports, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. Gateway in devcontainers devcontainers A Docker-based development environment specification, maintained by Microsoft and the open-source community, that lets a tool ship a fully configured, reproducible workspace any developer can launch inside VS Code or a compatible editor. , and agent version history via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. ︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Run Claude Code or Codex inside a devcontainer and route all LLM calls through the developer's own gateway — with usage rules and budgets enforced just as on the host.
copy
$ runlayer credential setup
Transfer ownership of a Runlayer agent via Terraform so governance stays in code and shows a reviewable diff in terraform plan.
main.tf
copy
resource "runlayer_agent" "my_agent" {
name = "my-agent"
owner_id = "usr_abc123"
}
Add the LLM Gateway devcontainer feature to a devcontainer so containerised coding agents inherit the host AI Watch gateway configuration automatically.
.devcontainer/devcontainer.json
copy
{
"features": {
"ghcr.io/runlayer/devcontainer-features/llm-gateway": {}
}
}
Import skills from private GitHub repos by pasting a repo URL in Add skill → GitHub; Runlayer reads the repo through the workspace's GitHub App connection with a short-lived read-only token, then treats the result as a regular workspace-wide skill with auto-update.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Use LLM Gateway inside devcontainers by adding the ghcr.io/runlayer/devcontainer-features/llm-gateway Feature, or by running runlayer credential setup in your image and mounting ~/.runlayer/aiwatch; usage rules, budgets, and offboarding apply as on the host. Not checked yet Improves the Terraform provider: setting owner_id on runlayer_agent transfers agent ownership, shown in terraform plan with the same checks as an in-app ownership transfer, and the runlayer_server resource and data source now hide transport_config headers, env, placeholder defaults, and test_placeholder_values, requiring sensitive = true on root module outputs referencing these values. Not checked yet Target every user or every agent account — including ones added later — with a single policy using the new all users and all agents principals; self-hosted deployments must run 4.1.0 or later on every backend instance before saving one. Not checked yet List, read, and restore agent versions from any AI client via Runlayer MCP; restores are saved as new versions so they can be undone. Not checked yet
+5 more
show less
Restrict offloaded large tool outputs fetched with get_large_output to only the user and agent grant that produced them, even when multiple users delegate to the same agent. Not checked yet Add agent bots and the Runlayer Teams notification bot to Microsoft Teams shared and private channels via Manage channel → Apps; already-installed bots update automatically. Not checked yet Set guest permissions on calendar events with create_event and update_event; pass edit_as_guest: true to update_event on events you do not organize to save changes on the organizer's calendar when guest edits are allowed. Not checked yet Copy a user access link from the agent account page with the new Copy user access link button so regular users can grant an agent account access on their behalf. Not checked yet Managed tunnel connections now automatically add capacity as stream usage grows and remove idle endpoints after their streams finish, with each endpoint defaulting to 256 concurrent streams. Not checked yet
Import skills from private GitHub repos by pasting a repo URL in Add skill → GitHub; Runlayer reads the repo through the workspace's GitHub App connection with a short-lived read-only token, then treats the result as a regular workspace-wide skill with auto-update.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Use LLM Gateway inside devcontainers by adding the ghcr.io/runlayer/devcontainer-features/llm-gateway Feature, or by running runlayer credential setup in your image and mounting ~/.runlayer/aiwatch; usage rules, budgets, and offboarding apply as on the host. Not checked yet Target every user or every agent account — including ones added later — with a single policy using the new all users and all agents principals; self-hosted deployments must run 4.1.0 or later on every backend instance before saving one. Not checked yet List, read, and restore agent versions from any AI client via Runlayer MCP; restores are saved as new versions so they can be undone. Not checked yet Copy a user access link from the agent account page with the new Copy user access link button so regular users can grant an agent account access on their behalf. Not checked yet
5 more in Everything
└──▷ BREAKING ON UPGRADE
!
Root module Terraform outputs that reference `transport_config` headers, `env`, placeholder defaults, or `test_placeholder_values` on `runlayer_server` now require `sensitive = true` or the plan will error.
Our best guess
!
Self-hosted deployments must run 4.1.0 or later on every backend instance before saving an 'all users' or 'all agents' policy; older instances skip these policies silently.
Our best guess
!
A `RunlayerInstance` with `spec.redis.tls: true` and `credentials.passwordFrom` previously connected without TLS; it now connects over TLS. If your Redis does not serve TLS, set `tls: false` explicitly.
Our best guess
Runlayer adds LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway multi-model failover, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. -driven agent controls, and a RESEND_API_KEY environment variable for self-hosted email delivery︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Inject the Resend API key into a Kubernetes self-hosted deployment so email delivery does not depend on WorkOS Vault.
copy
$ kubectl create secret generic runlayer-app \
--from-literal=RESEND_API_KEY=re_live_xxxxxxxxxxxx \
--dry-run=client -o yaml | kubectl apply -f -
Keep WorkOS, Sentry, and Resend secrets in AWS Secrets Manager only, preventing them from appearing in Terraform state on ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. deployments.
hcl
copy
tenant_secret_source = "provisioned"
Discover which LLM models are available to use as routing-rule targets or fallbacks before creating a rule.
copy
$ curl -s -H 'Authorization: Bearer <token>' \
https://your-runlayer-instance/api/v1/llm-gateway/models | jq '.[].id'
Supply the Resend API key to self-hosted deployments as the RESEND_API_KEY environment variable (or the runlayer-app Kubernetes secret key), which takes priority over the WorkOS Vault secret fallback.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Set up to three fallback models on an LLM gateway routing rule so the gateway retries on the next fallback after a server error, rate limit, timeout, or refused key — across providers if needed — via Settings → AI models → Budgets & routing. Not checked yet Set tenant_secret_source = "provisioned" in self-hosted ECS deployments so WorkOS, Sentry, and Resend keys are read straight from your AWS Secrets Manager secret instead of passing through Terraform state. Not checked yet Run a saved agent schedule once on demand through Runlayer MCP without changing its next or last run time. Not checked yet Configure request signing, rotate or disable signing secrets, and rename agent webhooks through the Runlayer Assistant or an MCP client. Not checked yet
+5 more
show less
Edit the webhook JSON body in Settings → Policies → Approval settings using variables like {{request_id}}, {{session_id}}, and {{status}}, and test the payload with Send test. Not checked yet List a poll trigger's recent polls, run Fetch now, and list live choices for a trigger's target fields (such as Slack channels or GitHub repositories) through Runlayer MCP. Not checked yet Transfer agent ownership to another person through an MCP client, subject to the same permission checks as the agent's Share dialog. Not checked yet Generate an AI icon suggestion for an agent through Runlayer MCP and apply it with update_agent. Not checked yet Delete an eval, record a human verdict on an eval case, pick source runs from a plain-language description, label runs pass or fail, and group failed runs by cause through the Runlayer Assistant or MCP clients. Not checked yet
Supply the Resend API key to self-hosted deployments as the RESEND_API_KEY environment variable (or the runlayer-app Kubernetes secret key), which takes priority over the WorkOS Vault secret fallback.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Set tenant_secret_source = "provisioned" in self-hosted ECS deployments so WorkOS, Sentry, and Resend keys are read straight from your AWS Secrets Manager secret instead of passing through Terraform state. Not checked yet Run a saved agent schedule once on demand through Runlayer MCP without changing its next or last run time. Not checked yet Configure request signing, rotate or disable signing secrets, and rename agent webhooks through the Runlayer Assistant or an MCP client. Not checked yet Edit the webhook JSON body in Settings → Policies → Approval settings using variables like {{request_id}}, {{session_id}}, and {{status}}, and test the payload with Send test. Not checked yet
+4 more
show less
List a poll trigger's recent polls, run Fetch now, and list live choices for a trigger's target fields (such as Slack channels or GitHub repositories) through Runlayer MCP. Not checked yet Transfer agent ownership to another person through an MCP client, subject to the same permission checks as the agent's Share dialog. Not checked yet Generate an AI icon suggestion for an agent through Runlayer MCP and apply it with update_agent. Not checked yet Delete an eval, record a human verdict on an eval case, pick source runs from a plain-language description, label runs pass or fail, and group failed runs by cause through the Runlayer Assistant or MCP clients. Not checked yet
1 more in Everything
└──▷ BREAKING ON UPGRADE
!
Creating or updating an LLM gateway routing rule via the API or Terraform now returns a 422 error when the rule's target or any fallback is not a model listed on your AI providers. Add the model under Settings → AI models → Providers or use a model from `GET /api/v1/llm-gateway/models`. Existing rules continue routing; updates that leave targets unchanged still succeed.
Our best guess
Runlayer adds Kubernetes Gateway API publishing, agent spend caps via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. , and suggestion policies to steer agents toward preferred tools︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Attach your own agent and session identifiers to Claude Code OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. sessions so you can trace a Runlayer session back to your internal agent.
copy
$ export OTEL_RESOURCE_ATTRIBUTES="sidekick.agent_id=my-agent-42,sidekick.session_key=proj-session-7"
Inspect or cap an agent's daily spend limit from an MCP client without leaving your automation workflow.
📍 In the Runlayer Assistant or any MCP client, ask: 'Show current spend and run limits for agent <agent-id>, then set a daily spend cap of $10.'
Create a suggestion policy so agents are nudged toward create_app on every Vercel deploy call, without blocking the original tool.
📍 In Settings → Security Scanners → Overrides, open the relevant connector override page, add a suggestion policy targeting the Vercel deploy tool call, enter your preferred message referencing create_app, and set frequency to Every call or Once per session .
Publish a Runlayer instance using the Kubernetes Gateway API alongside or instead of Ingress via the Runlayer operator.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Claude Code sessions sent over OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. now carry custom agent identifiers — set sidekick.agent_id and sidekick.session_key via OTEL_RESOURCE_ATTRIBUTES and they appear as External metadata on the session. Not checked yet Read an agent's spend and run limits, including current usage and reset times, and set or remove daily and weekly spend caps through the Runlayer Assistant and MCP clients. Not checked yet Admins can now open any team from the Teams page and inspect its members and shared assets without joining it. Not checked yet Sessions now show the agent's avatar and name instead of a generic Runlayer label, with a direct link to the agent from the session panel. Not checked yet
+4 more
show less
Editors can rename artifacts by double-clicking the title or editing it while Edit text is open; renaming does not create a new version, and a blank title falls back to the file name. Not checked yet Opening a teammate's redacted agent run in chat now explains why messages are hidden, and people with unredacted access can reveal messages inline with each reveal recorded in the audit log. Not checked yet Settings → Security Scanners now opens with tabs for Scanners, Security Response, Scan budgets, and Overrides, a scanner list grouped by category with a detail pane, and one page per connector or client override. Not checked yet Admins can now create suggestion policies that steer agents toward preferred tools — for example, suggesting create_app instead of a third-party deploy — without blocking the original tool call, triggering once per session or on every call. Not checked yet
Publish a Runlayer instance using the Kubernetes Gateway API alongside or instead of Ingress via the Runlayer operator.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Claude Code sessions sent over OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. now carry custom agent identifiers — set sidekick.agent_id and sidekick.session_key via OTEL_RESOURCE_ATTRIBUTES and they appear as External metadata on the session. Not checked yet Read an agent's spend and run limits, including current usage and reset times, and set or remove daily and weekly spend caps through the Runlayer Assistant and MCP clients. Not checked yet Editors can rename artifacts by double-clicking the title or editing it while Edit text is open; renaming does not create a new version, and a blank title falls back to the file name. Not checked yet Admins can now create suggestion policies that steer agents toward preferred tools — for example, suggesting create_app instead of a third-party deploy — without blocking the original tool call, triggering once per session or on every call. Not checked yet
4 more in Everything
Runlayer adds in-place artifact editing, per-schedule model selection, tunnel connector observability, and procedure auto-benchmarking︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Assign a lightweight model to an hourly health-check schedule and a more capable model to a weekly report trigger, keeping costs down without changing the agent's default.
📍 In the task or trigger dialog, open the model selector, choose the model the agent's AI provider serves, and save — the schedule or trigger will use that model instead of the agent's default.
Edit doc, CSV/TSV TSV A plain-text format storing tabular data with fields separated by tab characters, making it easy for cyber tools to parse and exchange structured records without a CSV parser's quoting complexity. , and HTML artifacts directly from the artifact page without invoking an agent; an agent's edit_artifact call that would overwrite a newer manual save is refused.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Run scheduled tasks and connector triggers on a model different from the agent's default — pick a cheaper model for frequent checks and a stronger one for heavier reports — via the task or trigger dialog. Not checked yet Procedure drafts are now benchmarked automatically by replaying the agent runs they were built from, so a draft reaches approval-ready or goes live without a manual benchmark run; the review panel shows queued, running, or failed status. Not checked yet Tunnel connectors now support optional liveness and readiness probes to distinguish a responsive connector from one with an established tunnel session, an optional Prometheus-compatible metrics endpoint covering connector readiness, endpoint connectivity, and connection failures, and optional JSON logs with timestamp, severity, and message fields; text remains the default and now uses key=value fields. Not checked yet Custom PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. rule patterns are now capped at 1,000 characters and policy regex conditions at 500 characters; existing longer patterns continue to work. Not checked yet
+2 more
show less
Access to Runlayer-managed agents such as the Runlayer Assistant is now restricted to admins who manage security policies; an agent's owner can no longer grant edit or View all runs access. Not checked yet The Organization API keys page now links to Personal API keys so users can find account-tied keys without navigating through Settings. Not checked yet
Edit doc, CSV/TSV TSV A plain-text format storing tabular data with fields separated by tab characters, making it easy for cyber tools to parse and exchange structured records without a CSV parser's quoting complexity. , and HTML artifacts directly from the artifact page without invoking an agent; an agent's edit_artifact call that would overwrite a newer manual save is refused.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Run scheduled tasks and connector triggers on a model different from the agent's default — pick a cheaper model for frequent checks and a stronger one for heavier reports — via the task or trigger dialog. Not checked yet Procedure drafts are now benchmarked automatically by replaying the agent runs they were built from, so a draft reaches approval-ready or goes live without a manual benchmark run; the review panel shows queued, running, or failed status. Not checked yet Tunnel connectors now support optional liveness and readiness probes to distinguish a responsive connector from one with an established tunnel session, an optional Prometheus-compatible metrics endpoint covering connector readiness, endpoint connectivity, and connection failures, and optional JSON logs with timestamp, severity, and message fields; text remains the default and now uses key=value fields. Not checked yet
3 more in Everything
└──▷ BREAKING ON UPGRADE
!
The Kubernetes operator now requires at least 4096 MiB of memory per slow-pool worker on `components.topicCpu` (up from 2048 MiB); any `RunlayerInstance` with `topicCpu.gunicornWorkers` set to 3 or more without a matching `resources` memory override fails validation after upgrade and is not reconciled — including version bumps — until memory is raised or worker count is lowered.
Our best guess
Runlayer adds scanner Hint action, customer web gateways, GitHub access MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools, Terraform resources, and a spend treemap in Analytics︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Keep a specific MCP client on the search-based tool flow instead of receiving connector tools directly.
copy
$ X-Runlayer-Tool-Exposure: force-initial
Scope a Deny policy to writes inside a specific folder by reading a nested object field in the payload.
yaml
copy
payload.folder.id
Manage agent GitHub access from any AI client with the new MCP tools get_agent_github_access, grant_agent_github_access, and revoke_agent_github_access.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Add runlayer_secret_store, runlayer_agent_webhook, and runlayer_agent_notification_route Terraform resources to manage external secret stores, inbound webhooks, and failure notification routes as code. Not checked yet Set a scanner to Hint to let a flagged tool call through while warning the agent that the output may be untrusted — MCP results carry the warning in _meta["com.runlayer/hint"], with the warning text editable under Edit security messaging — and choose how to handle clients that can't apply Mask or Hint, Block (default) or Alert, via the new settings under Security Scanners → Settings → Clients that can't apply Mask or Hint. Not checked yet Control connector tool exposure in the Runlayer Plugin by sending X-Runlayer-Tool-Exposure: force-initial to keep a client on the search-based flow, or disable flat mode for self-hosted deployments with FF_DISABLE=plugins-flat-mode (or enable it with FF_ENABLE=plugins-flat-mode for deployments still on WorkOS feature flags). Not checked yet Route agent internet traffic through your own HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. web gateway, applying its filtering and logging alongside Runlayer's network policy. Not checked yet
+5 more
show less
Write policy conditions that read fields inside object arguments with payload.<arg>.<field> (for example payload.folder.id) to scope a Deny rule to a single folder. Not checked yet Page through agent run trace events with the new events_after_seq input on get_agent_run_trace, passing each page's next_after_seq back until has_more is false. Not checked yet Turn on Chrome extension updates from your organization's update URL in Settings → AI Watch → Manage settings → Browser extension. Not checked yet Analytics Spend tab now shows a treemap of spend broken down by department, agent, model, or user, with drill-down to entity spend details. Not checked yet Agent Monitor Tokens tile now shows cache reads and cache writes as separate line items. Not checked yet
Manage agent GitHub access from any AI client with the new MCP tools get_agent_github_access, grant_agent_github_access, and revoke_agent_github_access.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Add runlayer_secret_store, runlayer_agent_webhook, and runlayer_agent_notification_route Terraform resources to manage external secret stores, inbound webhooks, and failure notification routes as code. Not checked yet Set a scanner to Hint to let a flagged tool call through while warning the agent that the output may be untrusted — MCP results carry the warning in _meta["com.runlayer/hint"], with the warning text editable under Edit security messaging — and choose how to handle clients that can't apply Mask or Hint, Block (default) or Alert, via the new settings under Security Scanners → Settings → Clients that can't apply Mask or Hint. Not checked yet Route agent internet traffic through your own HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. web gateway, applying its filtering and logging alongside Runlayer's network policy. Not checked yet Turn on Chrome extension updates from your organization's update URL in Settings → AI Watch → Manage settings → Browser extension. Not checked yet
+1 more
show less
Analytics Spend tab now shows a treemap of spend broken down by department, agent, model, or user, with drill-down to entity spend details. Not checked yet
4 more in Everything
└──▷ BREAKING ON UPGRADE
!
`get_agent_run_trace` no longer returns a total count with a run's raw events; page with the new `events_after_seq` input, passing each page's `next_after_seq` back until `has_more` is false.
Our best guess
!
While a run is still in progress, `GET /agents/{agent_id}/runs` and `GET /agents/{agent_id}/runs/timeline` return `event_count`, token counts, and `total_cost_usd` as `null` until the run ends and usage is recorded.
Our best guess
!
`afterTool` and `runTool` in `@runlayer/hooks-sdk` now throw `RunlayerBlockedError` when a Mask or Hint scanner would rewrite tool output and the fallback is Block — previously the original unmasked output was passed through.
Our best guess
Runlayer adds Artifacts (stable versioned links) and Apps (agent-built internal tools with owner-approved actions, a built-in database, scoped MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. access, and an audit log).
Runlayer now publishes agent-generated outputs as Artifacts — stable, versioned links requiring company sign-in that update in place when you ask the agent to revise them, with sharing controlled by people, groups, teams, or roles. Not checked yet Runlayer now supports Apps — Artifacts with an owner-approved action list, a built-in database, and live access to business systems through existing MCP connectors, with no API keys stored in the app and each call running under the viewer's own permissions. Not checked yet An Admin view lets app owners review every action before it runs, showing which MCP connectors it calls and whose access it uses; a changed action waits for re-approval while the last approved version continues to serve. Not checked yet Every call an App makes is written to the Runlayer audit log alongside existing agent and MCP activity, recording which app, which action, which connector, and on whose behalf. Not checked yet
4 details in Everything
Runlayer adds session search, raw file reads for Microsoft 365, and new agent configuration policy groupings︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Prevent users on a self-hosted deployment from seeing an empty session search UI before the indexer is running.
env
copy
SESSIONS_SEARCH_API_ENABLED=false
Retrieve the exact bytes of a large file from SharePoint when you need the raw binary content rather than a converted representation.
json
copy
{
"tool": "sharepoint_read_file",
"arguments": {
"file_id": "<file_id>",
"format": "raw",
"allow_large_file": true
}
}
Search agent sessions from the Sessions page on Runlayer-hosted deployments, or let agents search them through the Runlayer MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools; results cover sessions from October 29, 2026 onward.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet On self-hosted deployments, enable session search by running the session search indexer in write mode; set SESSIONS_SEARCH_API_ENABLED=false on the backend to hide the search UI until the indexer is ready. Not checked yet Read exact file bytes from OneDrive and SharePoint with format: "raw" on onedrive_read_file and sharepoint_read_file, and read files up to 50 MB with allow_large_file. Not checked yet
Search agent sessions from the Sessions page on Runlayer-hosted deployments, or let agents search them through the Runlayer MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools; results cover sessions from October 29, 2026 onward.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet On self-hosted deployments, enable session search by running the session search indexer in write mode; set SESSIONS_SEARCH_API_ENABLED=false on the backend to hide the search UI until the indexer is ready. Not checked yet
1 more in Everything
└──▷ BREAKING ON UPGRADE
!
The Slack channel setting in agent configuration policies is renamed to 'Slack outside approved channels'.
Our best guess
Runlayer adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. spend-breakdown tools, DNS filter block reporting for egress proxy, and Claude Desktop routing through the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. Gateway︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Read spend data from the Runlayer MCP using three new tools — get_spend_cost_breakdown (spend per provider and model), get_spend_people_usage (the All users list), and get_spend_department_usage (spend by department) — each requiring the View company metrics permission.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Runlayer Plugin's search_tools now returns readOnlyHint, destructiveHint, idempotentHint, and openWorldHint as annotations in nested mode, letting agents select read-only tools without enumerating every connector. Not checked yet Self-hosted egress proxy now accepts a list of DNS filter block answers so blocked agent destinations are refused immediately and recorded in response and audit logs. Not checked yet AI Watch now routes eligible users' Claude Desktop through the LLM Gateway when LLM routing is on, with short-lived per-device tokens, budgets, and Sessions. Not checked yet
Read spend data from the Runlayer MCP using three new tools — get_spend_cost_breakdown (spend per provider and model), get_spend_people_usage (the All users list), and get_spend_department_usage (spend by department) — each requiring the View company metrics permission.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
3 more in Everything
Runlayer adds update_skill_shares and list_skill_shares MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools for managing skill access, and metric definitions on Control and Usage dashboards.
Share skills with teams or people over the Runlayer MCP using the new update_skill_shares tool, which sets permissions or removes access under the same rules as the skill's Share dialog. Not checked yet Inspect current skill access over the Runlayer MCP using the new list_skill_shares tool, with share counts also surfaced in list_skills. Not checked yet Every number card on Control and Usage now shows an ⓘ metric definition explaining what it counts and what the trend arrow compares to. Not checked yet
3 details in Everything
Runlayer adds per-run LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. spend limits ($250 default), agent-change approval flows in chat, Kubernetes audit consumer shard leasing, and in-conversation skill editing.
Agents now stop a run once it has spent $250 (or the remaining daily/weekly budget, whichever is lower) when LLM traffic flows through the Runlayer LLM gateway, with the run failing with a named limit error and the agent owner receiving a Slack DM when Budget alerts are on. Not checked yet Runlayer now asks the person in a conversation to approve any agent-initiated change to its own setup (connectors, skills, instructions, subagents, schedules, triggers, webhooks, Slack settings, channel monitors, or adding a workspace connector) before applying it, including changes requested over iMessage and approved in Runlayer. Not checked yet The Kubernetes audit consumer now leases its Kinesis shards using DynamoDB checkpointing; custom {instance}-audit-consumer IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. policies must allow dynamodb:Query and dynamodb:UpdateItem on the checkpoint table, and dynamodb:DeleteItem scoped to dynamodb:LeadingKeys = workers#*. Not checked yet Handing a task to another agent now returns in about one second instead of about 20 seconds. Not checked yet Agents can now create and update skills directly in conversation without requiring an explicit Runlayer connector or a ZIP file upload. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
!
If you wrote a custom `{instance}-audit-consumer` IAM policy instead of using the published sample, you must now add `dynamodb:Query` and `dynamodb:UpdateItem` on the checkpoint table and `dynamodb:DeleteItem` scoped to `dynamodb:LeadingKeys = workers#*`, or the consumer will log `kinesis_consumer_missing_permissions` at startup and exit.
Our best guess
! Legacy macOS MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. scripts (AI Watch and Hooks) must be regenerated and redeployed: they now run uv and the Runlayer CLI as the signed-in user instead of root and keep the enrollment key off the command line.
Runlayer 2.0.0 adds client-IP enforcement via proxy headers and tightens session isolation to block cross-session manipulation︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Tell Runlayer how many proxies prepend to X-Forwarded-For in your self-hosted deployment so IP-range policies and rate limits see the correct client address.
.env
copy
PRE_AUTH_TRUSTED_PROXY_HOPS=2
Set PRE_AUTH_TRUSTED_PROXY_HOPS (Terraform: trusted_proxy_hops) to the number of appending proxies in self-hosted deployments with more than one, and CLIENT_IP_HEADER is now honoured only when it carries a single IP address.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet A tool call carrying someone else's session ID (via hook payload or x-runlayer-session-id header) can no longer block that session, inject scan results, add security events, or mark an operator Stop as having taken effect in that session's history. Not checked yet
Set PRE_AUTH_TRUSTED_PROXY_HOPS (Terraform: trusted_proxy_hops) to the number of appending proxies in self-hosted deployments with more than one, and CLIENT_IP_HEADER is now honoured only when it carries a single IP address.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 more in Everything
└──▷ BREAKING ON UPGRADE
!
The operator no longer injects `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, or `AWS_CA_BUNDLE` on MCP pods; ExtendDB SigV4 now uses AWS profile `extenddb` via `EXTENDDB_AWS_PROFILE` (credentials under `/etc/extenddb-aws`, CA on the profile). Custom `enable_db` images must build the DynamoDB client from that profile when `EXTENDDB_AWS_PROFILE` is set.
Our best guess
!
Client IP can no longer be chosen by the caller: rate limits, `ip_address` on audit events, and the `meta.request.ip` policy field now use the address your own proxy appended to `X-Forwarded-For`, never an earlier caller-supplied entry. IP-range policies and per-IP rate limits (including device enrollment) now see one address per office or fleet rather than per workstation.
Our best guess
!
Self-hosted deployments with more than one appending proxy must set `PRE_AUTH_TRUSTED_PROXY_HOPS` (Terraform: `trusted_proxy_hops`) to match; `CLIENT_IP_HEADER` is honoured only when it carries a single IP address.
Our best guess
!
A tool call sending someone else's session ID can no longer block that session via 'Block later tool calls when any scanner blocks', add scan results or security events to that session, or mark an operator Stop as having taken effect in it. Hook events naming another session are not recorded into it.
Our best guess
Runlayer adds iMessage delivery for scheduled agent runs, Outlook folder management, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. budget email alerts, and a model_version field in ToolGuard score API responses.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Configure LLM budget email alerts so administrators are notified before spend hits the full budget ceiling.
📍 In Settings, go to LLM Gateway › Usage rules, open an existing usage rule that has a total budget set, then open Email alerts and add the percentages (for example 50, 80, 100) at which administrators should be emailed.
ToolGuard score API responses now include model_version, identifying the model version expected to score the request — include it when reporting scan results to Runlayer.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Set email alerts for LLM budget thresholds by configuring percentages under Settings → LLM Gateway → Usage rules → Email alerts ; alerts fire once per percentage per budget window to organization settings administrators. Not checked yet The Microsoft Outlook connector now supports creating mail folders, moving folders, and moving messages between folders — redeploy the connector to get the new tools. Not checked yet Scheduled agent runs set up from an iMessage thread now post each run's result back via iMessage, and those set up from a Slack thread post results back in that thread. Not checked yet
ToolGuard score API responses now include model_version, identifying the model version expected to score the request — include it when reporting scan results to Runlayer.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Set email alerts for LLM budget thresholds by configuring percentages under Settings → LLM Gateway → Usage rules → Email alerts ; alerts fire once per percentage per budget window to organization settings administrators. Not checked yet
2 more in Everything
Runlayer adds compact tool discovery control, redacted session timelines, skill risk policy on API writes, and Terraform-managed skills in v1.41.0︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Keep a Runlayer Plugin in compact tool-discovery mode for an agent harness agent harness The software around an AI agent that manages its tools, execution loop, state and limits. It determines how the model's proposed actions are run and checked. that loads all tool definitions up front, avoiding the full connector tool listing.
copy
$ curl -H 'X-Runlayer-Tool-Exposure: force-initial' https://<your-runlayer-host>/mcp
Define and version-control a skill and its files in Terraform so that app edits surface as plan diffs and a blocked risk policy fails the apply.
main.tf
copy
resource "runlayer_skill" "data_lookup" {
name = "data-lookup"
namespace = "finance"
path = "skills/data-lookup"
files = {
"skill.yaml" = file("skills/data-lookup/skill.yaml")
"handler.py" = file("skills/data-lookup/handler.py")
}
}
Control compact tool discovery in agent harnesses agent harnesses The software around an AI agent that manages its tools, execution loop, state and limits. It determines how the model's proposed actions are run and checked. by sending X-Runlayer-Tool-Exposure: force-initial from any client to keep Runlayer Plugin on search_tools / execute_tool instead of listing every connector tool.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Runlayer now drops X-Runlayer-User-Email , X-Runlayer-Identity-Token , and other identity-forward headers when a client sends them, so an upstream server only ever sees the ones Runlayer injects; other custom headers (such as a correlation ID) still pass through. Not checked yet Skill risk policy now runs on API writes — creating or updating a skill's files via the API (including from Terraform) is rejected when the skill risk policy blocks the content, and nothing is saved when a write is blocked. Not checked yet Redacted sessions and agent runs now preserve more of their data instead of hiding it: the API and the get_session MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool return the full event timeline (times, event types, tool names, model, tokens) with ***REDACTED*** in place of prompts, responses, tool input/output, and page URLs; the list_sessions and search_session_events MCP tools no longer include the first prompt or generated title in list and search rows; and the get_agent_run_trace MCP tool keeps its steps with placeholder text instead of hiding the timeline entirely. Not checked yet Manage skills and their complete file sets as code with the new runlayer_skill resource in the Terraform provider; changes made in the app appear as a plan diff, and a file set blocked by your skill risk policy fails the apply. Not checked yet
+3 more
show less
Terraform provider now marks manual_oauth_client_secret and broker_vendor_client_secret on runlayer_server as sensitive, hiding them in plan and apply output; module outputs that reference them require sensitive = true. Not checked yet Kubernetes operator now rejects MCP servers that combine enable_db with an IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. annotation (eks.amazonaws.com/role-arn) on the MCP ServiceAccount, setting ExtendDBReady=False / IRSAConflict and leaving ExtendDB AWS env off the pod. Not checked yet Google Docs connectors now support copying existing templates with native formatting preserved, inspecting document structure and styles, and attaching comments to specific text ranges — requires redeploying existing Google Docs connectors. Not checked yet
Control compact tool discovery in agent harnesses agent harnesses The software around an AI agent that manages its tools, execution loop, state and limits. It determines how the model's proposed actions are run and checked. by sending X-Runlayer-Tool-Exposure: force-initial from any client to keep Runlayer Plugin on search_tools / execute_tool instead of listing every connector tool.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Runlayer now drops X-Runlayer-User-Email , X-Runlayer-Identity-Token , and other identity-forward headers when a client sends them, so an upstream server only ever sees the ones Runlayer injects; other custom headers (such as a correlation ID) still pass through. Not checked yet Manage skills and their complete file sets as code with the new runlayer_skill resource in the Terraform provider; changes made in the app appear as a plan diff, and a file set blocked by your skill risk policy fails the apply. Not checked yet Terraform provider now marks manual_oauth_client_secret and broker_vendor_client_secret on runlayer_server as sensitive, hiding them in plan and apply output; module outputs that reference them require sensitive = true. Not checked yet Kubernetes operator now rejects MCP servers that combine enable_db with an IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. annotation (eks.amazonaws.com/role-arn) on the MCP ServiceAccount, setting ExtendDBReady=False / IRSAConflict and leaving ExtendDB AWS env off the pod. Not checked yet
3 more in Everything
└──▷ BREAKING ON UPGRADE
!
Runlayer now drops `X-Runlayer-User-Email`, `X-Runlayer-Identity-Token`, and other identity-forward headers sent by a client — any upstream server or workflow that relied on forwarding these caller-supplied headers will no longer receive them.
Our best guess
!
`manual_oauth_client_secret` and `broker_vendor_client_secret` on `runlayer_server` are now marked sensitive in Terraform; module outputs that reference them must add `sensitive = true` or the apply will fail.
Our best guess
!
MCP servers on Kubernetes that combine `enable_db` with an IRSA annotation (`eks.amazonaws.com/role-arn`) on the MCP ServiceAccount are now rejected by the operator (`ExtendDBReady=False` / `IRSAConflict`); remove one or the other to restore functionality.
Our best guess
Runlayer 1.40.0 adds rate-limit policies, artifact secret scanning secret scanning Checking files, code or other data for exposed credentials such as passwords, API keys and tokens. Findings help teams remove the secret and revoke or rotate it. , waterfall agent timelines, voice over iMessage, and GPT-6.1 Terra support.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Cap a noisy connector to 30 tool calls per minute per session to prevent runaway agents from exhausting API quotas.
📍 In the Runlayer console, go to the connector's Policies tab, create a new policy, set Action to Rate limit , choose the '30 calls per minute per session' template, then save. Calls over the limit are refused and appear in the audit log as Tool Call Rate Limited .
Set a workspace-wide artifact auto-delete rule with a Keep forever override for a sensitive reports folder, so idle drafts are cleaned up while compliance artifacts are retained.
📍 In the Runlayer console, go to Settings → Artifacts, enable the workspace-wide auto-delete rule, then add a per-folder override for the Reports folder set to Keep forever , and save.
Adds rate-limit policies letting admins cap tool-call frequency per connector — for example 100 calls per hour per user or 30 calls per minute per session — with Rate limit as a policy action, two rate-limit templates, per-policy badge display, and refused calls logged as Tool Call Rate Limited in the audit log.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Blocks artifact publishing when content contains an obvious API key, access token access token A credential that authorizes a client to use a service or API. It usually has limited permissions and a lifetime; anyone holding it may be able to use those permissions. , or private key, telling the agent to redact and republish. Not checked yet Adds Timeline / Waterfall switch to the agent run drawer, charting each tool call as a bar at its real offset from run start with subagent steps nested under their call. Not checked yet Adds GPT-6.1 Terra to the agent model picker for OpenAI providers, with reasoning, image input, and Spend pricing. Not checked yet Adds voice message support over iMessage: send a voice message from Messages and the agent transcribes and replies using the workspace's OpenAI provider. Not checked yet
+5 more
show less
Adds workspace-wide artifact auto-delete policies in Settings → Artifacts , with per-folder overrides (for example Keep forever for a folder), archiving idle artifacts first and deleting 30 days later. Not checked yet Deactivated users' MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. -managed devices now block tool calls in Protect and Enforce modes via AI Watch hooks; devices Runlayer cannot match to a user receive the organization's Enforce tool-type blocklist. Not checked yet Scopes plugin, skill install counts on the Metrics page and a connector's most-active-users list to organization-only activity, and rejects date ranges older than 90 days. Not checked yet Adds Clio v1.0 session-topic filter (behind session-topics-clio feature flag) listing 63 Clio subtopics — for example Research and prepare for sales engagements — alongside existing topics on the Sessions page. Not checked yet Session compaction now auto-retries parked sessions after upgrades (at most once per day, up to three retries per session), eliminating most manual support resets. Not checked yet
Adds rate-limit policies letting admins cap tool-call frequency per connector — for example 100 calls per hour per user or 30 calls per minute per session — with Rate limit as a policy action, two rate-limit templates, per-policy badge display, and refused calls logged as Tool Call Rate Limited in the audit log.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Blocks artifact publishing when content contains an obvious API key, access token access token A credential that authorizes a client to use a service or API. It usually has limited permissions and a lifetime; anyone holding it may be able to use those permissions. , or private key, telling the agent to redact and republish. Not checked yet Adds Timeline / Waterfall switch to the agent run drawer, charting each tool call as a bar at its real offset from run start with subagent steps nested under their call. Not checked yet Adds voice message support over iMessage: send a voice message from Messages and the agent transcribes and replies using the workspace's OpenAI provider. Not checked yet Adds workspace-wide artifact auto-delete policies in Settings → Artifacts , with per-folder overrides (for example Keep forever for a folder), archiving idle artifacts first and deleting 30 days later. Not checked yet
5 more in Everything
└──▷ BREAKING ON UPGRADE
!
Incident API and MCP tool requests for a time range longer than 7 days now return only the 7 days ending at the range's end date; callers must request longer ranges in 7-day steps.
Our best guess
Runlayer 1.39.0 adds hosting-type filtering for connectors, cookie masking in approvals, federated agent server scoping, and a 36 MiB MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. request size cap.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Filter the Connectors page to show only connectors you can self-host, to audit your local attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. .
📍 In the Runlayer web app, go to Connectors, open the Hosting filter, and select Local .
Adds a Hosting filter on the Connectors page to narrow connectors by type: Local , Remote , or Runlayer Deploy .︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Applies cookie masking in approval requests across the web app, Slack, and Microsoft Teams for every cookie field, including fields such as auth_cookie and session_cookie. Not checked yet Enforces server scoping for federated agent accounts (those signed in through an identity provider identity provider A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. ): tokens are restricted to the servers they were issued for, the setting shows as on and locked, and existing API keys on those accounts are refused. Not checked yet Limits MCP endpoint request bodies to 36 MiB, returning HTTP 413 for anything larger; sized to allow a full 25 MB artifact upload via create_artifact / update_artifact. Not checked yet Restricts connector URL redirects to within the server's own origin — redirects to another host, another port, or from https:// to http:// are not followed; a same-host http:// → https:// upgrade is still permitted. Not checked yet
+2 more
show less
Replaces the Official badge with a Third-party icon on connector cards to mark connectors not built by the service's vendor; removes the Secure badge. Not checked yet Restricts local stdio servers to run only on the user's machine via the Runlayer CLI — Runlayer no longer starts a local stdio server on its own servers when called through the proxy URL. Not checked yet
Adds a Hosting filter on the Connectors page to narrow connectors by type: Local , Remote , or Runlayer Deploy .︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Limits MCP endpoint request bodies to 36 MiB, returning HTTP 413 for anything larger; sized to allow a full 25 MB artifact upload via create_artifact / update_artifact. Not checked yet
5 more in Everything
└──▷ BREAKING ON UPGRADE
!
Federated agent accounts (signed in through an identity provider) now have server scoping permanently on and locked — existing API keys on those accounts are refused at the server level; revoke any keys you no longer need before unbinding the account from its identity provider.
Our best guess
!
Connector URLs that redirect to another host, another port, or from `https://` down to `http://` are no longer followed — update connector configurations to use the final destination URL directly.
Our best guess
!
MCP endpoint requests with a body larger than 36 MiB are rejected with HTTP 413 — payloads exceeding this limit must be reduced or split.
Our best guess
!
Runlayer no longer starts a local stdio server on its own servers when called through the proxy URL — local stdio servers must be run on the user's machine via the Runlayer CLI.
Our best guess
Runlayer 1.38.0 adds runlayer_agent_trigger in Terraform and exposes MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. resources/templates/list through the gateway.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Define an agent's poll trigger as Terraform code so it is version-controlled and repeatable across environments.
hcl
copy
resource "runlayer_agent_trigger" "nightly_poll" {
agent_id = runlayer_agent.my_agent.id
trigger_type = "poll"
event_key = "nightly"
account_id = "<account_id>"
}
Verify that a connector's MCP resource templates are now visible to clients via the Runlayer gateway.
copy
$ curl -X POST https://<your-runlayer-host>/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"resources/templates/list","params":{"connector_id":"<connector_id>"}}'
Adds runlayer_agent_trigger Terraform resource to manage an agent's event and poll triggers as code; changing trigger_type, event_key, or account_id replaces the trigger (requires agent triggers enabled for the organization).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Exposes MCP resources/templates/list through the Runlayer gateway so clients can list a connector's resource templates from upstream servers. Not checked yet Admins can now delete a connector directly from the ⋯ menu on its connector page, not only from Manage connectors. Not checked yet Renames the personal tab on Agents, Skills, Plugins, and Artifacts pages to Owned by me . Not checked yet
Adds runlayer_agent_trigger Terraform resource to manage an agent's event and poll triggers as code; changing trigger_type, event_key, or account_id replaces the trigger (requires agent triggers enabled for the organization).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Exposes MCP resources/templates/list through the Runlayer gateway so clients can list a connector's resource templates from upstream servers. Not checked yet
2 more in Everything
Runlayer 1.36.0 lets skill admins detach skills from their source repos and improves Go agent follow-through and ToolGuard recommendations.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Enables skill owners and skill admins to detach a skill published with runlayer skills push from its source repository so it can be edited directly in Runlayer, preserving files, version history, and sharing.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Allows editors to detach a skill once its owner is deactivated, preventing orphaned skills when a publisher leaves. Not checked yet After detachment, later pushes from the source repository no longer update the skill, automatic updates are turned off, and pushing a skill with the same name fails until one is renamed. Not checked yet Improves the Go agent to check its own work before marking tasks complete, wait on slow results such as CI or deploys, report the real outcome, and support timed reminders (e.g. 'ping me in 30 min'). Not checked yet Retrains the ToolGuard tool-removal model so recommendations are scoped to the tools a deployment actually sends and are proportionate to each agent's tool set, rather than occasionally suggesting removing every tool. Not checked yet
Enables skill owners and skill admins to detach a skill published with runlayer skills push from its source repository so it can be edited directly in Runlayer, preserving files, version history, and sharing.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
4 more in Everything
└──▷ BREAKING ON UPGRADE
!
Pushing a skill with the same name as an already-detached skill fails until one of them is renamed.
Our best guess
Runlayer 1.35.0 adds bulk agent deletion, .xlsx .xlsx The file format used by Microsoft Excel for spreadsheets, based on the Open XML standard. Cyber tools use it to ingest or export structured tabular data in a format analysts already work with. spreadsheet previews, Stop-effect visibility, and compliance import scope clarity.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Clean up a large fleet of decommissioned agents — including their schedules, webhooks, and Slack apps — in a single action rather than one at a time.
📍 In the Runlayer console, go to Agents → Inventory tab, check the disabled agents you want to remove, then choose Delete from the bulk-action menu.
Deploy the AI Watch Chrome extension via a computer-level MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. profile on macOS by copying the generated ExtensionSettings entry directly from Runlayer.
📍 In the Runlayer console, go to Settings → Browser extension, enable 'Chrome extension installed by your policy (macOS)', then copy the ExtensionSettings entry shown and paste it into your MDM Chrome policy profile.
Adds bulk deletion of disabled agents from the Agents Inventory tab — select agents, choose Delete, and their schedules, webhooks, and Slack apps are removed in one action; enabled agents are left untouched.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds read-only .xlsx spreadsheet previews in the artifact viewer, with a tab per sheet and the workbook's number formats, colors, and merged cells, so agents' Excel outputs are readable without downloading. Not checked yet Settings → Agent session monitoring now clarifies that a Claude or ChatGPT compliance import covers every user in the connected organization or workspace, including people who have never signed in to Runlayer. Not checked yet The Chrome extension policy page (macOS, AI Watch) now surfaces the Runlayer extension ID, the organization's update URL, and a ready-to-copy ExtensionSettings entry for computer-level MDM Chrome profiles. Not checked yet An agent whose face is an emoji now displays that emoji as its Slack app icon instead of the Runlayer logo. Not checked yet
+4 more
show less
Shared environment variable tooltips on hosted connectors now explain whether a value is shared across all users or entered individually per user. Not checked yet Access tooltips on shared agents now describe what access level you hold and who to ask for Can edit permission when a trigger, scheduled task, or connector cannot be added. Not checked yet Admins can now skip all remaining setup checklist steps at once instead of one by one. Not checked yet Agents now automatically publish files they create (decks, documents, spreadsheets, PDFs) to Artifacts and reply with a link, instead of reporting no way to share them. Not checked yet
Adds bulk deletion of disabled agents from the Agents Inventory tab — select agents, choose Delete, and their schedules, webhooks, and Slack apps are removed in one action; enabled agents are left untouched.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds read-only .xlsx spreadsheet previews in the artifact viewer, with a tab per sheet and the workbook's number formats, colors, and merged cells, so agents' Excel outputs are readable without downloading. Not checked yet
7 more in Everything
Runlayer 1.34.0 adds artifact search in Launcher, audit-log entries for agent run cancels, and Chrome-policy-managed AI Watch extension installs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Use your existing Chrome fleet policy to deploy AI Watch without letting Runlayer overwrite or shadow your other managed extensions (e.g. Okta).
📍 In AI Watch browser extension settings, enable Chrome extension installed by your policy , then add the Runlayer entry to your Google Admin or MDM Chrome extension policy. AI Watch will write no Chrome policy of its own, and the device health check will confirm your policy installed the extension.
Adds Chrome extension installed by your policy toggle in AI Watch browser extension settings, letting you install AI Watch via Google Admin, Chrome Enterprise Core, or MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. instead of having AI Watch write its own Chrome policy — preventing it from overwriting yours and removing extensions like Okta.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds audit log entries when an agent run is stopped via the API, web app, or Slack, recording who stopped it and whether the sandbox halted. Not checked yet Stopping a session now also cancels all Runlayer Agents runs inside it, including runs you do not own, and only reports Terminated once the agent's runtime confirms. Not checked yet Adds artifact search to the Launcher — find accessible artifacts by title or filename, open them directly, and return to recently opened files. Not checked yet Evaluation replays are now isolated to your organization — a replay can no longer list or call a connector belonging to another organization. Not checked yet
Adds Chrome extension installed by your policy toggle in AI Watch browser extension settings, letting you install AI Watch via Google Admin, Chrome Enterprise Core, or MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. instead of having AI Watch write its own Chrome policy — preventing it from overwriting yours and removing extensions like Okta.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds audit log entries when an agent run is stopped via the API, web app, or Slack, recording who stopped it and whether the sandbox halted. Not checked yet Adds artifact search to the Launcher — find accessible artifacts by title or filename, open them directly, and return to recently opened files. Not checked yet
2 more in Everything
1.33.0 - Artifact notifications and resilient Go (2026-10-22)
Oct 22, 2026
·
issue 117
Runlayer 1.33.0 adds an Auto-sync API, v1 deprecation headers, and artifact comment notifications via Slack/Teams.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Audit which of your automation scripts still call unsupported v1 endpoints by inspecting the Deprecation header returned on any v1 API-key request.
copy
$ curl -si -H 'Authorization: Bearer <api-key>' https://api.runlayer.com/v1/<endpoint> | grep -i deprecation
Idempotently enable auto-sync for a specific connector by type and ID without risking duplicate writes.
copy
$ curl -X PUT https://api.runlayer.com/v2/auto-sync/<type>/<id> \
-H 'Authorization: Bearer <api-key>' \
-H 'Content-Type: application/json' \
-d '{"auto_sync": true}'
Adds an Auto-sync API to read, set, or remove a connector, plugin, or skill's device auto-sync setting by its type and ID, using an idempotent PUT.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Deprecation response header to API-key calls made to v1 endpoints, making it easy to identify scripts that still depend on unsupported v1 automation paths. Not checked yet Adds artifact comment notifications via Slack or Teams: mentions, replies, and comments on owned artifacts now trigger a message from the Runlayer assistant linking directly to the artifact. Not checked yet Go now retries failed lookups via alternate routes, checks whether a failed write landed before retrying (preventing duplicates), cites the source of each number in its answers, and executes the next step rather than offering it. Not checked yet
Adds an Auto-sync API to read, set, or remove a connector, plugin, or skill's device auto-sync setting by its type and ID, using an idempotent PUT.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Deprecation response header to API-key calls made to v1 endpoints, making it easy to identify scripts that still depend on unsupported v1 automation paths. Not checked yet Adds artifact comment notifications via Slack or Teams: mentions, replies, and comments on owned artifacts now trigger a message from the Runlayer assistant linking directly to the artifact. Not checked yet
1 more in Everything
1.32.0 - Sharing API and MCP session stops (2026-10-21)
Oct 21, 2026
·
issue 116
Runlayer 1.32.0 adds a Sharing API, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. session stop/clear tools, and Terraform resources for team members and group bindings.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Manage team membership and directory-group bindings as code in Terraform so role assignments are version-controlled and repeatable.
hcl
copy
resource "runlayer_team_member" "analyst" {
team_id = runlayer_team.soc.id
user_id = "user_abc123"
role = "member"
}
resource "runlayer_team_group_binding" "soc_ad_group" {
team_id = runlayer_team.soc.id
group_id = "dir_group_xyz"
}
Adds stop_session and clear_session_stop tools to the Runlayer MCP so agents and automation (e.g.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ SOAR SOAR Security orchestration, automation and response, coordinating incident workflows across tools. Playbooks can gather evidence, assign work or carry out approved response actions. playbooks) can stop a session and clear a stop; requires the same permission as the API, a reason is mandatory, and the audit log records whether the action came from the API or the MCP. Not checked yet Adds runlayer_team_member and runlayer_team_group_binding resources to Terraform provider 1.8.1, enabling role and directory-group membership to be managed as code; applying either resource adopts an already-existing membership or binding. Not checked yet Adds a Sharing API that reads, sets, or removes one principal's access to an agent, skill, or plugin with a single idempotent call keyed by principal. Not checked yet Adds Auto-review and Your review tabs to the run drawer, with draft notes preserved when switching between them. Not checked yet Expands PrivateLink PrivateLink An AWS networking feature that exposes a service over a private endpoint inside a VPC, so traffic never traverses the public internet, giving cyber tools a way to integrate with cloud services without opening public routes. support for Runlayer Deploy connectors beyond four connections, with additional connections using AWS rule capacity shared across deployments. Not checked yet
+1 more
show less
Moves session storage compaction to its own ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. service so heavy compaction no longer interrupts new session activity in the Sessions view. Not checked yet
Adds stop_session and clear_session_stop tools to the Runlayer MCP so agents and automation (e.g.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ SOAR SOAR Security orchestration, automation and response, coordinating incident workflows across tools. Playbooks can gather evidence, assign work or carry out approved response actions. playbooks) can stop a session and clear a stop; requires the same permission as the API, a reason is mandatory, and the audit log records whether the action came from the API or the MCP. Not checked yet Adds runlayer_team_member and runlayer_team_group_binding resources to Terraform provider 1.8.1, enabling role and directory-group membership to be managed as code; applying either resource adopts an already-existing membership or binding. Not checked yet Adds a Sharing API that reads, sets, or removes one principal's access to an agent, skill, or plugin with a single idempotent call keyed by principal. Not checked yet Adds Auto-review and Your review tabs to the run drawer, with draft notes preserved when switching between them. Not checked yet
2 more in Everything
└──▷ BREAKING ON UPGRADE
! Stopping a session via the API now requires a session Runlayer has already recorded — an unknown session ID is refused rather than silently creating a stop record.
1.31.0 - Go deliverables and session layer tags (2026-10-21)
Oct 21, 2026
·
issue 116
Runlayer 1.31.0 adds Go deliverable generation, session layer tags, bulk artifact deletion, and Kubernetes session materialization.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Identify which layer captured each turn in a multi-layer session to debug duplicate turns during an Agent runtime + LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway recording.
📍 In the Sessions view, open any recorded session → each prompt, response, and tool card now displays a layer tag (Agent runtime, LLM gateway, or Client hook) directly on the card.
Clean up stale artifacts in bulk instead of deleting them one at a time from the library.
📍 In the Artifacts library, check the checkboxes next to the artifacts you want to remove → select Delete selected to remove them all in one step.
Adds layer-capture tags to each prompt, response, and tool card in Sessions, showing which layer (Agent runtime, LLM gateway, or Client hook) captured a turn when more than one layer recorded it.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds bulk delete to the Artifacts library, letting you select multiple artifacts and remove them in one step. Not checked yet Adds the exact build commit with a copy button to Settings → General next to the version number. Not checked yet Go now builds and links the finished artifact — table, chart, one-page doc, or file — instead of describing it in chat when asked to compare options, show a trend, plan a trip, or send files. Not checked yet Moves session compaction to its own Deployment on Kubernetes via the Runlayer operator, isolating heavy session work from ingest and allowing Kinesis installs to scale both past one replica. Not checked yet
Adds layer-capture tags to each prompt, response, and tool card in Sessions, showing which layer (Agent runtime, LLM gateway, or Client hook) captured a turn when more than one layer recorded it.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds bulk delete to the Artifacts library, letting you select multiple artifacts and remove them in one step. Not checked yet Adds the exact build commit with a copy button to Settings → General next to the version number. Not checked yet
2 more in Everything
1.30.0 - Eval replay and Go follow-through (2026-10-21)
Oct 21, 2026
·
issue 116
Adds eval replay with recorded tool results, agent account OAuth connectors, improved Go follow-through, auto-saving run reviews, and an enhanced offline eval run picker.
Adds a Replay recorded results option under Tool mocking in agent evals, feeding each matching call its original recorded result so every replay sees identical data while remaining side-effect free. Not checked yet Adds an OAuth connector workflow for agent accounts so admins can attach a connector without linking their own credentials — each user then grants access with their own account. Not checked yet Go now continues completing unfinished parts of a request at the end of a turn instead of prompting whether it should, while still returning decisions involving money, access, data deletion, or messages to the user. Not checked yet Run reviews in the run drawer now auto-save Pass/Fail, notes, and expected output after a pause in typing or on drawer close, replacing the explicit Save button with a Saved indicator. Not checked yet Adds an offline eval run picker with search and filter by status, start date, or topic; shift-click range selection; quick picks for recent failures or topic spreads; and an Ask AI option that returns matching runs with reasons. Not checked yet
+1 more
show less
Agent owners now receive a Slack DM when their agent reaches adoption milestones of 3, 5, 10, 25 (and beyond) users, with a distinct message at each milestone. Not checked yet
6 details in Everything
1.29.0 - iMessage agents and recorder detection (2026-10-20)
Oct 20, 2026
·
issue 115
Adds iMessage agent channel, GitHub App integration for agents, ExtendDB NetworkPolicy NetworkPolicy A Kubernetes API object that defines which pods may send or receive traffic, enforced by the cluster's CNI plugin to give cyber tools namespace-level network segmentation without host firewall rules. isolation, RunlayerInstance CR image overrides, and semantic customer versioning.
Adds iMessage channel for agents: users can text an agent from Messages on iPhone, iPad, or Mac after linking their number to their Runlayer account; admins choose which agent answers the linked number. Not checked yet Adds GitHub App integration for agents: workspace admins can connect a GitHub App and grant agents access to selected repositories via short-lived tokens. Not checked yet Adds RunlayerInstance CR overrides for ExtendDB init/reset Jobs' helper container images (kubectl, Postgres client, AWS CLI) on self-hosted Kubernetes, removing the need to wait on an operator release. Not checked yet Adds ExtendDB ingress NetworkPolicy for self-hosted deployments that scopes ExtendDB to only the linked MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. namespace. Not checked yet Adds Postgres connection-budget sizing guidance and an image-bump/recovery runbook for self-hosted Kubernetes operators enabling ExtendDB. Not checked yet
+2 more
show less
Introduces semantic versioning for customer releases starting at 1.29.0: new major for breaking changes, new minor for new features, new patch for fixes only. Not checked yet Members can no longer remove themselves from a team; only a team owner or workspace admin can remove them, preventing accidental exit from AI Watch policies targeting that team. Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! The separate Goal achieved tile has been removed; goal outcomes and failure reasons are now only available in Agent Insights.
1.28.1575 - Computer-use detection and session stop (2026-10-20)
Oct 20, 2026
·
issue 115
Adds session stop controls (Shift+K), scoped agent token enforcement (FF_DISABLE/FF_ENABLE), credential revocation on run end, and redaction-aware stream replay.
Security, IT, and Super Admins can stop a live agent session and resume it from the Sessions page session drawer, or with Shift+K , with a required reason and full audit trail. Not checked yet Scoped agent or on-behalf-of tokens (requested with resource) now return 403 invalid_target on out-of-scope servers for all agent accounts; self-hosted operators control this with FF_DISABLE=agent-token-audience-enforcement or FF_ENABLE=agent-token-audience-enforcement. Not checked yet Agent run credentials are revoked the moment a run finishes rather than remaining valid until natural expiry. Not checked yet Agent run live-stream replay enforces workspace redaction rules; viewers must hold the unredact permission and confirm before content is replayed. Not checked yet Agents offer an inline connector card in chat when a needed app is missing, eliminating a settings-page detour. Not checked yet
+1 more
show less
Device check-ins and scans no longer write to the shared MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. configuration record, eliminating row contention for large fleets. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! Scoped agent or on-behalf-of tokens are now rejected with 403 invalid_target on servers outside their declared resource scope for ALL agent accounts — self-hosted operators can revert with FF_DISABLE=agent-token-audience-enforcement.! Exchanging a scoped agent token for an on-behalf-of token now requires a resource within the original token's scope; requests without one return 400 invalid_target.! The MDM configuration card's Last connected label and status badge are removed.! The Turn on Shadow AI detection onboarding step has been removed.
Runlayer agents can now be defined and scheduled as code via a Terraform provider with runlayer_agent and runlayer_agent_schedule resources.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Define an agent with least-privilege tool access and a network egress policy so security teams can review agent permissions like IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. in a pull request.
main.tf
copy
terraform {
required_providers {
runlayer = {
source = "downloads.runlayer.com/runlayer/runlayer"
version = "~> 1.5"
}
}
}
provider "runlayer" {}
resource "runlayer_agent" "release_notes" {
name = "release-notes"
prompt = trimspace(file("${path.module}/prompts/release-notes.md"))
model = "claude-sonnet-5"
servers = [{
server_id = runlayer_server.github.id
tool_names = ["list_pull_requests", "get_pull_request"]
}]
egress_policy = {
default_action = "deny"
allow = ["github.com", "*.githubusercontent.com"]
}
env = {
RELEASE_CHANNEL = "stable"
}
}
Attach a recurring cron schedule to an agent so it runs automatically every Monday morning — change the day with a one-line diff and a reviewed PR.
schedules.tf
copy
resource "runlayer_agent_schedule" "sprint_digest" {
agent_id = runlayer_agent.team["sprint-digest"].id
name = "Sprint digest"
input_prompt = "Summarize last week's closed issues for the team."
cron_expression = "0 9 * * 1"
schedule_semantics = "local_wall_clock"
timezone = "America/New_York"
}
Import an existing Runlayer agent into Terraform state by its UUID UUID A universally unique identifier, usually a 128-bit value used to identify an object across systems. It is designed to make independently generated identifiers unlikely to collide. so all future changes go through plan and review.
copy
$ terraform import runlayer_agent.support_triage 9f1c2b7e-...
Adds the runlayer_agent Terraform resource (with name, prompt, model, servers using per-connector tool_names, egress_policy, env, tags, example_prompts, and is_disabled, installable from downloads.runlayer.com/runlayer/runlayer version ~> 1.5), the runlayer_agent_schedule resource (since provider 1.5.0) for attaching a cron schedule via agent_id, cron_expression, schedule_semantics, and timezone, the runlayer_server and runlayer_policy resources for managing connectors and policies as code, and egress_policy support on runlayer_agent with default_action and allow fields for per-agent network access policy in version control.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds the runlayer_server Terraform data source to look up an existing connector by server_id for use in agent definitions, and the runlayer_agent Terraform data source exposing tool_count, skill_count, and env_keys for CI checks against existing agents. Not checked yet Supports terraform import runlayer_agent.<name> <uuid> to bring existing agents under Terraform management. Not checked yet Authenticates the provider via RUNLAYER_API_KEY and RUNLAYER_BASE_URL environment variables. Not checked yet New Terraform provider is available in beta for both Runlayer-hosted and self-hosted deployments, with the full schema under Help → Terraform Reference in the app. Not checked yet
5 details in Everything
1.28.1480 - Slack stop button and ADK telemetry (2026-10-17)
Oct 17, 2026
·
issue 112
Runlayer 1.28.1480 adds a Slack stop button for agents and Google ADK ADK Google's Agent Development Kit, an open-source framework for building and orchestrating AI agents; cyber tools use it to compose multi-agent workflows with built-in tool-calling and state management. session telemetry via a native Python plugin.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds a Slack stop button for agents that have their own Slack app, letting any authorized user halt all in-progress replies in a thread.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Google ADK session telemetry for Python agents via a native plugin (see Hooks SDK) that captures prompts, assistant responses, and tool activity in one conversation, with local tool enforcement and correlation to Runlayer MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. audits. Not checked yet Adds connector search highlighting in Manage connectors , including surfacing the matching description excerpt under the connector name when the match is in the description. Not checked yet Places the current user first, marked (you), in user filters across Sessions, Incidents, Audit Logs, and other list views. Not checked yet
Adds a Slack stop button for agents that have their own Slack app, letting any authorized user halt all in-progress replies in a thread.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Google ADK session telemetry for Python agents via a native plugin (see Hooks SDK) that captures prompts, assistant responses, and tool activity in one conversation, with local tool enforcement and correlation to Runlayer MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. audits. Not checked yet
2 more in Everything
1.28.1446 - Supported clients and card detection (2026-10-16)
Oct 16, 2026
·
issue 111
Runlayer 1.28.1446 adds full client visibility for AI Watch policy pickers and connector request approvals via existing shared connectors.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Check which AI Watch clients and minimum versions are enforceable before authoring a new Enforce or Protect policy.
📍 In the Runlayer console, go to Manage → Endpoints → View supported clients to see every client AI Watch can protect, its minimum required version, and whether enforcement blocks before the tool runs.
Approve an incoming connector request without granting duplicate access when the requester already has access to one of your shared connectors.
📍 In the Runlayer console, go to Inbox, open the connector request, select an existing connector the requester already has access to (shown as Has access ), and approve — no additional policy is created.
The View supported clients dialog under Manage → Endpoints now lists every client AI Watch hooks can protect and enforce, including each client's minimum version and whether it blocks before the tool runs only.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet The Enforce and Protect built-in policy pickers now offer the full AI Watch supported client list. Not checked yet Approve a new connector request using a connector you already built and shared; existing connectors the requester can already access show as Has access and approve the request without adding another policy. Not checked yet
The View supported clients dialog under Manage → Endpoints now lists every client AI Watch hooks can protect and enforce, including each client's minimum version and whether it blocks before the tool runs only.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Approve a new connector request using a connector you already built and shared; existing connectors the requester can already access show as Has access and approve the request without adding another policy. Not checked yet
1 more in Everything
1.28.1407 - Detect agents inside IDEs (2026-10-16)
Oct 16, 2026
·
issue 110
Runlayer Detect now inventories IDE-native AI agents and their MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers, and connector policies gain per-tool granularity.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Verify that Xcode 26.3+ CodingAssistant MCP servers are now visible in your Detect inventory after upgrading — agents in that folder were previously missed entirely.
📍 In the Runlayer console, go to Detect and filter by IDE to confirm Claude and Codex agents running from the Xcode CodingAssistant folder appear in the agent inventory.
Detects IDE-native AI agents that were previously invisible — including Claude and Codex agents in Xcode 26.3+ (from its own CodingAssistant folder), Visual Studio Copilot agent mode, JetBrains AI Assistant, Gemini in Android Studio, GitHub Copilot for Xcode and Eclipse, Firebender, Positron, and PearAI — because none of these read the standalone Claude Code, Codex, or VS Code config files.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Recognizes Codex for VS Code, CodeGPT, Qoder CN, Bito, Zencoder, Tabby, twinny, Verdent, Pieces, and the Firebender JetBrains plugin as AI extensions in the Detect inventory. Not checked yet
Detects IDE-native AI agents that were previously invisible — including Claude and Codex agents in Xcode 26.3+ (from its own CodingAssistant folder), Visual Studio Copilot agent mode, JetBrains AI Assistant, Gemini in Android Studio, GitHub Copilot for Xcode and Eclipse, Firebender, Positron, and PearAI — because none of these read the standalone Claude Code, Codex, or VS Code config files.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 more in Everything
1.28.1396 - Gateway spend tracking and session stop (2026-10-15)
Oct 15, 2026
·
issue 110
Adds session stop API, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. Gateway spend tab, connector approval intake, idle-connector keep-alive, upstream User-Agent identification, and expanded Runlayer Plugin artifact operations.
Adds a Session stop API for Security, IT, and Super Admins to halt a live agent session with a reason; subsequent MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool calls carrying that session's id are denied until an admin clears the stop, with each stop, first denied call, and clear recorded in the audit log. Not checked yet Adds a Settings → LLM Gateway → Spend tab listing every LLM call the gateway reported, with cost, tokens, and charged usage rule, and totals spend by agent run, device, or model over a chosen time range; calls the gateway cannot price show as unpriced rather than $0. Not checked yet Adds connector approval intake so workspace admins can direct employees to an external approval form with custom instructions, with the option to disable native connector submissions. Not checked yet Runlayer Plugin agents can now publish, find, read, edit, and delete artifacts, and delete skills and agents directly, without a separate Runlayer MCP server connection. Not checked yet Runlayer now names the AI client in the User-Agent sent to Streaming HTTP and SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. connectors and identifies itself as Runlayer on OAuth requests, enabling out-of-the-box connectivity to servers that check the calling client or reject OAuth requests without a User-Agent . Not checked yet
+1 more
show less
Runlayer now renews an unused connector's sign-in every few days for up to 90 days without use, keeping idle connectors connected. Not checked yet
6 details in Everything
1.28.1381 - Secret stores and agent eval scoring (2026-10-15)
Oct 15, 2026
·
issue 110
Adds secret stores (AWS Secrets Manager), agent eval scoring, Terraform-managed scanner/AI Watch defaults, plugin-scoped tokens, and hardened connector sandboxing sandboxing Running code inside a restricted environment that limits what it can access or change. The isolation reduces the impact of mistakes or untrusted code, depending on the sandbox's controls. .
Adds secret stores: keep connector credentials in your own AWS Secrets Manager and reference them in connector headers and environment variables; workspace admins manage stores under Settings. Not checked yet Adds Matches expected output eval scorer for agent runs — save the expected answer on a reviewed run, then replay it to regression-test prompt and model changes. Not checked yet Adds runlayer_security_scanner_settings Terraform resource to manage organization-wide security scanner defaults as code; self-hosted deployments require backend 1.28.1220 or later. Not checked yet Adds runlayer_ai_watch_enforce_entry Terraform resource to manage each AI Watch Enforce allowlist or Protect denylist entry (remote MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. URL, stdio package, or built-in) as code; self-hosted deployments require backend 1.28.1171 or later. Not checked yet Adds PATCH /ai-watch/policy-rules/{id} to edit the organization-wide AI Watch policy, now an editable default (Monitor with Sessions off) rather than a computed value; the rule list shows which deployments differ from it. Not checked yet
+7 more
show less
Adds components.extendDB opt-in to Kubernetes operator deployments to provision DynamoDB-compatible token storage via ExtendDB on the instance Postgres (Preview; requires botocore >= 1.31 / boto3 >= 1.28 or JS v3 / Java 2 / Go v2 and AWS_ENDPOINT_URL_DYNAMODB injection). Not checked yet Adds plugin-scoped on-behalf-of tokens for strict-mode agent accounts, scoped to a plugin's OAuth connectors that already have a session grant. Not checked yet Connector environment variables: stdio connectors no longer accept dynamic-loader variables (LD_*, DYLD_*, GCONV_PATH) in their environment or inherit list. Not checked yet Hosted stdio connectors (npx, uvx, uv) now accept only a defined allowlist of package-selection options and UV_* / npm_config_* environment variable names; file-reading options (--env-file, --userconfig), filesystem path values, and variables such as HOME, PATH, PREFIX, XDG_*, NODE_PATH, and PYTHONPATH are refused for hosted runners. Not checked yet Exposed paths listed in service.expose on deployed MCP servers no longer receive users' Runlayer cookies or set cookies, and their responses run in a sandboxed context blocking scripts and forms. Not checked yet Tool Output Offloading: jq filters AI clients run on offloaded outputs are now sandboxed and cannot read server environment variables or files. Not checked yet Local connectors now run only on the user's machine through the Runlayer CLI; the gateway refuses to start or dial them on any proxy path. Not checked yet
12 details in Everything
└──▷ BREAKING ON UPGRADE
! The gateway refuses to start or dial connectors configured for local deployment on any proxy path; a direct POST /api/v1/proxy/{id}/mcp call to one is recorded as a security violation and can end the caller's session.! stdio connectors that carry LD_*, DYLD_*, or GCONV_PATH variables in their environment or inherit list will be refused at launch.! Hosted stdio connectors (npx, uvx, uv) that pass file-reading options (--env-file, --userconfig), filesystem path values, or disallowed environment variable names (HOME, PATH, PREFIX, XDG_*, NODE_PATH, PYTHONPATH) are refused on save and at launch.
Runlayer adds per-agent network access policies — allow/block lists enforced at the network layer for every agent sandbox connection.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Restrict a finance agent to only its required external hosts, preventing exfiltration to arbitrary endpoints even if the agent is prompt-injected.
📍 In the agent's settings, set the network access policy mode to Allow list and add entries such as api.salesforce.com and *.hubspot.com. All other outbound connections from the agent sandbox are denied.
Adds per-agent network access policies with three modes — Unrestricted , Allow list , and Block list — configurable in each agent's settings or via the API.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Writes every connection attempt to the audit log with the run, agent, host, and outcome, without logging sensitive data such as request bodies or credentials. Not checked yet Fails closed: if a network policy cannot be enforced, the agent does not run. Not checked yet Network access policies are available for Runlayer-hosted agents and self-hosted AWS deployments. Not checked yet
4 details in Everything
1.28.1284 - Vendor agent detection and thread replies (2026-10-13)
Oct 13, 2026
·
issue 108
Session Grants API gains single-grant fetch by ID; agents reply to own Slack thread posts without @mention when Thread follow-ups is Anyone in the thread .
Adds GET by ID to the Session Grants API so automation can fetch a single session grant in the same shape returned by create/update, without listing all grants for an agent account. Not checked yet Enables agents to answer replies to their own Slack posts (for example, scheduled-run updates) without an @mention when Thread follow-ups is set to Anyone in the thread . Not checked yet
2 details in Everything
1.28.1271 - Bot thread monitoring and unified sessions (2026-10-13)
Oct 13, 2026
·
issue 108
Runlayer 1.28.1271 adds bot thread monitoring, headless OAuth via --no-browser, new API endpoints for webhooks, routing rules, and a DoorDash connector.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Authorize a local HTTP/SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector on a headless server where no browser is available, then complete the OAuth flow over SSH with curl.
copy
$ runlayer run --no-browser
Adds runlayer run --no-browser flag for headless OAuth, letting you authorize local HTTP/SSE connectors on a browserless host and complete login with curl.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a GET endpoint to read a single agent webhook by its ID; webhook creation now returns fields at the top level of the response (nested webhook object still returned for existing integrations). Not checked yet Adds API support for setting a routing rule's evaluation position when creating or updating it, enabling automation to manage LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway rule order one rule at a time. Not checked yet Adds API endpoints that return stored scanner overrides for an MCP client, a local tool family, or a single local tool in the same shape that updating them returns. Not checked yet Adds API support for setting hidden clients in the same request that updates other organization settings. Not checked yet
+5 more
show less
Adds API support for setting a skill's tags and (for skill admins) marking it verified at creation time, without a follow-up update. Not checked yet Adds Servers API response parity: creating or updating a server now returns the same response as fetching it, including access level and allowed clients. Not checked yet Adds Teams API calls to fetch a single group bound to a team and bind a group in one idempotent call by group ID. Not checked yet Adds Also evaluate their replies in a thread option to Slack channel monitors, enabling monitors to act on bot or app replies inside a thread (one reply per thread triggers a run). Not checked yet Adds Add me as collaborator button in an agent's Slack settings, letting workspace admins become collaborators on a Runlayer-managed Slack app. Not checked yet
Adds runlayer run --no-browser flag for headless OAuth, letting you authorize local HTTP/SSE connectors on a browserless host and complete login with curl.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds API endpoints that return stored scanner overrides for an MCP client, a local tool family, or a single local tool in the same shape that updating them returns. Not checked yet Adds Also evaluate their replies in a thread option to Slack channel monitors, enabling monitors to act on bot or app replies inside a thread (one reply per thread triggers a run). Not checked yet Adds Add me as collaborator button in an agent's Slack settings, letting workspace admins become collaborators on a Runlayer-managed Slack app. Not checked yet
6 more in Everything
1.28.1233 - Claude subscriptions and policy impact checks (2026-10-12)
Oct 12, 2026
·
issue 108
Runlayer: Adds runlayer_plugin Terraform resource to define plugins with their connectors and skills as code.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds runlayer_agent_schedule Terraform resource to deploy an agent's cron schedules alongside the agent itself. Not checked yet Adds a new endpoint to return a single LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway usage rule by ID. Not checked yet Adds a new endpoint to fetch a single LLM gateway virtual key by ID (secret shown only at creation). Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! Updating a tool's security settings now returns the scanner overrides (tool name plus settable fields) instead of the full stored settings row — automation that parsed the previous full-row response will need to be updated.
1.28.1233 (2026-10-12)
Oct 12, 2026
·
issue 106
New Terraform resources for plugins, schedules, teams, org settings, policy attributes, and AI Watch; new single-resource API endpoints across gateway, MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. , OAuth, and AI providers; pre-save policy impact checks.
Adds runlayer_plugin resource to the Terraform provider to define plugins with their connectors and skills as code. Not checked yet Adds runlayer_agent_schedule resource to the Terraform provider to deploy an agent's cron schedules alongside the agent itself. Not checked yet Adds runlayer_team and runlayer_organization resources to the Terraform provider to manage teams and organization settings as code. Not checked yet Adds runlayer_policy_attribute_setting resource to the Terraform provider to define policy-referenceable attributes as code. Not checked yet Adds Terraform provider resources to manage AI Watch enforcement settings, per-user AI Watch policies, and per-tool scanner overrides on a connector. Not checked yet
+18 more
show less
Adds a new endpoint to read a single AI Watch enforce entry by ID, and endpoints to list, read, or delete a single user's scoped AI Watch policies. Not checked yet Adds a new endpoint to return one tool's stored scanner overrides; updating a tool's security settings now returns those overrides (tool name plus settable fields) instead of the full stored settings row. Not checked yet Adds a new endpoint to return a server's stored scanner overrides in the same shape that updating them returns. Not checked yet Adds a new endpoint to return a single LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway usage rule by ID, in the same shape as create/update responses. Not checked yet Adds a new endpoint to fetch a single LLM gateway virtual key by ID, in the same shape as list and update endpoints. Not checked yet Adds a new endpoint to fetch a single MDM configuration by ID, returning the same details as updating it. Not checked yet Adds a new endpoint to fetch a single pre-registered OAuth client by ID, in the same shape as the update response. Not checked yet Adds a new endpoint to return a single private connection by ID, in the same shape as list and delete endpoints. Not checked yet Adds a new endpoint to fetch a single AI provider by ID, in the same shape as create and update responses (API key is masked, never returned). Not checked yet Adds a new endpoint to read and set the organization's recommended agent model as a single setting. Not checked yet Adds a new endpoint to return a package's update policy in the same shape as the update response, including org defaults. Not checked yet Adds a new endpoint to return a single LLM gateway routing rule by ID, in the same shape as create/update responses. Not checked yet Adds endpoints to fetch a single team member and to add a member or set their role in one idempotent call by user ID. Not checked yet Updates the Skills API to create or update a skill with its complete set of files in one request and read every file's content back. Not checked yet Updates the Teams API so creating or updating a team returns the same details as fetching it, including shared skill, plugin, agent, and artifact counts. Not checked yet The Runlayer Assistant, policy builder chat, and any MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. client can now test a policy impact before it is saved, showing who gains or loses which access by name with divergent cases called out first. Not checked yet Creating or editing a policy through Runlayer tools now returns the access impact (who gains or loses which access) before the change is saved, and holds back changes where some users' access moves the opposite direction until the agent acknowledges the result. Not checked yet LLM Gateway now routes image generation requests (/v1/images/*) through the gateway. Not checked yet
23 details in Everything
Runlayer adds enterprise governance for Meta Muse, including a single MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. gateway endpoint, shadow AI discovery, and SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. -exportable audit logs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds a single Runlayer plugin endpoint that routes all Muse tool calls through Runlayer's MCP gateway, replacing ungoverned per-connector MCP setups.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds shadow AI discovery that detects when Muse is used inside company systems without Runlayer governance and surfaces per-employee activity. Not checked yet Adds on-behalf-of authentication for Muse, with employee identity sourced from your IDP IDP A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. via SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. so Muse acts within that person's permissions only. Not checked yet Adds fine-grained policy and human-approval rules for Muse tool calls — including example controls such as blocking Gmail sends to external domains. Not checked yet Adds audit logging of every Muse tool call, exportable to a SIEM. Not checked yet
+2 more
show less
Adds runtime security scanning of every Muse tool call for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. , credential exposure, and data exfiltration data exfiltration Moving data out of a system or organization without authorization. It can happen through network transfers, removable media or other channels. . Not checked yet Supports governing Muse across 18,000+ MCPs plus custom connectors for internal systems through a single approved endpoint. Not checked yet
7 details in Everything
1.28.1158 - Slack bot triggers and Deploy autoscaling (2026-10-10)
Oct 10, 2026
·
issue 108
Runlayer 1.28.1158 adds Slack bot filtering, Deploy autoscaling via infrastructure.scaling, AI Watch browser-extension and Office add-in detection, and signed support-acces︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Supply Runlayer's public signing keys for signed support-access on a Kubernetes deployment before upgrading.
runlayer-app Secret
copy
# In the runlayer-app Secret
DEBUG_OPS_REQUEST_SIGNING_JWKS='{"keys":[{...}]}'
Restrict a Slack channel monitor to trigger only from a specific alerting bot, selected from recently active bots in that channel.
📍 In the channel monitor settings, enable Respond to messages from bots , select Only specific bots and apps , then pick your alerting bot from the list of recently active bots or paste a link to one of its messages.
Adds infrastructure.scaling config to run Runlayer Deploy MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers as multiple replicas — fixed count or CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. /network autoscaled — with each MCP session pinned to one replica.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds DEBUG_OPS_REQUEST_SIGNING_JWKS environment variable (Kubernetes runlayer-app Secret) and debug_ops_request_signing_jwks Terraform input (ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. ) to supply Runlayer's trusted public signing keys for signed, encrypted diagnostic support-access requests. Not checked yet Adds long-lived API keys for agent accounts, creatable from the Manage API keys menu, usable on the MCP gateway in place of the client credentials flow — unavailable when Require DPoP, Strict mode , or Enforce audience is on. Not checked yet Adds AI Watch Detect inventory of browser extensions across Chrome, Edge, Brave, Chromium, and Firefox profiles, surfacing AI extensions (including Claude in Chrome, ChatGPT browser control, Perplexity, Grammarly, Browser MCP, Playwright MCP Bridge, and meeting recorders) on the Shadow AI page with store, enabled state, install method, and sideload status. Not checked yet Adds AI Watch Detect inventory of Office add-ins for Excel, Word, PowerPoint, Outlook, and OneNote on Windows and macOS, surfacing AI add-ins (including Claude for Excel/Word/PowerPoint/Outlook and the ChatGPT add-in) on the Shadow AI page with publisher, version, host application, store origin, and sideload status. Not checked yet
+5 more
show less
Adds per-bot filtering to Slack channel monitors — choose Respond to messages from bots to respond to all bots/apps or only named ones selected from recently active bots or a message link; noisy bots are rate-limited per channel and the agent never triggers itself. Not checked yet Adds admin control to set the model, provider (including OpenAI-compatible gateways), and model settings for the Runlayer Assistant from Settings → AI Providers. Not checked yet Adds audit-log events for prompt discovery via connectors (listing a connector's prompts through Runlayer), matching existing coverage for tools and resources; events also appear in SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. exports. Not checked yet Adds OAuth Scopes policy conditions that always reflect the scopes the upstream provider granted, not the scopes an MCP client requested at reconnect. Not checked yet Shows readable model names for custom Bedrock inference-profile ARNs in the model picker (e.g. Claude Sonnet 4.5 (inference profile) ), requiring bedrock:GetInferenceProfile on the provider's role. Not checked yet
Adds infrastructure.scaling config to run Runlayer Deploy MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers as multiple replicas — fixed count or CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. /network autoscaled — with each MCP session pinned to one replica.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds DEBUG_OPS_REQUEST_SIGNING_JWKS environment variable (Kubernetes runlayer-app Secret) and debug_ops_request_signing_jwks Terraform input (ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. ) to supply Runlayer's trusted public signing keys for signed, encrypted diagnostic support-access requests. Not checked yet Adds long-lived API keys for agent accounts, creatable from the Manage API keys menu, usable on the MCP gateway in place of the client credentials flow — unavailable when Require DPoP, Strict mode , or Enforce audience is on. Not checked yet Adds AI Watch Detect inventory of browser extensions across Chrome, Edge, Brave, Chromium, and Firefox profiles, surfacing AI extensions (including Claude in Chrome, ChatGPT browser control, Perplexity, Grammarly, Browser MCP, Playwright MCP Bridge, and meeting recorders) on the Shadow AI page with store, enabled state, install method, and sideload status. Not checked yet Adds AI Watch Detect inventory of Office add-ins for Excel, Word, PowerPoint, Outlook, and OneNote on Windows and macOS, surfacing AI add-ins (including Claude for Excel/Word/PowerPoint/Outlook and the ChatGPT add-in) on the Shadow AI page with publisher, version, host application, store origin, and sideload status. Not checked yet
+2 more
show less
Adds per-bot filtering to Slack channel monitors — choose Respond to messages from bots to respond to all bots/apps or only named ones selected from recently active bots or a message link; noisy bots are rate-limited per channel and the agent never triggers itself. Not checked yet Adds admin control to set the model, provider (including OpenAI-compatible gateways), and model settings for the Runlayer Assistant from Settings → AI Providers. Not checked yet
3 more in Everything
└──▷ BREAKING ON UPGRADE
! ECS deployments must supply Runlayer's trusted public signing keys via the debug_ops_request_signing_jwks Terraform input before upgrading — missing or unusable keys disable all diagnostic support access.! Kubernetes deployments must set DEBUG_OPS_REQUEST_SIGNING_JWKS in the runlayer-app Secret before upgrading — missing or unusable keys disable all diagnostic support access.! The AI Watch backend must be upgraded before the AI Watch endpoint; unrecognized browser extensions and Office add-ins remain hidden until both sides are updated.
1.28.1158 (2026-10-10)
Oct 10, 2026
·
issue 101
Runlayer 1.28.1158 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server autoscaling, agent-account API keys, Office add-in Shadow AI detection, and signed support-access encryption.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Provide signed-support-access signing keys to a Kubernetes deployment so diagnostic requests remain available after upgrading.
yaml
copy
apiVersion: v1
kind: Secret
metadata:
name: runlayer-app
stringData:
DEBUG_OPS_REQUEST_SIGNING_JWKS: '<jwks-json>'
Create a long-lived API key for an agent account to authenticate against the MCP gateway without the client credentials flow.
📍 In the Runlayer console, go to the agent account's detail page → Manage API keys → Create key. Copy the returned key and use it as a bearer token when calling the MCP gateway.
Adds infrastructure.scaling to the infrastructure module for scaling deployed MCP servers at a fixed replica count or autoscaled on CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. and network use, with each MCP session pinned to one replica.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds long-lived API keys for agent accounts, creatable from the Manage API keys menu, usable on the MCP gateway in place of the client credentials flow; unavailable when Require DPoP, Strict mode , or Enforce audience is on. Not checked yet Adds DEBUG_OPS_REQUEST_SIGNING_JWKS (Kubernetes Secret) and debug_ops_request_signing_jwks Terraform input (ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. ) to supply trusted public signing keys for signed, encrypted support-access diagnostic requests; missing or unusable keys disable diagnostic access entirely. Not checked yet AI Watch Detect now inventories Office add-ins (Excel, Word, PowerPoint, Outlook, OneNote) on Windows and macOS and surfaces AI ones — including Claude for Excel/Word/PowerPoint/Outlook and the ChatGPT add-in — on the Shadow AI page, reporting publisher, version, host application, store origin, and sideload status. Not checked yet AI Watch Detect now inventories browser extensions across Chrome, Edge, Brave, Chromium, and Firefox profiles and surfaces AI ones — including Claude in Chrome, ChatGPT browser control, Perplexity, Grammarly, Browser MCP, Playwright MCP Bridge, and meeting recorders — on the Shadow AI page, reporting store, enabled state, installation method, and whether sideloaded. Not checked yet
+5 more
show less
Adds bot-filtering to Slack channel monitors: with Respond to messages from bots on, monitors can be scoped to specific bots or apps selected by name from recently-posting bots or by message link, instead of requiring Slack app IDs. Not checked yet Prompt discovery (listing a connector's prompts via Runlayer) now records audit events visible in the audit log and SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. exports, consistent with existing tool and resource listing events. Not checked yet Admins can now select the model, provider (including an OpenAI-compatible gateway), and model settings for the Runlayer Assistant from Settings → AI Providers. Not checked yet Subagents running on the Pi harness now inherit the parent agent's sandbox guidance, memory context, and skills, and can browse, use memory, and recover connectors. Not checked yet OAuth Scopes policy conditions now always reflect scopes granted by the upstream provider, not those requested by a reconnecting MCP client. Not checked yet
Adds infrastructure.scaling to the infrastructure module for scaling deployed MCP servers at a fixed replica count or autoscaled on CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. and network use, with each MCP session pinned to one replica.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds long-lived API keys for agent accounts, creatable from the Manage API keys menu, usable on the MCP gateway in place of the client credentials flow; unavailable when Require DPoP, Strict mode , or Enforce audience is on. Not checked yet Adds DEBUG_OPS_REQUEST_SIGNING_JWKS (Kubernetes Secret) and debug_ops_request_signing_jwks Terraform input (ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. ) to supply trusted public signing keys for signed, encrypted support-access diagnostic requests; missing or unusable keys disable diagnostic access entirely. Not checked yet AI Watch Detect now inventories Office add-ins (Excel, Word, PowerPoint, Outlook, OneNote) on Windows and macOS and surfaces AI ones — including Claude for Excel/Word/PowerPoint/Outlook and the ChatGPT add-in — on the Shadow AI page, reporting publisher, version, host application, store origin, and sideload status. Not checked yet AI Watch Detect now inventories browser extensions across Chrome, Edge, Brave, Chromium, and Firefox profiles and surfaces AI ones — including Claude in Chrome, ChatGPT browser control, Perplexity, Grammarly, Browser MCP, Playwright MCP Bridge, and meeting recorders — on the Shadow AI page, reporting store, enabled state, installation method, and whether sideloaded. Not checked yet
5 more in Everything
└──▷ BREAKING ON UPGRADE
! ECS deployments must supply Runlayer's trusted public signing keys via the Terraform debug_ops_request_signing_jwks input before upgrading; the backend must be upgraded before the AI Watch endpoint or unrecognized add-ins and extensions will stay hidden.! Kubernetes deployments must set DEBUG_OPS_REQUEST_SIGNING_JWKS in the runlayer-app Secret before upgrading; missing or unusable keys disable all diagnostic support access.
1.28.1115 - Agent inventory and artifact folders (2026-10-09)
Oct 9, 2026
·
issue 108
Adds agent Inventory tab with bulk management, artifact folders via set_artifact_folder/create_artifact, per-user hook daemon on by default, custom model pricing in Settings → AI Providers, and policy-aware audit logs.
New supported platform Adds Inventory tab to the Agents page for bulk model upgrades and disables, replacing the Unused tab. Not checked yet Adds artifact folder organization with set_artifact_folder tool and folder option on create_artifact, browsable from the Artifacts page. Not checked yet Updated detection Enables per-user hook daemon by default on enrolled macOS and Windows devices; verify with aiwatch daemon status. Not checked yet Lets admins configure input, output, cache-read, and cache-write prices per custom model in Settings → AI Providers. Not checked yet Adds Allowed by row to audit log tool-call details, listing policies that permitted each allowed call. Not checked yet
+4 more
show less
Extends Run now to all users a scheduled task runs for, not only editors. Not checked yet Extends agent run failure Slack DM alerts to webhook-triggered runs; toggle renamed to Run failures , on by default. Not checked yet Deactivated users' in-progress agent runs can no longer post or react in Slack. Not checked yet workspace removed as a default allowed built-in MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server for Claude Code; must be re-added explicitly. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! workspace is no longer a default allowed built-in MCP server for Claude Code and has been removed from existing custom allowed lists — add it back explicitly in Enforce policy only if you accept that a user's own Claude Desktop MCP server can take that name.
1.28.1115 (2026-10-09)
Oct 9, 2026
·
issue 098
Adds artifact folders, agent inventory tab, per-user hook daemon, custom model pricing, Claude Haiku 5.5 support, and richer audit-log policy attribution.
Adds folder option on create_artifact and the new set_artifact_folder tool so agents can file published artifacts into nested folder paths using / as a separator. Not checked yet Adds aiwatch daemon status shell command to check whether the per-user hook daemon is running on enrolled macOS and Windows devices. Not checked yet Adds an Inventory tab on the Agents page listing every editable agent with owner, model, recent runs, and upkeep issues (idle, never run, newer model available, owner left), with bulk model-upgrade and bulk-disable actions; replaces the Unused tab. Not checked yet Adds per-custom-model input, output, cache-read, and cache-write price configuration under Settings → AI Providers so agent-run cost and budget limits price custom models correctly. Not checked yet Adds Claude Haiku 5.5 as a selectable agent model via the Anthropic API or AWS Bedrock, with adaptive thinking effort settings. Not checked yet
+6 more
show less
Adds Run now action on scheduled tasks for every person the task runs as, even users without edit access. Not checked yet Adds Allowed by row to audit-log entries for allowed tool calls and resource reads, listing the policies that permitted them with links to each policy. Not checked yet Adds per-user hook daemon enabled by default on enrolled macOS and Windows devices, giving Claude Code, Codex, and other hook-driven clients faster responses without spawning a new process per call; Cursor and Goose hooks now carry a 120 s timeout. Not checked yet Adds Slack DM failure alerts for agents without their own Slack app when any webhook or scheduled run fails (not only failed-to-start runs); the toggle is renamed Run failures and is on by default. Not checked yet Adds a unified, searchable agent model picker that groups models by AI provider with starred favorites and an inline reasoning-effort menu. Not checked yet Adds Slack channel monitor option to receive messages from other apps' bots (off by default for new monitors). Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The workspace built-in MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server is no longer trusted by default for Claude Code and is removed from existing custom allowed lists; add it back explicitly only if your policy accepts it.
1.28.1078 - Agent usage feed and faster hooks (2026-10-07)
Oct 7, 2026
·
issue 108
Runlayer 1.28.1078 adds a GET /api/v1/agents/metrics/usage feed and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools for agent usage reporting, plus faster Monitor-mode hooks.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Pull token and cost usage for all agents into a data warehouse or BI tool on a schedule.
copy
$ curl -s -H "Authorization: Bearer <token>" https://app.runlayer.com/api/v1/agents/metrics/usage
Ask your AI client to list who is consuming each agent and how many tokens they have used, using the new MCP tools.
📍 Use the get_agent_usage_report tool (via Runlayer MCP) to retrieve creator, consumer, sharing, and token usage for all agents; then call list_agent_usage_consumers to break down consumers per agent.
Adds GET /api/v1/agents/metrics/usage endpoint to pull every agent's creator, consumers, sharing, and token and cost usage into a BI tool or data warehouse.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds get_agent_usage_report and list_agent_usage_consumers tools to the Runlayer MCP so AI clients can query agent usage directly. Not checked yet Reduces latency in AI Watch Monitor mode by delivering tool-call hook answers before output scanning runs, so coding-agent sessions no longer block on scanner latency per tool call. Not checked yet Adds sorting to the Artifacts page by newest, oldest, most recently updated, or least recently updated. Not checked yet Adds a clickable failed-runs count under the Success rate on an agent's Monitor tab that opens Sessions pre-filtered to failed runs. Not checked yet
Adds GET /api/v1/agents/metrics/usage endpoint to pull every agent's creator, consumers, sharing, and token and cost usage into a BI tool or data warehouse.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds get_agent_usage_report and list_agent_usage_consumers tools to the Runlayer MCP so AI clients can query agent usage directly. Not checked yet
3 more in Everything
1.28.1078 (2026-10-07)
Oct 7, 2026
·
issue 097
Runlayer adds GET /api/v1/agents/metrics/usage and two MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools for agent usage reporting, plus artifact sort controls.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Pull per-agent token and cost usage into a data warehouse or BI dashboard for chargeback or governance reporting.
copy
$ curl -H 'Authorization: Bearer <token>' 'https://app.runlayer.com/api/v1/agents/metrics/usage'
Adds GET /api/v1/agents/metrics/usage endpoint to pull every agent's creator, consumers, sharing, and token and cost usage into a BI tool or data warehouse.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds get_agent_usage_report and list_agent_usage_consumers MCP tools in Runlayer MCP so AI clients can query agent usage, sharing, and token data directly. Not checked yet Adds sorting to the Artifacts page by newest, oldest, most recently updated, or least recently updated. Not checked yet Adds a clickable failed-runs count under Success rate on an agent's Monitor tab that opens Sessions filtered to failed runs. Not checked yet Improves AI Watch Monitor mode so tool-call hooks receive their answer before output scanning runs, removing scanner latency from every tool-call round-trip in coding-agent sessions. Not checked yet
Adds GET /api/v1/agents/metrics/usage endpoint to pull every agent's creator, consumers, sharing, and token and cost usage into a BI tool or data warehouse.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds get_agent_usage_report and list_agent_usage_consumers MCP tools in Runlayer MCP so AI clients can query agent usage, sharing, and token data directly. Not checked yet
3 more in Everything
1.28.1073 - Scoped AI Watch policies, allowed agents (2026-10-07)
Oct 7, 2026
·
issue 108
Adds scoped AI Watch policy rules API, plugin-scoped agent tokens, allowed-agent handoff controls, schedule_continuation for agents, and artifact embed links.
Adds GET /ai-watch/policy-rules/check?device_id=… to preview the effective AI Watch policy a specific machine receives before applying changes. Not checked yet Adds the /ai-watch/policy-rules API to set AI Watch mode, session capture, browser controls, detection phases, and scan bounds per team, group, user, or device without a separate deployment. Not checked yet Adds plugin-scoped agent on-behalf-of tokens by passing a plugin's MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. URL as resource, restricting the token to that plugin's endpoint only. Not checked yet Adds Allowed agents section on an agent's detail page so each user of a shared agent can choose which agents it may hand work to on their behalf. Not checked yet Adds schedule_continuation for agents to end a run and resume the same conversation after a delay of 1 minute to 24 hours. Not checked yet
+8 more
show less
Adds webhook source allowlists for self-hosted ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. deployments to permit integration source IP ranges for agent webhook invocation. Not checked yet Adds Approve always option on agent handoff prompts, which adds the agent to Allowed agents so future handoffs skip the approval prompt. Not checked yet Adds /artifacts/<id>/embed link to share an artifact full-screen without the Runlayer header. Not checked yet Batches AI Watch hook telemetry to disk and delivers up to 100 events per request, surviving daemon restarts and short outages. Not checked yet Reduces AI Watch inventory to a single request per scan, uploading content only when Runlayer has not seen it before. Not checked yet Skips redundant hook round trips in AI Watch Protect mode for tool calls already routed through the Runlayer gateway. Not checked yet Masks redacted tool-call inputs in the run transcript on Pi agents when a scanner's Mask action redacts a secret. Not checked yet Hides tokens, keys, and credential-like values in approval requests in the web app, Slack, and Microsoft Teams. Not checked yet
13 details in Everything
└──▷ BREAKING ON UPGRADE
! An agent account with no Runlayer-hosted agent behind it (an external agent using client credentials) can no longer call run_agent.! Scheduled and triggered agent handoffs now hand off only to agents listed in Allowed agents ; targets from the prior 30 days are auto-added up to 50 per person and calling agent.
1.28.1019 - Voice messages and agent handoff approvals (2026-10-06)
Oct 6, 2026
·
issue 108
Runlayer 1.28.1019 adds in-chat voice input, agent handoff approvals, and Bedrock connection validation with model selection.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Scope your Bedrock provider to only the models your account has actually enabled, so users cannot attempt to invoke unavailable models.
📍 In your AWS IAM role for Runlayer, add the following permissions, then go to Runlayer › AI Providers › AWS Bedrock › Validate connection:
- bedrock:ListFoundationModels
- bedrock:ListInferenceProfiles
- bedrock:GetFoundationModelAvailability
Runlayer will list your enabled models with all checked by default; uncheck any you want to hide.
Send a voice prompt to an agent without typing, useful when dictating a long or complex task during an active conversation.
📍 In an open agent chat, click the microphone icon in the message box, speak your prompt, then click stop. Runlayer transcribes the audio using your workspace OpenAI provider into the message box for review before you send.
Review all runs a specific scheduled task has started, without manually filtering the Sessions tab.
📍 Open the agent › Scheduled tasks › click the task › in the edit dialog, click View runs . The Sessions tab opens pre-filtered to only the runs that task triggered.
Adds bedrock:ListFoundationModels, bedrock:ListInferenceProfiles, and bedrock:GetFoundationModelAvailability IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. permissions to AWS Bedrock provider setup, enabling Validate connection to check the role and list only the models your account has enabled in that Region.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds agent handoff approvals: when in a conversation, an agent hands work to another agent only after you approve, showing the target agent and owner, the task it will send, and the agent's summary of what it shares and expects back. Not checked yet Adds in-chat voice input — click the microphone in the message box, speak, then click stop; Runlayer transcribes the recording into the message box using your workspace's OpenAI provider. Not checked yet Adds a View runs button to a scheduled task's edit dialog, opening the agent's Sessions tab filtered to runs that task started. Not checked yet Moves run limits and cost budgets from the agent's Settings tab to the Monitor tab as a Limits card showing usage against each limit, with an Edit limits button. Not checked yet
+2 more
show less
Moves run-result and budget-alert DMs for agents with their own Slack app to a new Notifications section in the app's Slack settings; Run results now also controls the scheduled run failure DM. Not checked yet Adds approval requirement for setting up or changing a schedule, trigger, webhook, or Slack channel monitor from within a conversation. Not checked yet
Adds bedrock:ListFoundationModels, bedrock:ListInferenceProfiles, and bedrock:GetFoundationModelAvailability IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. permissions to AWS Bedrock provider setup, enabling Validate connection to check the role and list only the models your account has enabled in that Region.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds agent handoff approvals: when in a conversation, an agent hands work to another agent only after you approve, showing the target agent and owner, the task it will send, and the agent's summary of what it shares and expects back. Not checked yet Adds in-chat voice input — click the microphone in the message box, speak, then click stop; Runlayer transcribes the recording into the message box using your workspace's OpenAI provider. Not checked yet Adds a View runs button to a scheduled task's edit dialog, opening the agent's Sessions tab filtered to runs that task started. Not checked yet Adds approval requirement for setting up or changing a schedule, trigger, webhook, or Slack channel monitor from within a conversation. Not checked yet
2 more in Everything
└──▷ BREAKING ON UPGRADE
! The agent's Settings tab is removed; run limits and cost budgets are now on the Monitor tab under a Limits card.
1.28.1019 (2026-10-06)
Oct 6, 2026
·
issue 096
Runlayer 1.28.1019 adds voice input to agent chat, agent handoff approvals, and live Bedrock model validation.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Grant a Bedrock IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. role the minimum permissions needed so Runlayer can validate the connection and enumerate only the models your account has actually enabled.
json
copy
{
"Version": "2012-10-17",
"Statement": [
{
"Effect": "Allow",
"Action": [
"bedrock:ListFoundationModels",
"bedrock:ListInferenceProfiles",
"bedrock:GetFoundationModelAvailability"
],
"Resource": "*"
}
]
}
Approve an agent handoff mid-conversation so one agent can delegate a task to a second agent, with full visibility of the target agent, its owner, and the task being sent.
📍 1. In an active agent conversation, wait for the handoff approval prompt to appear.
2. Review the target agent name, its owner, and the truncated task summary.
3. Click Approve to allow the handoff, or Deny to cancel it and continue in the current agent.
Use voice input to query an agent when typing is impractical — useful during live investigations or hands-free triage sessions.
📍 1. Open an agent's chat view.
2. Click the microphone icon in the message box and speak your query.
3. Click Stop — Runlayer transcribes the audio using your workspace's OpenAI provider.
4. Edit the transcribed text if needed, then send.
Adds bedrock:ListFoundationModels, bedrock:ListInferenceProfiles, and bedrock:GetFoundationModelAvailability IAM actions to the AWS Bedrock provider setup, enabling live connection validation that lists and checks only the models your account has enabled in that Region.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds voice input to agent chat: click the microphone in the message box, speak, then click stop — Runlayer transcribes the recording into the message box using your workspace's OpenAI provider. Not checked yet Adds an approval gate for agent handoffs: before an agent passes work to another agent mid-conversation, the user must approve, with the target agent, its owner, and the task shown. Not checked yet Adds approval gate coverage to schedule, trigger, webhook, and Slack channel monitor changes made from within a conversation. Not checked yet Adds a View runs button to a scheduled task's edit dialog, opening the agent's Sessions tab filtered to runs that task started. Not checked yet
+3 more
show less
Moves run limits and cost budgets from the Settings tab to a Limits card on the Monitor tab, with an Edit limits button showing usage against each limit. Not checked yet Adds a Notifications section in the Slack app settings for agents with their own Slack app, consolidating run-result and budget-alert DMs; Run results now also controls the scheduled run failure DM. Not checked yet Adds save confirmation to agent settings changes, explaining side effects (such as Code mode turning Procedures off) and showing the actual reason when a save fails. Not checked yet
Adds bedrock:ListFoundationModels, bedrock:ListInferenceProfiles, and bedrock:GetFoundationModelAvailability IAM actions to the AWS Bedrock provider setup, enabling live connection validation that lists and checks only the models your account has enabled in that Region.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds voice input to agent chat: click the microphone in the message box, speak, then click stop — Runlayer transcribes the recording into the message box using your workspace's OpenAI provider. Not checked yet Adds an approval gate for agent handoffs: before an agent passes work to another agent mid-conversation, the user must approve, with the target agent, its owner, and the task shown. Not checked yet Adds approval gate coverage to schedule, trigger, webhook, and Slack channel monitor changes made from within a conversation. Not checked yet Adds a View runs button to a scheduled task's edit dialog, opening the agent's Sessions tab filtered to runs that task started. Not checked yet
3 more in Everything
└──▷ BREAKING ON UPGRADE
! The agent's Settings tab is removed; run limits and cost budgets are now on the Monitor tab under the Limits card.
Runlayer: Requires topicCpu.rev to be configured for Procedures — creating or validating a Procedure without it returns 503.
└──▷ USE IT
Enable the self-hosted Rev decision model so the Runlayer Operator runs local risk scoring instead of calling an external service.
yaml
copy
images:
topicCpuRev: REGISTRY/toolguard:runlayer-rev-guard-TAG
topicCpu:
rev:
enabled: true
gunicornWorkers: 1
Inject additional environment variables into every backend-image workload without conflicting with operator-managed names.
yaml
copy
extraEnv:
- name: MY_CUSTOM_VAR
value: "my-value"
- name: ANOTHER_VAR
value: "another-value"
Configure the OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. observability sidecar to export telemetry health metrics to a reachable collector endpoint.
yaml
copy
observability:
otlp:
endpoints:
- name: runlayer-metrics
protocol: http
endpoint: http://otel-collector.monitoring.svc:4318
1.28.991 - Agent handoffs and delegation review (2026-10-02)
Oct 2, 2026
·
issue 108
Runlayer 1.28.991 adds agent-to-agent handoffs, Cursor billing integration, named env-var inheritance for local MCPs, and a delegation review policy template.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Require human approval for every agent-to-agent delegation — including scheduled runs — before it executes, to enforce a governance boundary in multi-agent workspaces.
📍 In the Runlayer console, go to Policies and create a new policy using the Review agent delegation template, then attach it to the workspace or the agents you want gated.
Pass a user's local GitHub token and Node options into a local MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. without storing the values in Runlayer — useful when the MCP needs per-user credentials at runtime.
📍 On the local stdio connector settings page, add GH_TOKEN and NODE_OPTIONS to the list of inherited environment variables, then save. Runlayer stores only the names; values are read from each user's shell when runlayer run starts the MCP.
Adds GH_TOKEN, NODE_OPTIONS, and other named environment variables to the inherit list on a local stdio connector so runlayer run copies each user's shell values into the MCP process without storing the values server-side.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Can hand work to other agents toggle in agent settings to control whether an agent can discover and delegate tasks to other agents. Not checked yet Adds a Review agent delegation policy template under Policies so workspaces with approval policies can require approval for every agent-to-agent run, including scheduled ones. Not checked yet Adds a Cursor Team or Enterprise billing API key connection under Settings → Integrations, with key verification on save, key erasure on disconnect, and preserved historical usage. Not checked yet Adds skill usage analytics — daily trends, totals, and top users — accessible through the Runlayer connector, scoped to the skill's editor permissions. Not checked yet
+1 more
show less
Adds plain-language explanations to Block bypassed tool calls in a session, describing why the block did not take effect and how to prevent similar calls. Not checked yet
Adds GH_TOKEN, NODE_OPTIONS, and other named environment variables to the inherit list on a local stdio connector so runlayer run copies each user's shell values into the MCP process without storing the values server-side.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Can hand work to other agents toggle in agent settings to control whether an agent can discover and delegate tasks to other agents. Not checked yet Adds a Review agent delegation policy template under Policies so workspaces with approval policies can require approval for every agent-to-agent run, including scheduled ones. Not checked yet Adds a Cursor Team or Enterprise billing API key connection under Settings → Integrations, with key verification on save, key erasure on disconnect, and preserved historical usage. Not checked yet Adds skill usage analytics — daily trends, totals, and top users — accessible through the Runlayer connector, scoped to the skill's editor permissions. Not checked yet
1 more in Everything
1.28.991 (2026-10-02)
Oct 2, 2026
·
issue 093
Runlayer 1.28.991 adds agent delegation approval policies, Cursor billing integration, and environment variable inheritance for local MCPs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Enforce human approval on every agent-to-agent handoff, including scheduled runs, to satisfy change-control requirements.
📍 In the Runlayer console, go to Settings → Policies and add a new policy using the Review agent delegation template, then save and apply it to the workspace.
Propagate a developer's local GitHub token into an MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. without storing the value in Runlayer — ideal for local stdio connectors that need per-user credentials.
📍 On the local stdio connector configuration, add GH_TOKEN to the list of named environment variables to inherit; runlayer run will then copy the value from each user's shell at runtime.
Connect a Cursor Enterprise account to sync billing data into Runlayer for unified usage tracking.
📍 In the Runlayer console, go to Settings → Integrations, paste the Cursor Enterprise billing API key and the matching Cursor organization ID, then click Connect. Runlayer verifies the key before saving.
Adds GH_TOKEN, NODE_OPTIONS, and other named environment variables to local stdio connectors so admins can list variables that runlayer run copies from each user's shell into the MCP process — values are never sent to Runlayer.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Review agent delegation policy template requiring approval for every agent-to-agent run, including scheduled ones, in workspaces with approval policies. Not checked yet Enables workspace admins to connect or disconnect a Cursor Team or Enterprise billing API key from Settings → Integrations, with key verification before saving and key erasure on disconnect. Not checked yet Adds a Can hand work to other agents toggle in each agent's settings to control whether it can discover and delegate tasks to other agents. Not checked yet Exposes skill usage totals, daily trends, and top users through the Runlayer connector by asking connected agents. Not checked yet
+1 more
show less
Adds plain-language explanations to tool calls marked Block bypassed in a session, describing why the block did not take effect and how to stop similar calls. Not checked yet
Adds GH_TOKEN, NODE_OPTIONS, and other named environment variables to local stdio connectors so admins can list variables that runlayer run copies from each user's shell into the MCP process — values are never sent to Runlayer.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Review agent delegation policy template requiring approval for every agent-to-agent run, including scheduled ones, in workspaces with approval policies. Not checked yet Enables workspace admins to connect or disconnect a Cursor Team or Enterprise billing API key from Settings → Integrations, with key verification before saving and key erasure on disconnect. Not checked yet Exposes skill usage totals, daily trends, and top users through the Runlayer connector by asking connected agents. Not checked yet
2 more in Everything
└──▷ BREAKING ON UPGRADE
! On AgentCore, the agent sandbox AWS role no longer has sts:AssumeRole permission — it is now limited to pulling the sandbox image and writing runtime logs; any agent code that relied on sts:AssumeRole inside the sandbox will fail.
Runlayer: Adds additional_tags input to apply extra tags to deployment workload resources, with explicit caller opt-in required; aws-apn-id must use the format pc:<Marketplace product code> and must not replace a provider default_tags value.
└──▷ USE IT
Enable the Rev self-hosted decision model sidecar on an m7i.2xlarge instance with 2 concurrent workers, fitting within the 30720 MiB task memory budget.
hcl
copy
enable_runlayer_rev = true
enable_runlayer_topic_cpu = true
runlayer_rev_image_tag = "runlayer-rev-guard-v202609292007"
runlayer_rev_gunicorn_workers = 2
runlayer_rev_memory = 8192
runlayer_rev_cpu_share = 0.25
runlayer_rev_timeout = 10
Attach an OTel Collector OTel Collector An OpenTelemetry vendor-neutral agent, maintained by the CNCF, that receives, processes, and exports telemetry data (traces, metrics, logs) so tools avoid coupling to a specific observability backend. sidecar to backend and worker tasks to forward telemetry to a customer-owned OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. gRPC gRPC An open-source remote procedure call framework from Google that uses HTTP/2 and Protocol Buffers to let services call each other's functions across a network, giving tools low-latency, strongly typed inter-process communication. endpoint, while decoupling flow-trace collection from export transport.
hcl
copy
otel_collector = {
enabled = true
export_endpoint = "grpc://otel.internal.example.com:4317"
}
runlayer_obs_otel_enabled = true
FLOW_TRACE_COLLECTION_ENABLED = true
FLOW_TRACE_ADAPTIVE_SAMPLING_ENABLED = true
Keep a stable NAT Elastic IP for sandbox egress in proxy_only mode so third-party allowlists don't break when proxy tasks are replaced.
hcl
copy
sandbox_egress_mode = "proxy_only"
sandbox_egress_proxy_keep_nat_gateway = true
Adds sandbox_egress_proxy_keep_nat_gateway to retain the module-created AgentCore consumer VPC VPC A logically isolated virtual network inside a public cloud provider's infrastructure, letting tools deploy resources with private addressing, controlled routing, and firewall rules without managing physical hardware. NAT gateway in sandbox_egress_mode = 'proxy_only', keeping proxy tasks in private subnets behind the NAT Elastic IP for stable egress IPs. Not checked yet
1 detail in Everything
1.28.979 - Interactive agent cards and private previews (2026-10-02)
Oct 2, 2026
·
issue 108
Runlayer 1.28.979 adds interactive agent cards, PagerDuty triggers, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. schedule/trigger/webhook editing, private artifact previews, and agent failure analysis.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Pull audit events for a single agent session without paging the full audit window — useful during an incident investigation.
copy
$ list_audit_logs(rl_session_id="ses_01abc123def")
Review per-person token spend across the whole org, including a catch-all row for contributors outside the top 30.
copy
$ get_agent_token_usage(group_by="actor")
Adds rl_session_id to the list_audit_logs MCP tool for fetching a single session's audit activity without paging the full window, and group_by=actor to get_agent_token_usage, returning an Other actors row for everyone past the top 30 so per-person spend always totals to the org.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds update_agent_schedule, update_agent_trigger, and update_agent_webhook MCP tools to edit existing schedules, triggers, and webhooks in place — preserving webhook URLs. Not checked yet Adds PagerDuty triggers so agents can start when a PagerDuty incident is triggered, acknowledged, reassigned, or has its priority changed. Not checked yet Adds interactive agent cards in chat that let agents present inline decision cards (approve a plan, add a connector) and continue the conversation from the user's choice; private artifact previews in agent chat for generated reports or visuals visible only to you, expiring unless you choose Save artifact ; and brings agent cards and artifact previews to Slack and Microsoft Teams with inline button responses that continue the agent in the same thread. Not checked yet Adds file attachments in the agent playground — images, PDFs, Office documents, and text files via paperclip, paste, or drag-and-drop. Not checked yet
+5 more
show less
Adds agent failure analysis: mark runs Pass or Fail with a note from the run drawer, then use Analyze failures on the Evals tab to group failing notes into categories and start an offline eval from any category. Not checked yet Adds a Usage & edits panel to the skill page showing uses, unique users, and edits over the last 7, 30, or 90 days, with edit markers on the usage chart and top-users breakdown. Not checked yet Extends AgentGuard to score sessions from devices in AI Watch Monitor mode, surfacing detections as alerts without blocking tool calls. Not checked yet Adds Claude Code subagent token usage (Explore, Plan, and custom agents) to Sessions and the Usage page, attributed to the parent session and priced per model (requires the updated Runlayer CLI / AI Watch hook); analytics grouping by department and person with drill-down into department or group spend and per-run output visibility; a Status filter on the Sessions tab, with Analytics → Agents → Top erroring agents now linking to that agent's Sessions tab filtered to failed runs; and a model cost breakdown filter by provider with matching row count display. Not checked yet Adds Slack support for .zip, .mp4, and .mov file attachments (up to 100 MB), landing files in the agent's workspace for unpacking or inspection. Not checked yet
Adds rl_session_id to the list_audit_logs MCP tool for fetching a single session's audit activity without paging the full window, and group_by=actor to get_agent_token_usage, returning an Other actors row for everyone past the top 30 so per-person spend always totals to the org.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds update_agent_schedule, update_agent_trigger, and update_agent_webhook MCP tools to edit existing schedules, triggers, and webhooks in place — preserving webhook URLs. Not checked yet Adds PagerDuty triggers so agents can start when a PagerDuty incident is triggered, acknowledged, reassigned, or has its priority changed. Not checked yet Adds interactive agent cards in chat that let agents present inline decision cards (approve a plan, add a connector) and continue the conversation from the user's choice; private artifact previews in agent chat for generated reports or visuals visible only to you, expiring unless you choose Save artifact ; and brings agent cards and artifact previews to Slack and Microsoft Teams with inline button responses that continue the agent in the same thread. Not checked yet Adds file attachments in the agent playground — images, PDFs, Office documents, and text files via paperclip, paste, or drag-and-drop. Not checked yet
+2 more
show less
Adds agent failure analysis: mark runs Pass or Fail with a note from the run drawer, then use Analyze failures on the Evals tab to group failing notes into categories and start an offline eval from any category. Not checked yet Adds a Usage & edits panel to the skill page showing uses, unique users, and edits over the last 7, 30, or 90 days, with edit markers on the usage chart and top-users breakdown. Not checked yet
3 more in Everything
└──▷ BREAKING ON UPGRADE
! The procedures_validator input in the Terraform ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. module is deprecated and ignored; procedure validation now runs in the agent sandbox and requires enable_runlayer_agents with the AgentCore runtime. Setting procedures_validator causes terraform plan to warn; it will stop being accepted in the next major module version.! If you run both the local Claude Code hook and Anthropic inference hooks simultaneously, reported Claude Code spend may drop because turns previously counted once per feed are now deduplicated.
1.28.979 (2026-10-02)
Oct 2, 2026
·
issue 092
Runlayer 1.28.979 adds PagerDuty triggers, AgentGuard Monitor mode, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. session filtering, inline agent cards in Slack/Teams, and agent failure analysis.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Pull audit logs for a single agent session in MCP without paging the full audit window.
copy
$ list_audit_logs(rl_session_id="sess_abc123")
Break down per-person token spend across the full org, including a catch-all row for users outside the top 30.
copy
$ get_agent_token_usage(group_by="actor")
Adds rl_session_id parameter to list_audit_logs MCP tool so agents can retrieve a single session's activity without paging the full audit window.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds update_agent_schedule, update_agent_trigger, and update_agent_webhook MCP tools to edit existing schedules, triggers, and webhooks in place without deleting and recreating them. Not checked yet Adds group_by=actor support to get_agent_token_usage MCP tool, now returning an Other actors row for everyone past the top 30 so per-person spend always totals to the org. Not checked yet Adds PagerDuty triggers: agents can now start when a PagerDuty incident is triggered, acknowledged, reassigned, or has its priority changed. Not checked yet Adds AgentGuard in Monitor mode: scores sessions from devices in AI Watch Monitor mode and surfaces detections as alerts without ever blocking tool calls. Not checked yet
+15 more
show less
Adds agent failure analysis: mark agent runs Pass or Fail with a note from the run drawer, then use Analyze failures on the Evals tab to group failing notes into categories and launch an offline eval from any category. Not checked yet Adds interactive inline decision cards in agent chats: agents can request approvals or connector sign-ins through cards answered inline, with the conversation continuing from the choice. Not checked yet Adds private artifact previews in chat: agents can display generated reports or visuals visible only to the recipient, expiring unless saved via Save artifact . Not checked yet Adds agent cards and artifact previews in Slack and Microsoft Teams, with inline button responses that keep the agent continuing in the same thread. Not checked yet Adds file attachment support in the agent playground: attach images, PDFs, Office documents, and text files via paperclip, paste, or drag and drop. Not checked yet Adds support for .zip, .mp4, and .mov file attachments in Slack agents (up to 100 MB), landing files in the agent's workspace for unpacking or inspection. Not checked yet Adds Claude Code subagent token usage to Sessions and the Usage page, attributed to the parent session and priced per model; requires the updated Runlayer CLI / AI Watch hook. Not checked yet Adds Running vs Idle status to open sessions: sessions show Running while events arrive and Idle with last-activity time once quiet. Not checked yet Adds Top erroring agents drill-through in Analytics: clicking an agent opens its Sessions tab filtered to failed runs, and Sessions gains a new Status filter. Not checked yet Adds analytics grouping by department and person: group ROI artifacts by department or individual, see which outputs an agent run produced, and drill into spend. Not checked yet Adds instruction-change tracking in agent chat: when an agent changes its own instructions the chat shows a diff with an Undo button to restore the previous version. Not checked yet Adds Skill Usage & edits panel: shows uses, unique users, and edits over 7, 30, or 90 days with edit markers on the usage chart, full edit history with diff links, and top users. Not checked yet Adds Claude.ai compliance imports via read:compliance_user_data scope on a claude.ai Compliance Access Key, continuing imports after Anthropic's September 22 listing change. Not checked yet Adds model cost filtering by provider in detailed usage calculations, showing the matching row count. Not checked yet Adds duplicate GitHub skill URL detection: importing a skill from a URL already in the workspace flags it on the review step and offers Update from source instead of creating a second copy. Not checked yet
Adds rl_session_id parameter to list_audit_logs MCP tool so agents can retrieve a single session's activity without paging the full audit window.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds update_agent_schedule, update_agent_trigger, and update_agent_webhook MCP tools to edit existing schedules, triggers, and webhooks in place without deleting and recreating them. Not checked yet Adds PagerDuty triggers: agents can now start when a PagerDuty incident is triggered, acknowledged, reassigned, or has its priority changed. Not checked yet Adds AgentGuard in Monitor mode: scores sessions from devices in AI Watch Monitor mode and surfaces detections as alerts without ever blocking tool calls. Not checked yet Adds agent failure analysis: mark agent runs Pass or Fail with a note from the run drawer, then use Analyze failures on the Evals tab to group failing notes into categories and launch an offline eval from any category. Not checked yet
+8 more
show less
Adds interactive inline decision cards in agent chats: agents can request approvals or connector sign-ins through cards answered inline, with the conversation continuing from the choice. Not checked yet Adds private artifact previews in chat: agents can display generated reports or visuals visible only to the recipient, expiring unless saved via Save artifact . Not checked yet Adds agent cards and artifact previews in Slack and Microsoft Teams, with inline button responses that keep the agent continuing in the same thread. Not checked yet Adds file attachment support in the agent playground: attach images, PDFs, Office documents, and text files via paperclip, paste, or drag and drop. Not checked yet Adds Running vs Idle status to open sessions: sessions show Running while events arrive and Idle with last-activity time once quiet. Not checked yet Adds instruction-change tracking in agent chat: when an agent changes its own instructions the chat shows a diff with an Undo button to restore the previous version. Not checked yet Adds Skill Usage & edits panel: shows uses, unique users, and edits over 7, 30, or 90 days with edit markers on the usage chart, full edit history with diff links, and top users. Not checked yet Adds Claude.ai compliance imports via read:compliance_user_data scope on a claude.ai Compliance Access Key, continuing imports after Anthropic's September 22 listing change. Not checked yet
7 more in Everything
└──▷ BREAKING ON UPGRADE
! The procedures_validator input to the Terraform ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. module is deprecated and ignored; procedure validation now runs in the agent sandbox and requires enable_runlayer_agents with the AgentCore runtime. Setting procedures_validator causes terraform plan to warn; it will stop working in the next major module version.! If you run both the local Claude Code hook and Anthropic inference hooks, reported Claude Code spend may decrease because turns previously counted once per feed are now deduplicated.
Runlayer: Adds additional_tags input to attach extra tags to deployment workload resources, with explicit opt-in required for partner attribution via the aws-apn-id tag using the pc:<Marketplace product code> format.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Enable the self-hosted Rev decision model alongside a tuned memory budget and timeout so the backend can query it without blocking the hot path.
hcl
copy
enable_runlayer_rev = true
enable_runlayer_topic_cpu = true
runlayer_rev_image_tag = "runlayer-rev-guard-v202609292007"
runlayer_rev_gunicorn_workers = 2
runlayer_rev_memory = 8192
runlayer_rev_timeout = 10
Scope a per-service environment variable to the backend task only, without leaking it to the worker or consumers.
hcl
copy
additional_backend_only_env_vars = {
ECS_TASK_PROTECTION_ENABLED = "true"
}
Adds additional_backend_only_env_vars input for non-sensitive environment variables scoped exclusively to the backend service task, excluding the worker, consumers, and backend migration task — useful for per-service settings like ECS_TASK_PROTECTION_ENABLED. Not checked yet Adds FLOW_TRACE_COLLECTION_ENABLED control (defaults to runlayer_obs_otel_enabled) to decouple backend flow-metric generation from export transport. Not checked yet Adds FLOW_TRACE_ADAPTIVE_SAMPLING_ENABLED for adaptive sampling on hot-path flow traces as an independent cost lever, operative even when remote export is disabled. Not checked yet Adds runlayer_rev_cpu_share input (strictly between 0 and 1) to reserve a fractional CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. share for the Rev container from the slow pool's remainder. Not checked yet
4 details in Everything
Runlayer Terraform module gains additional_tags input for deployment metadata and clarifies agent sandbox requirement for Procedures.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Tag all Runlayer-managed workload resources with environment and team metadata for cost attribution and audit.
hcl
copy
additional_tags = {
environment = "production"
team = "platform"
}
Adds additional_tags input (string map, default {}) to the Terraform module to apply deployment metadata tags to directly managed workload resources; resource identity tags take precedence.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Procedure creation and validation now requires an agent runtime (with AgentCore); without it, both operations return 503. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! Creating or validating a Procedure without an agent runtime (with AgentCore) now returns 503 instead of succeeding.
Runlayer Operator gains extraEnv, opt-in topicCpu.rev self-hosted decision model, and OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. sidecar support.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Enable the opt-in Rev self-hosted decision model so the operator wires RUNLAYER_REV_ENDPOINT_URL and RUNLAYER_REV_TIMEOUT into backends automatically.
yaml
copy
topicCpuRev:
image: REGISTRY/toolguard:runlayer-rev-guard-TAG
topicCpu:
rev:
enabled: true
gunicornWorkers: 2
Inject deployment-wide environment variables into every backend-image workload without risking silent overrides of operator-managed names.
yaml
copy
extraEnv:
- name: MY_CUSTOM_VAR
value: "my-value"
- name: ANOTHER_VAR
value: "another-value"
Configure the OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. endpoint so the OpenTelemetry sidecar exports its health metrics only to the Runlayer-monitored endpoint.
yaml
copy
observability:
otlp:
endpoints:
- name: runlayer-telemetry
protocol: http
url: http://<otlp-collector-host>:4318
Adds extraEnv config key to inject extra environment variables into every backend-image workload; unlike the ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. module's additional_backend_env_vars, any name the operator sets itself is rejected rather than silently overridden.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds topicCpu.rev opt-in self-hosted decision model (POST /predict/runlayer-rev) backed by the topicCpuRev image (REGISTRY/toolguard:runlayer-rev-guard-TAG); enabling it sets RUNLAYER_REV_ENDPOINT_URL and RUNLAYER_REV_TIMEOUT on backends, requires topicCpu.rev.enabled: true and the images.topicCpuRev image, and needs Procedures also configured or Procedure create/validate calls return 503. Not checked yet Adds topicCpu.rev.gunicornWorkers setting to control worker count for the Rev model; memory must be at least (workers + 1) * 2560 MiB (default resource profile: 5632Mi request / 6144Mi limit). Not checked yet
3 details in Everything
Runlayer adds Claude.ai chat import via Anthropic Compliance Access Keys, covering Claude Science, Claude for Microsoft 365, and Claude in Chrome Beta .︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds support for importing Claude.ai chats by pasting an Anthropic sk-ant-api01-… Compliance Access Key (scoped read:compliance_user_data) into Runlayer under Settings → Claude.ai Web (expand Claude.ai Web under Web clients).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds optional Anthropic organization ID filtering (UUID UUID A universally unique identifier, usually a 128-bit value used to identify an object across systems. It is designed to make independently generated identifiers unlikely to collide. or org_… form) on Claude.ai imports to limit which organizations' chats are pulled. Not checked yet Adds beta import of prompts and replies from Claude Science, Claude for Microsoft 365, and Claude in Chrome — sources that Runlayer hooks cannot capture — using the same read:compliance_user_data Compliance Access Key; requires UUID-form org IDs to filter by organization and must be enabled by the Runlayer account team. Not checked yet
3 details in Everything
1.28.944 - Configurable invisible character detection (2026-10-01)
Oct 1, 2026
·
issue 108
Per-category invisible character actions (Allow/Alert/Mask/Block) are now overridable at the connector, client, local-tool family, or individual tool level.
New detection Updated detection Splits invisible character detection into distinct categories — Hidden characters , ANSI colour codes , Control characters , Isolated zero-width characters , C1 control characters , and Encoded hidden text — each configurable with its own action (Allow , Alert , Mask , or Block ). Not checked yet Enables per-category action overrides at the connector, client, local-tool family, or individual tool level, mirroring the existing PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. -type override model. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! Terminal-noise incidents previously dismissed under HIDDEN_CHARS are not transferred to the new CONTROL_CHARS category — prior dismissals are lost and must be re-applied.
1.28.944 (2026-10-01)
Oct 1, 2026
·
issue 092
Runlayer 1.28.944 splits invisible character detection into per-category actions — Allow, Alert, Mask, or Block — with fine-grained overrides.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Splits invisible character detection into distinct categories — ANSI colour codes , Hidden characters , Control characters , Isolated zero-width characters , C1 control characters , and Encoded hidden text — each with its own action (Allow, Alert, Mask, or Block) configurable globally and overridden per connector, client, local-tool family, or tool.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds an ANSI colour codes category (allowed by default) so colourised output from tools like git, lefthook, and pytest no longer triggers hidden-character events. Not checked yet Adds three opt-in strict categories for connectors whose output should never carry invisible text: Isolated zero-width characters , C1 control characters , and Encoded hidden text (covering Unicode tags, invisible operators, unbalanced bidi isolates, and dense zero-width sequences), all allowed by default until explicitly enabled. Not checked yet Concealing sequences (SGR conceal, background colours, OSC hyperlinks and clipboard writes), bidi overrides, and zero-width runs are consolidated under a Hidden characters category that cannot be switched off. Not checked yet Incidents now report the specific category that fired and group terminal-noise events under CONTROL_CHARS instead of HIDDEN_CHARS, so prior dismissals of terminal-noise incidents do not transfer. Not checked yet
Splits invisible character detection into distinct categories — ANSI colour codes , Hidden characters , Control characters , Isolated zero-width characters , C1 control characters , and Encoded hidden text — each with its own action (Allow, Alert, Mask, or Block) configurable globally and overridden per connector, client, local-tool family, or tool.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds an ANSI colour codes category (allowed by default) so colourised output from tools like git, lefthook, and pytest no longer triggers hidden-character events. Not checked yet Adds three opt-in strict categories for connectors whose output should never carry invisible text: Isolated zero-width characters , C1 control characters , and Encoded hidden text (covering Unicode tags, invisible operators, unbalanced bidi isolates, and dense zero-width sequences), all allowed by default until explicitly enabled. Not checked yet Concealing sequences (SGR conceal, background colours, OSC hyperlinks and clipboard writes), bidi overrides, and zero-width runs are consolidated under a Hidden characters category that cannot be switched off. Not checked yet
1 more in Everything
└──▷ BREAKING ON UPGRADE
! Terminal-noise incidents are now grouped under CONTROL_CHARS instead of HIDDEN_CHARS; prior dismissals of those incidents do not transfer to the new grouping.
1.28.943 - Agent web browsing and output analytics (2026-10-01)
Oct 1, 2026
·
issue 108
Adds RunlayerInstance.spec.extraEnv, OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. sidecar health export, list_teams MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool, eval judge agreement, and universal agent web browsing.
Adds RunlayerInstance.spec.extraEnv to the Kubernetes operator CRD CRD A Kubernetes extension that adds a new object type to the cluster, so a tool's configuration is stored, validated and versioned by Kubernetes itself rather than in a file beside it. to append environment variables to every backend-image workload (backend, worker, migration job, consumers) for settings the CRD has no dedicated field for. Not checked yet Adds OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. collector sidecar health metric export in the Kubernetes operator — queue depth, send failures, and receiver refusals — published to endpoints named runlayer-* using protocol: http. Not checked yet Adds list_teams tool to Runlayer MCP for listing workspace teams. Not checked yet Extends list_agents in Runlayer MCP to filter by drafts, tags, disabled status, team, and All Workspace, and to sort by name, last used, or run count. Not checked yet Enables AI output analytics (Output view in Analytics) for all users without requiring admin activation — tracks pull requests, documents, and other artifacts produced by AI sessions. Not checked yet
+5 more
show less
Adds a Most / Least toggle to the Top active accounts card on Analytics → Overview, surfacing the least-active users (including those with zero actions) in the selected range. Not checked yet Adds judge agreement tracking to agent eval comparative scorers — each scorer now shows a confusion matrix and a verdict-match rate against your labels, with a warning when too few cases are labelled. Not checked yet Gives every agent a real browser automatically; per-agent Web browsing toggle is removed — use the agent's network access policy to control site reach. Not checked yet Adds connector search link for admins in My Connectors to jump directly to Manage connectors, including connectors not granted to the admin. Not checked yet Enforces connector tool selection at the gateway — a connector with zero tools selected on an agent now grants that agent zero tools, closing a gap where agent-credentialed requests could previously call every tool on the connector. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! The enable_web_fetch API field and Terraform field are removed — all agents now have web browsing unconditionally; use the agent network access policy to restrict site access instead.! OpenTelemetry collector sidecar health metrics are published ONLY to endpoints named runlayer-* with protocol: http; endpoints with any other name never receive these metrics.
1.28.943 (2026-10-01)
Oct 1, 2026
·
issue 092
Runlayer 1.28.943 adds Kubernetes extraEnv injection, OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. sidecar health export, SkillGuard security scoring, and expanded MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. agent filtering.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Inject a custom environment variable (e.g. an internal API base URL) into all Runlayer backend workloads when the CRD CRD A Kubernetes extension that adds a new object type to the cluster, so a tool's configuration is stored, validated and versioned by Kubernetes itself rather than in a file beside it. has no dedicated field for it.
yaml
copy
spec:
extraEnv:
- name: INTERNAL_API_BASE
value: "https://internal.example.com"
Expose OTel collector sidecar health metrics so Runlayer can monitor your Kubernetes deployment's telemetry pipeline — endpoint name must start with runlayer- and use HTTP.
yaml
copy
endpoints:
- name: runlayer-otel-health
protocol: http
port: 8888
Adds RunlayerInstance.spec.extraEnv to the Kubernetes CRD to append environment variables to every backend-image workload (backend, worker, migration job, consumers) for settings the CRD has no dedicated field for.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. collector sidecar health metric export to endpoints named runlayer-* (protocol: http) covering export queue depth, send failures, and receiver refusals — mirroring ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. telemetry monitoring for Kubernetes deployments. Not checked yet Adds SkillGuard as the engine for skill security scanning, with findings that highlight the specific source lines the model flagged. Not checked yet Expands list_agents in Runlayer MCP to filter by drafts, tags, disabled status, team, and All Workspace, and to sort by name, last used, or run count. Not checked yet Adds a list_teams tool to Runlayer MCP. Not checked yet
+4 more
show less
Enables AI output analytics (the Output view in Analytics) for all workspaces without requiring admin activation. Not checked yet Adds a Most / Least toggle to the Top active accounts card on Analytics → Overview, letting admins surface users with the fewest actions in a selected range. Not checked yet Adds per-scorer confusion matrix and labelling-confidence warning to comparative scorers on eval runs, showing how often each scorer's verdicts match human labels. Not checked yet Enables agent browsing by default for all agents; web access is now governed by the agent's network access policy rather than a per-agent toggle. Not checked yet
Adds RunlayerInstance.spec.extraEnv to the Kubernetes CRD to append environment variables to every backend-image workload (backend, worker, migration job, consumers) for settings the CRD has no dedicated field for.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. collector sidecar health metric export to endpoints named runlayer-* (protocol: http) covering export queue depth, send failures, and receiver refusals — mirroring ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. telemetry monitoring for Kubernetes deployments. Not checked yet Adds a list_teams tool to Runlayer MCP. Not checked yet
6 more in Everything
└──▷ BREAKING ON UPGRADE
! The per-agent Web browsing toggle is removed; web access is now controlled entirely by the agent's network access policy.! The enable_web_fetch API field and Terraform field are removed.! OpenTelemetry collector sidecar health metrics are exported ONLY to endpoints named runlayer-* using protocol: http; endpoints with any other name never receive these metrics.
1.28.933 - Organization LLM budget covers agents (2026-10-01)
Oct 1, 2026
·
issue 108
Org LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. budget now enforces spend limits across agent runs and virtual keys, not just devices.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Extends the organization usage rule's total budget to cover agent runs and virtual keys, halting both at the LLM gateway once the budget is exhausted.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Uninstalling AI Watch on macOS and Windows now removes LLM routing from Claude Code and Codex managed settings, returning retired devices to their normal provider. Not checked yet
Extends the organization usage rule's total budget to cover agent runs and virtual keys, halting both at the LLM gateway once the budget is exhausted.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 more in Everything
1.28.933 (2026-10-01)
Oct 1, 2026
·
issue 092
Organization LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. budget enforcement now extends to agent runs and virtual keys, blocking both at the gateway when the limit is spent.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Runlayer adds self-hosted Rev decision model, OTel Collector OTel Collector An OpenTelemetry vendor-neutral agent, maintained by the CNCF, that receives, processes, and exports telemetry data (traces, metrics, logs) so tools avoid coupling to a specific observability backend. sidecar, and procedures-validator sidecar to ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. Terraform Terraform An open-source infrastructure-as-code tool by HashiCorp that provisions cloud and on-premises resources through declarative configuration files, letting cyber tools automate and version-control their deployment environments. inputs︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Deploy the self-hosted Rev decision model on an m7i.2xlarge with 2 workers, sized to fit alongside the slow and fast containers within the 30720 MiB instance limit.
hcl
copy
enable_runlayer_rev = true
enable_runlayer_topic_cpu = true
runlayer_rev_image_tag = "runlayer-rev-guard-v202609292007"
runlayer_rev_gunicorn_workers = 2
runlayer_rev_memory = 8192
runlayer_rev_cpu_share = 0.20
runlayer_rev_timeout = 10
Enable the OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. Collector sidecar and forward telemetry to a customer-owned OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. gRPC gRPC An open-source remote procedure call framework from Google that uses HTTP/2 and Protocol Buffers to let services call each other's functions across a network, giving tools low-latency, strongly typed inter-process communication. endpoint, while keeping Runlayer-side export configured separately.
hcl
copy
otel_collector = {
export_endpoint = "otel-collector.internal:4317"
}
Attach a procedures-validator sidecar to the serving backend, pinned to a specific digest, with custom CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. and memory reservations.
hcl
copy
procedures_validator = {
image = "registry.example.com/procedures-validator@sha256:abc123"
cpu = 256
memory = 1024
}
Adds enable_runlayer_rev Terraform input to run Rev, Runlayer's self-hosted decision model, as a third container (runlayer-topic-cpu-rev) in the topic CPU task, exposing POST /predict/runlayer-rev on NLB port 8082 and setting RUNLAYER_REV_ENDPOINT_URL and RUNLAYER_REV_TIMEOUT on the backend; requires enable_runlayer_topic_cpu = true.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds runlayer_rev_image_tag Terraform input to specify the Rev container image (Rev-only ToolGuard profile runlayer-rev-guard-v<model_version>, built with image_profile=rev); tag must start with runlayer-rev-guard-v (e.g. runlayer-rev-guard-v202609292007). Not checked yet Adds runlayer_rev_gunicorn_workers Terraform input to control Rev container concurrency (range 1–6); each worker loads its own fp32 encoder (~2.5–2.7 GiB RSS) and serializes forwards, with the recycler briefly running workers+1. Not checked yet Adds runlayer_rev_memory Terraform input to set the hard memory limit (MiB) for the Rev container; must be at least (workers + 1) * 2560 MiB to accommodate recycler overlap. Not checked yet Adds runlayer_rev_cpu_share Terraform input to set the fractional CPU units reserved for the Rev container (soft floor, taken from the slow pool's remainder); fast share + Rev share must stay below 1 unless an absolute override is set. Not checked yet
+3 more
show less
Adds runlayer_rev_timeout Terraform input to set the backend HTTP client timeout in seconds per Rev decision request (RUNLAYER_REV_TIMEOUT), range 1–60; matches operator field topicCpu.rev.timeoutSeconds. Not checked yet Adds an optional OTel Collector sidecar for backend and worker ECS tasks; when enabled, adds a second container receiving telemetry via localhost:4317, with export_endpoint set to the customer-owned OTLP gRPC endpoint (loopback values are rejected at plan time); Runlayer-side export is configured separately via runlayer_obs_otel_* inputs. Not checked yet Adds procedures_validator Terraform input for an optional procedures-validator sidecar on the serving backend task; accepts object({ image = string, cpu = optional(number, 128) , memory = optional(number, 512) }) with image required to be explicitly tagged or digest-pinned. Not checked yet
8 details in Everything
Runlayer launches Sessions & Shadow AI: proactive skill/MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. scanning, AI Watch client, and browser extension across Mac, Windows, and Linux︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Introduces AI Watch , a lightweight endpoint client that detects and logs all employee AI activity across clients, agents, MCPs, skills, and tool calls on Mac, Windows, and Linux.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds proactive scanning of skill files and MCP servers at installation time — before execution — detecting prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. , data exfiltration data exfiltration Moving data out of a system or organization without authorization. It can happen through network transfers, removable media or other channels. , privilege escalation privilege escalation Gaining permissions beyond those an account or process initially had. It can turn limited access into administrator control or access to another user's resources. , and guardrail bypass techniques. Not checked yet Ships a browser extension with AI Watch to cover browser-based AI sessions, supporting Google Chrome, Mozilla Firefox, and Microsoft Edge. Not checked yet Supports deployment of AI Watch via MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. providers including Jamf, Workspace ONE, and Intune for enterprise-scale rollout. Not checked yet Provides full agent session logs with turn-by-turn visibility across user inputs, AI reasoning steps, MCP tool calls, and actions, with in-line alerts on high-risk behavior. Not checked yet
+1 more
show less
Enables deterministic policies to block high-risk skills and tool calls proactively, preventing execution of malicious AI artifacts. Not checked yet
6 details in Everything
1.28.911 - Shadow AI dashboard drill-downs (2026-09-30)
Sep 30, 2026
·
issue 108
Shadow AI dashboard drill-downs now link to filtered Detail tables with shareable URLs, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. gains artifact custom-link management.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Share a pre-filtered Shadow AI details view with a teammate — copy the URL after drilling into a risk level row and send it directly.
📍 In the Shadow AI dashboard, click a skill risk level or managed connector row to open the Details table, then copy the URL from the browser address bar and share it.
Clicking a row on a Shadow AI dashboard card (skill risk level or managed connector) now opens the Details table with matching filters applied.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Details table filters are persisted in the page URL, enabling shareable filtered views and a functioning Back button that returns to the originating dashboard tab. Not checked yet Assistants and agents can now set, change, or remove an artifact's custom link, and open an artifact from its custom link, through Runlayer MCP. Not checked yet
Clicking a row on a Shadow AI dashboard card (skill risk level or managed connector) now opens the Details table with matching filters applied.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Assistants and agents can now set, change, or remove an artifact's custom link, and open an artifact from its custom link, through Runlayer MCP. Not checked yet
1 more in Everything
1.28.911 (2026-09-30)
Sep 30, 2026
·
issue 091
Runlayer 1.28.911 adds artifact custom-link management via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. and shareable URL-persisted Details filters for Shadow AI.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Enables assistants and agents to set, change, remove, and open an artifact by its custom link through Runlayer MCP.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Persists Shadow AI Details table filters in the page URL so filtered views can be shared directly, with Back returning to the originating dashboard tab. Not checked yet Collapses the Connected Agent Apps list on the Integrations page by default with a count, preventing long page loads in large Slack workspaces. Not checked yet
Enables assistants and agents to set, change, remove, and open an artifact by its custom link through Runlayer MCP.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
2 more in Everything
Runlayer Terraform module gains AgentCore VPC VPC A logically isolated virtual network inside a public cloud provider's infrastructure, letting tools deploy resources with private addressing, controlled routing, and firewall rules without managing physical hardware. /PrivateLink PrivateLink An AWS networking feature that exposes a service over a private endpoint inside a VPC, so traffic never traverses the public internet, giving cyber tools a way to integrate with cloud services without opening public routes. networking inputs and scan-budget timeout controls︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Deploy AgentCore over a module-created private VPC with PrivateLink, letting the module auto-derive all subnets from the default CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. block.
hcl
copy
runlayer_agentcore_network_mode = "VPC"
enable_privatelink = true
runlayer_agentcore_consumer_vpc_cidr_block = "10.112.0.0/20"
Bring an existing VPC and specific private subnets for the AgentCore consumer endpoint instead of letting the module create one.
hcl
copy
runlayer_agentcore_network_mode = "VPC"
enable_privatelink = true
runlayer_agentcore_consumer_vpc_id = "vpc-0abc12345def67890"
runlayer_agentcore_consumer_private_subnet_ids = ["subnet-0aaa111", "subnet-0bbb222"]
Adds runlayer_agentcore_consumer_vpc_id with runlayer_agentcore_consumer_private_subnet_ids Terraform inputs to bring an existing VPC for the AgentCore consumer endpoint. Not checked yet Adds runlayer_agentcore_consumer_vpc_cidr_block Terraform input (defaults to 10.112.0.0/20) to let the module create a dedicated AgentCore consumer VPC, which connects only via PrivateLink and may overlap other VPC ranges. Not checked yet Adds public subnet CIDR input for NAT egress in the module-created AgentCore consumer VPC, one per AZ; when left unset alongside the private list, subnets are auto-derived from the first half of the consumer CIDR block (starting at 10.112.0.0/24). Not checked yet Enforcement scans now draw their timeout from the workspace scan latency budget (Security Scanners -> Scan budgets, range 50 ms–300 s, configurable fail-open or fail-closed); a ToolGuard backend timeout also governs tool-list scans, analyze, and models requests, all of which fail open on timeout. Not checked yet
Adds runlayer_agentcore_consumer_vpc_id with runlayer_agentcore_consumer_private_subnet_ids Terraform inputs to bring an existing VPC for the AgentCore consumer endpoint. Not checked yet Adds runlayer_agentcore_consumer_vpc_cidr_block Terraform input (defaults to 10.112.0.0/20) to let the module create a dedicated AgentCore consumer VPC, which connects only via PrivateLink and may overlap other VPC ranges. Not checked yet Adds public subnet CIDR input for NAT egress in the module-created AgentCore consumer VPC, one per AZ; when left unset alongside the private list, subnets are auto-derived from the first half of the consumer CIDR block (starting at 10.112.0.0/24). Not checked yet
1 more in Everything
Runlayer agents can now DM any person by email from webhook, schedule, or API runs — no Slack user ID needed.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Have a webhook-triggered run DM a ticket assignee when the agent finishes, by passing their email in the payload instead of looking up a Slack user ID.
📍 Steps: In your webhook payload, include the assignee email (e.g. assignee_email: alice@example.com). In the agent prompt, write: 'When done, DM the ticket assignee at the assignee_email from the payload with a summary.' Runlayer resolves the email to the linked Slack account automatically.
Enables agents started by webhook, schedule, or API to send Slack DMs to any person addressed by email (e.g.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ assignee_email in the webhook payload) — no Slack user ID required. Not checked yet Supports addressing the run owner directly in playground prompts (e.g. 'DM me the summary when you're done') so the agent resolves the sender automatically. Not checked yet
Enables agents started by webhook, schedule, or API to send Slack DMs to any person addressed by email (e.g.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ assignee_email in the webhook payload) — no Slack user ID required. Not checked yet
1 more in Everything
Runlayer adds a Platform Analytics section with artifact view metrics, unique visitor counts, and source breakdowns.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Check which artifacts are getting the most traction across your org, and where views are coming from (app, Slack, or MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. client).
📍 In the Runlayer console, navigate to Platform Analytics › Artifacts. Ensure your account has the View Company Metrics permission (Analytics Admin). Review Most viewed artifacts , Artifact views over time , and Views by source for the desired date range.
Adds an Artifacts analytics section showing Artifact views , Unique visitors , Artifacts viewed , Artifact views over time , Most viewed artifacts , and Views by source (broken down by app, Slack, or MCP client).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Users with View Company Metrics (such as Analytics Admin) see org-wide counts, the chart, and Views by source ; others see metrics only for artifacts they created. Not checked yet Most viewed artifacts shows artifact titles org-wide only when the viewer also has Manage Agents ; otherwise it appears as Your most viewed artifacts and is scoped to the viewer's own artifacts. Not checked yet
3 details in Everything
1.28.902 - Artifact view analytics and custom links (2026-09-30)
Sep 30, 2026
·
issue 108
Runlayer 1.28.902 adds artifact view analytics, custom artifact links, editable LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. Gateway routing rules, Slack DMs from any agent run, and AI-generated agent icons.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Create a new agent that is Slack-enabled from the start, now that Slack setup is opt-in.
json
copy
{ "name": "ops-assistant", "enable_channels": ["slack"] }
Restore the old per-IP failover connect behaviour for AI Watch hooks in environments where the new happy-eyeballs logic causes unexpected timeouts.
.env
copy
RUNLAYER_HAPPY_EYEBALLS=0
Add Slack to an agent that was created without it, now that Slack setup is decoupled from agent creation.
json
copy
{ "agent_id": "<agent_id>", "enable_channels": ["slack"] }
Adds enable_channels=["slack"] parameter to the create_agent MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool to opt in to Slack app creation; agents created without it no longer receive a Slack app or slack_app_created event, and Slack can be added later via update_agent.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds RUNLAYER_HAPPY_EYEBALLS=0 environment variable to restore previous per-IP connect behaviour for AI Watch hooks when the network path to Runlayer is unavailable. Not checked yet Adds an artifact views counter in the artifact header showing who opened it and whether they arrived from Runlayer, Slack, or an MCP client, plus an org-wide Artifacts tab in Analytics for admins showing the most viewed artifacts. Not checked yet Admins can now edit existing LLM Gateway routing rules' pattern, target, and condition in place, and edit a virtual key's name, spend budget, and over-budget behaviour from Settings → LLM Gateway without rotating the key. Not checked yet Slack DMs from any agent run: agents started from the playground, a webhook, or a schedule can now DM people on Slack by email address. Not checked yet
+2 more
show less
AI-generated agent icons: the agent icon picker gains a Generate tab that creates an icon from the agent's name, instructions, and workspace; requires an OpenAI API key. Not checked yet Agent run token accounting now covers cache read, cache write, and reasoning tokens reasoning tokens Intermediate reasoning a model writes out before its final answer. Reasoning models generate it automatically and it is often billed as extra output tokens. : the Agent Monitor's Tokens tile counts them alongside input and output with a model pricing hover card listing the cache write price per million tokens, and a finished run's status strip shows input, output, and cached token counts next to its cost with a hover breakdown including cache writes and reasoning tokens. Not checked yet
Adds enable_channels=["slack"] parameter to the create_agent MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool to opt in to Slack app creation; agents created without it no longer receive a Slack app or slack_app_created event, and Slack can be added later via update_agent.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds RUNLAYER_HAPPY_EYEBALLS=0 environment variable to restore previous per-IP connect behaviour for AI Watch hooks when the network path to Runlayer is unavailable. Not checked yet Adds an artifact views counter in the artifact header showing who opened it and whether they arrived from Runlayer, Slack, or an MCP client, plus an org-wide Artifacts tab in Analytics for admins showing the most viewed artifacts. Not checked yet AI-generated agent icons: the agent icon picker gains a Generate tab that creates an icon from the agent's name, instructions, and workspace; requires an OpenAI API key. Not checked yet
3 more in Everything
└──▷ BREAKING ON UPGRADE
! get_skill and get_skill_file plugin skill tools no longer accept the old query, skill, and file arguments — only skill_id (and file_id for files) are accepted; clients holding an older tool list receive an error directing them to use search_skills instead.! The create_agent MCP tool no longer creates a Slack app by default; callers that relied on automatic Slack app creation must now pass enable_channels=["slack"] explicitly.
1.28.902 (2026-09-30)
Sep 30, 2026
·
issue 090
Runlayer 1.28.902 adds artifact view analytics, custom artifact links, in-place LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. Gateway rule editing, AI-generated agent icons, and Slack DMs from any agent run.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Create a new agent via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. without automatically provisioning a Slack app, then add Slack explicitly afterward.
copy
$ # Create agent with no Slack app
create_agent name='Cost Watcher' instructions='Monitor spend and alert on anomalies.'
# Later, opt in to Slack
update_agent agent_id='<agent_id>' enable_channels=['slack']
Navigate to the org-wide artifact analytics view to identify which artifacts are most accessed and from which surfaces (Runlayer, Slack, MCP).
📍 In the Runlayer console, go to Analytics › Artifacts tab to view the most-viewed artifacts across your organisation, including per-artifact visitor counts and source breakdown.
Adds enable_channels=["slack"] parameter to the create_agent MCP tool so Slack app provisioning is now opt-in; use update_agent to add Slack later.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds RUNLAYER_HAPPY_EYEBALLS=0 environment variable to restore previous per-IP connect behaviour when the network path to Runlayer is down. Not checked yet Adds artifact view analytics — a views counter in the artifact header shows how many people opened the artifact, who they were, and whether they arrived via Runlayer, Slack, or an MCP client. Not checked yet Adds an org-wide Artifacts tab in Analytics for admins showing the most-viewed artifacts across the organisation. Not checked yet Adds custom artifact links so an artifact can be given a readable address (e.g. /artifacts/kpi-dashboard) from its ⋯ menu, with the original link remaining valid. Not checked yet
+6 more
show less
Adds a Generate tab to the agent icon picker that creates an icon from the agent's name, instructions, and workspace; requires an OpenAI API key. Not checked yet Enables agents started from the playground, a webhook, or a schedule to DM people on Slack by email, so DM me when done requests work outside Slack. Not checked yet Enables in-place editing of LLM Gateway routing rules — admins can now change the pattern, target, and condition of an existing rule without deleting and re-adding it. Not checked yet Enables in-place editing of LLM Gateway virtual keys — admins can change a key's name, spend budget, and over-budget behaviour from Settings → LLM Gateway without changing the key itself. Not checked yet Expands Agent Monitor token accounting to include cache read, cache write, and reasoning tokens reasoning tokens Intermediate reasoning a model writes out before its final answer. Reasoning models generate it automatically and it is often billed as extra output tokens. in the Tokens tile and the model pricing hover card. Not checked yet Adds input, output, and cached token counts with cost to the finished agent run's status strip, with a hover breakdown including cache writes and reasoning tokens. Not checked yet
Adds enable_channels=["slack"] parameter to the create_agent MCP tool so Slack app provisioning is now opt-in; use update_agent to add Slack later.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds RUNLAYER_HAPPY_EYEBALLS=0 environment variable to restore previous per-IP connect behaviour when the network path to Runlayer is down. Not checked yet Adds artifact view analytics — a views counter in the artifact header shows how many people opened the artifact, who they were, and whether they arrived via Runlayer, Slack, or an MCP client. Not checked yet Adds an org-wide Artifacts tab in Analytics for admins showing the most-viewed artifacts across the organisation. Not checked yet Adds custom artifact links so an artifact can be given a readable address (e.g. /artifacts/kpi-dashboard) from its ⋯ menu, with the original link remaining valid. Not checked yet
+1 more
show less
Adds a Generate tab to the agent icon picker that creates an icon from the agent's name, instructions, and workspace; requires an OpenAI API key. Not checked yet
5 more in Everything
└──▷ BREAKING ON UPGRADE
! get_skill and get_skill_file plugin skill tools no longer accept the old query and skill / file arguments — only skill_id (and file_id for files) are accepted; clients holding an older tool list receive an error directing them to use search_skills instead.! The create_agent MCP tool no longer provisions a Slack app or emits a slack_app_created event unless enable_channels=["slack"] is passed in the call.
Runlayer adds a standalone session-search indexer, flow-trace collection toggles, and VPC VPC A logically isolated virtual network inside a public cloud provider's infrastructure, letting tools deploy resources with private addressing, controlled routing, and firewall rules without managing physical hardware. /PrivateLink PrivateLink An AWS networking feature that exposes a service over a private endpoint inside a VPC, so traffic never traverses the public internet, giving cyber tools a way to integrate with cloud services without opening public routes. networking controls for ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. deployments.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Enable the session-search indexer in soak mode first so you can validate extraction metrics before committing real index writes.
hcl
copy
enable_session_search_indexer = true
enable_hook_events_pipeline = true
session_search_index_mode = "shadow"
session_search_indexer_config = {
cpu = 512
memory = 2048
}
Promote to write mode and tune flush frequency without changing the module, using the FF_ENABLE flag to bypass per-org feature gates in staging.
hcl
copy
session_search_index_mode = "write"
session_search_indexer_extra_env = {
SESSIONS_SEARCH_FLUSH_SECONDS = "5"
FF_ENABLE = "session-search-ingest"
}
Decouple flow-trace collection from OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. export and enable adaptive sampling to reduce cost on high-throughput paths.
hcl
copy
FLOW_TRACE_COLLECTION_ENABLED = true
FLOW_TRACE_ADAPTIVE_SAMPLING_ENABLED = true
Adds FLOW_TRACE_COLLECTION_ENABLED environment variable to enable or disable backend flow-metric generation independently of export transport; defaults to runlayer_central_otel_enabled || runlayer_obs_otel_enabled.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds FLOW_TRACE_ADAPTIVE_SAMPLING_ENABLED as an independent cost lever that sheds local step-recording work even when remote export is off. Not checked yet Adds runlayer_agentcore_network_mode Terraform input requiring PUBLIC or VPC; VPC mode requires enable_privatelink = true and either runlayer_agentcore_consumer_vpc_id with runlayer_agentcore_consumer_private_subnet_ids, or runlayer_agentcore_consumer_vpc_cidr_block with matching private and public subnet CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. lists. Not checked yet Adds enable_session_search_indexer Terraform input to deploy a standalone Kinesis consumer that extracts searchable text, entities, and findings from hook events and writes the session-search index tables in Postgres; opt-in, default off, requires enable_hook_events_pipeline = true. Not checked yet Adds session_search_indexer_config Terraform input to configure cpu (minimum 256) and memory (minimum 1024) for the session-search indexer ECS service. Not checked yet
+2 more
show less
Adds session_search_index_mode Terraform input (values: off, shadow, write) to control indexer behaviour: shadow parses and extracts without writing, write enables real index writes and the coverage-gap alarm, off scales the ECS service to 0 while preserving checkpoint state. Not checked yet Adds session_search_indexer_extra_env Terraform input for passthrough environment variables (keys must start with SESSIONS_SEARCH_ or be FF_ENABLE/FF_DISABLE) to tune indexer knobs such as SESSIONS_SEARCH_FLUSH_SECONDS and SESSIONS_SEARCH_MAX_ROWS_PER_SECOND without a module change. Not checked yet
7 details in Everything
1.28.869 (2026-09-29)
Sep 29, 2026
·
issue 089
Runlayer 1.28.869 adds AI browser inventory, obs-only flow metrics opt-out, Claude Sonnet 5.5 for agents, and connector event triggers for all workspaces.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Opt out of automatic flow-metric collection when running obs-only OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. export without tooling export, to avoid unexpected data ingestion.
hcl
copy
flow_metrics_collection_enabled = false
Adds flow_metrics_collection_enabled = false Terraform ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. config key to opt out of backend flow-metric collection when observability OTLP export is on and tooling export is off (collection now defaults on in that mode).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet AI Watch Detect now inventories 16 standalone AI browsers built on Chromium — including Perplexity Comet, Dia, Opera Neon, ChatGPT Atlas, Norton Neo, and BrowserOS — on macOS, Windows, and Linux, counting a browser as installed only when its own installation is found. Not checked yet AI Watch Detect inventories 16 more standalone AI browsers — including Fellou, Strawberry Browser, Kahana Oasis, and kweo — on macOS, Windows, and Linux. Not checked yet Agents can now run on Claude Sonnet 5.5 via the Anthropic API or AWS Bedrock, with adaptive thinking effort settings. Not checked yet Connector event triggers — such as a new Gmail label, Linear issue, or Google Drive file — are now available for agents in every workspace without requiring an access request. Not checked yet
+1 more
show less
Adds a Fetch deployments button when adding or editing an Azure Foundry AI provider, automatically listing models served by the endpoint and populating deployment names. Not checked yet
Adds flow_metrics_collection_enabled = false Terraform ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. config key to opt out of backend flow-metric collection when observability OTLP export is on and tooling export is off (collection now defaults on in that mode).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet AI Watch Detect now inventories 16 standalone AI browsers built on Chromium — including Perplexity Comet, Dia, Opera Neon, ChatGPT Atlas, Norton Neo, and BrowserOS — on macOS, Windows, and Linux, counting a browser as installed only when its own installation is found. Not checked yet
4 more in Everything
└──▷ BREAKING ON UPGRADE
! With observability OTLP export on and tooling export off, backend flow-metric collection now defaults on — operators who did not previously collect flow metrics in this configuration must explicitly set flow_metrics_collection_enabled = false in their Terraform ECS inputs to opt out.
Runlayer Terraform ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. module gains sandbox egress proxy, SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. export consumers, and new config inputs for AZ selection and secret-store identity.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Enable the identity-aware egress proxy for agent sandboxes so outbound traffic is filtered by organization policy rather than allowed directly through NAT.
hcl
copy
sandbox_egress_mode = "proxy"
runlayer_agentcore_network_mode = "VPC"
sandbox_egress_proxy_dns_servers = ["1.1.1.1", "8.8.8.8"]
sandbox_egress_proxy_egress_ports = [443, 8080]
sandbox_egress_proxy_platform_allow_hosts = ["*.mycompany.internal"]
Ship audit-log SIEM data to a downstream system by enabling the standalone Kinesis consumer ECS service with enough capacity for production-volume audit records.
hcl
copy
audit_log_siem_export_kinesis_consumer_config = {
enabled = true
cpu = 512
memory = 1024
desired_count = 2
}
Route critical CloudWatch alarms to an internal Slack relay SNS SNS Amazon Simple Notification Service, a managed pub/sub messaging service from AWS that lets tools fan out alerts or events to multiple subscribers — queues, email, HTTP endpoints, or Lambda functions — without managing broker infrastructure. topic alongside the default alerting path.
hcl
copy
critical_alerts_extra_sns_topic_arns = [
"arn:aws:sns:us-east-1:123456789012:slack-critical-relay"
]
Adds sandbox_egress_mode Terraform input (values: direct, proxy, proxy_only) to control how AgentCore sandboxes reach the internet, with direct as the default; proxy and proxy_only require runlayer_agentcore_network_mode = VPC.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds sandbox_egress_proxy_image_uri input to override the sandbox egress proxy container image; must include an explicit tag or digest. Not checked yet Adds sandbox_egress_proxy_dns_servers input (default ["1.1.1.1", "8.8.8.8"]) to set upstream IPv4 DNS resolvers used by the sandbox egress proxy for destination lookups. Not checked yet Adds sandbox_egress_proxy_platform_allow_hosts input to specify additional platform host patterns the egress proxy permits, using the same grammar as agent policies (host, *.host, optional :port). Not checked yet Adds sandbox_egress_proxy_egress_ports input (default [443]) to declare extra TCP TCP A network protocol that delivers a reliable, ordered stream of bytes between two endpoints. It detects lost data and retransmits it. destination ports the egress proxy security group may open to the internet. Not checked yet
+7 more
show less
Adds secret_stores_allow_aws_workload_identity input to allow AWS secret stores without a role ARN to use the backend ECS task role; intended for single-org self-hosted deployments only. Not checked yet Adds critical_alerts_extra_sns_topic_arns input to fan out critical alarms to extra SNS topics (e.g. an internal Slack relay), capped at 3 extra topics when ToolGuard alarms are enabled (4 when enable_monitoring or critical_alerts_enabled is off). Not checked yet Adds audit_log_siem_export_kinesis_consumer_config input to configure a standalone audit-log SIEM export ECS service that exports enriched SIEM objects from the audit-log Kinesis stream; requires cpu >= 256, memory >= 512, desired_count >= 1. Not checked yet Adds session_materializer_config input to configure a standalone session-materializer Kinesis consumer ECS service that reads the hook-events stream and performs segment compaction; requires cpu >= 256, memory >= 3072, desired_count >= 0. Not checked yet Adds cold_analyzers_consumer_config input to configure a standalone cold-analyzers Kinesis consumer ECS service that reads the hook-events stream; requires cpu >= 256, memory >= 2048, desired_count >= 0. Not checked yet Adds session_siem_export_kinesis_consumer_config input to configure a standalone session SIEM export ECS service that writes gzipped NDJSON NDJSON A text format where each line is a self-contained JSON object, making it easy to stream, append, and parse large datasets record-by-record without loading the whole file into memory. to a managed or external S3 bucket; requires cpu >= 256, memory >= 2048, desired_count >= 1. Not checked yet Documents availability-zone selection for the main VPC VPC A logically isolated virtual network inside a public cloud provider's infrastructure, letting tools deploy resources with private addressing, controlled routing, and firewall rules without managing physical hardware. , RDS, and the AgentCore consumer VPC, with the plan failing if a listed AZ is not supported in AgentCore. Not checked yet
Adds sandbox_egress_mode Terraform input (values: direct, proxy, proxy_only) to control how AgentCore sandboxes reach the internet, with direct as the default; proxy and proxy_only require runlayer_agentcore_network_mode = VPC.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds sandbox_egress_proxy_image_uri input to override the sandbox egress proxy container image; must include an explicit tag or digest. Not checked yet Adds sandbox_egress_proxy_dns_servers input (default ["1.1.1.1", "8.8.8.8"]) to set upstream IPv4 DNS resolvers used by the sandbox egress proxy for destination lookups. Not checked yet Adds sandbox_egress_proxy_platform_allow_hosts input to specify additional platform host patterns the egress proxy permits, using the same grammar as agent policies (host, *.host, optional :port). Not checked yet Adds sandbox_egress_proxy_egress_ports input (default [443]) to declare extra TCP TCP A network protocol that delivers a reliable, ordered stream of bytes between two endpoints. It detects lost data and retransmits it. destination ports the egress proxy security group may open to the internet. Not checked yet
+6 more
show less
Adds secret_stores_allow_aws_workload_identity input to allow AWS secret stores without a role ARN to use the backend ECS task role; intended for single-org self-hosted deployments only. Not checked yet Adds critical_alerts_extra_sns_topic_arns input to fan out critical alarms to extra SNS topics (e.g. an internal Slack relay), capped at 3 extra topics when ToolGuard alarms are enabled (4 when enable_monitoring or critical_alerts_enabled is off). Not checked yet Adds audit_log_siem_export_kinesis_consumer_config input to configure a standalone audit-log SIEM export ECS service that exports enriched SIEM objects from the audit-log Kinesis stream; requires cpu >= 256, memory >= 512, desired_count >= 1. Not checked yet Adds session_materializer_config input to configure a standalone session-materializer Kinesis consumer ECS service that reads the hook-events stream and performs segment compaction; requires cpu >= 256, memory >= 3072, desired_count >= 0. Not checked yet Adds cold_analyzers_consumer_config input to configure a standalone cold-analyzers Kinesis consumer ECS service that reads the hook-events stream; requires cpu >= 256, memory >= 2048, desired_count >= 0. Not checked yet Adds session_siem_export_kinesis_consumer_config input to configure a standalone session SIEM export ECS service that writes gzipped NDJSON NDJSON A text format where each line is a self-contained JSON object, making it easy to stream, append, and parse large datasets record-by-record without loading the whole file into memory. to a managed or external S3 bucket; requires cpu >= 256, memory >= 2048, desired_count >= 1. Not checked yet
1 more in Everything
Runlayer Terraform module gains Bedrock provider fan-out for Slack monitors and a sandbox egress proxy mode.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Enable the sandbox egress proxy for all organizations before cutting over to proxy-only mode to avoid a gap in sandbox internet access.
hcl
copy
additional_backend_env_vars = { FF_ENABLE = "<flags already forced>,sandbox-egress-proxy" }
After the backend rollout completes, enforce proxy-only egress so no sandbox run bypasses the proxy.
hcl
copy
sandbox_egress_mode = "proxy_only"
Adds BEDROCK_ENABLED support to the agent-event-trigger consumer, granting nonstreaming bedrock:InvokeModel access to Claude foundation models and deployment-account Claude inference profiles for legacy platform fallback.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds sts:AssumeRole grants scoped to arn:aws:iam::*:role/runlayer-bedrock-* and arn:aws:iam::*:role/RunlayerBedrock* so the ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. task role can assume saved Bedrock provider roles for Slack monitors. Not checked yet Adds sandbox_egress_mode = "proxy_only" Terraform setting to route all sandbox internet traffic exclusively through the egress proxy. Not checked yet Adds FF_ENABLE flag sandbox-egress-proxy (set via additional_backend_env_vars) to enable the sandbox egress proxy per organization before switching to proxy_only mode. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! Updating the consumer image alone does not install the new bedrock:InvokeModel IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. permission — the Terraform module must also be upgraded and applied, or the permission will be missing after rollout.! Setting sandbox_egress_mode = "proxy_only" without first enabling the sandbox-egress-proxy feature flag (via additional_backend_env_vars / FF_ENABLE) and waiting for the backend rollout will leave organizations without the flag without sandbox internet access for several minutes.
Runlayer adds a unified policy engine extending POST /api/v1/policies to agents, skills, plugins, artifacts, teams, and org-level actions.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Grant a support group permission to view and run a specific triage agent, using the new unified policy body shape.
copy
$ curl -s -X POST "$RUNLAYER_URL/api/v1/policies" \
-H "x-runlayer-api-key: $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"principal": { "type": "group", "ids": ["'$GROUP_ID'"] },
"kind": "permission",
"effect": "allow",
"resource": { "type": "agent", "ids": ["'$AGENT_ID'"] },
"actions": ["view", "run"],
"description": "Support group can run the triage agent",
"conditions": []
}' | jq '{id, principal, effect, resource, actions}'
Block a specific group from accessing a skill that is otherwise shared with the whole organization, using an explicit org-allow plus group-deny pair.
copy
$ # Step 1: allow the whole org
curl -s -X POST "$RUNLAYER_URL/api/v1/policies" \
-H "x-runlayer-api-key: $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"principal": { "type": "org" },
"kind": "permission",
"effect": "allow",
"resource": { "type": "skill", "ids": ["'$SKILL_ID'"] },
"actions": ["view", "use"],
"conditions": []
}'
# Step 2: explicitly deny the restricted group (deny beats allow)
curl -s -X POST "$RUNLAYER_URL/api/v1/policies" \
-H "x-runlayer-api-key: $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"principal": { "type": "group", "ids": ["'$RESTRICTED_GROUP_ID'"] },
"kind": "permission",
"effect": "deny",
"resource": { "type": "skill", "ids": ["'$SKILL_ID'"] },
"actions": ["*"],
"conditions": []
}'
Delegate agent-creation rights to a Finance team by granting the create_agent org-level action to an attributes-matched principal.
copy
$ curl -s -X POST "$RUNLAYER_URL/api/v1/policies" \
-H "x-runlayer-api-key: $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"principal": { "type": "attributes", "attributes": { "department": "Finance" } },
"kind": "permission",
"effect": "allow",
"resource": { "type": "org" },
"actions": ["create_agent"],
"description": "Finance staff can create agents",
"conditions": []
}' | jq '{id, principal, resource, actions}'
Extends POST /api/v1/policies with a unified body shape that targets agent, skill, plugin, artifact, agent_account, team, and org resource types, alongside the existing connector shape.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds effect (replacing connector-shape action), resource ({ "type": "<type>", "ids": [...] }, { "type": "<type>", "all": true }, or { "type": "org" }), and actions (list of action names) fields to the unified policy body. Not checked yet Introduces team and org principal types (unified shape only), and an owner principal that resolves to whoever owns the resource being checked. Not checked yet Defines a full action vocabulary per resource type: connector adds use, call_tool:*, call_tool:<name>, read_resource:*, read_resource:<uri>, edit_security, run_diagnostics, view_metrics; agent adds run, view_runs_own, view_runs_all; artifact adds download; team adds join, share_assets; org exposes admin capabilities including manage_admins, view_audit_logs_all, view_unredacted_content, manage_security_policies, manage_policies, create_connector, create_agent, and more. Not checked yet Adds named preset bundles — Viewer , Editor , and Manager — that expand to concrete action sets: Viewer grants view plus the type's consume action; Editor adds edit and share; Manager adds manage_access. Not checked yet
+2 more
show less
Enforces explicit-deny semantics: any matching deny policy overrides all allow policies including owner and share grants, affecting open, run, call, and download operations in real time. Not checked yet Returns error code unified_policy_engine_inactive when a unified-shape request targets a non-connector resource whose workspace has not yet been migrated to the unified policy store. Not checked yet
7 details in Everything
1.28.845 (2026-09-28)
Sep 28, 2026
·
issue 089
Runlayer 1.28.845 adds OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. API key ingestion for AI clients, Pi integration, and MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. -only Shadow AI Scan key minting.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Set up OTLP telemetry ingestion from Claude Code into Runlayer by creating a write-only OTLP Telemetry API key scoped to OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. only.
📍 In the Runlayer console, go to Organization API keys → Create key, select the OTLP Telemetry permission (must be the only permission), then configure your Claude Code exporter to send logs, metrics, and traces to your Runlayer OTLP endpoint using the generated key.
Connect an Oh My Pi agent to Runlayer governance in one step, routing its MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools through Runlayer policy enforcement.
Adds a new write-only OTLP Telemetry organization API key permission for OpenTelemetry ingestion (logs, metrics, traces) from AI clients such as Claude Code, Claude Cowork, and Glean; created from the Organization API keys page and must be the key's only permission — cannot use the AI Watch scan or hook endpoints.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Restricts Shadow AI Scan key creation to the MDM configuration wizard only; the Organization API keys page no longer offers the Shadow AI Scan role, and the API rejects hand-created keys with it, ensuring every key links devices and scan data to a configuration card. Not checked yet Adds a Pi integration guide enabling agents built on Pi to route MCP tools through Runlayer, enforce policy on local tools like bash, and record activity in Sessions. Not checked yet Adds an Oh My Pi (omp) tab in the connector setup guide with a one-line /mcp add command that signs in and saves the connector. Not checked yet Adds generated chat titles to an agent's chat list, replacing the first prompt, with rename available from the ⋯ menu. Not checked yet
+3 more
show less
Adds redirect URI approval guidance — the approval screen now shows the path Settings → General → OAuth redirect URIs and lets members copy a shareable link for their admin. Not checked yet Speeds up AI Watch scans by batching artifact reporting in requests of up to 25 artifacts instead of one request per artifact, reducing traffic against the Runlayer deployment. Not checked yet Skips unchanged plugins already held by the server for the same window as skills, cutting repeat uploads on every scheduled scan tick. Not checked yet
Adds a new write-only OTLP Telemetry organization API key permission for OpenTelemetry ingestion (logs, metrics, traces) from AI clients such as Claude Code, Claude Cowork, and Glean; created from the Organization API keys page and must be the key's only permission — cannot use the AI Watch scan or hook endpoints.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Pi integration guide enabling agents built on Pi to route MCP tools through Runlayer, enforce policy on local tools like bash, and record activity in Sessions. Not checked yet Adds an Oh My Pi (omp) tab in the connector setup guide with a one-line /mcp add command that signs in and saves the connector. Not checked yet Adds generated chat titles to an agent's chat list, replacing the first prompt, with rename available from the ⋯ menu. Not checked yet
4 more in Everything
└──▷ BREAKING ON UPGRADE
! The Organization API keys page no longer offers the Shadow AI Scan role, and the API rejects hand-created keys with that role; Shadow AI Scan keys must now be minted through the MDM configuration wizard.
Runlayer: Adds Claude Opus 5.5 support for agents through the Anthropic API or AWS Bedrock, with adaptive thinking effort settings.
└──▷ TRY IT
Confirm which org or enrollment API key a managed device is actually using before troubleshooting an enrollment failure.
copy
$ aiwatch config show
Create an agent via Runlayer MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. and skip Slack setup in one call, useful for headless or CI-provisioned agents that should not have a Slack presence.
json
copy
{
"name": "data-pipeline-agent",
"enable_channels": []
}
Lock down an access policy so it only applies when a client connected via device-code registration, not pre-registered or manually issued credentials.
json
copy
{
"condition": {
"field": "meta.client.kind",
"operator": "equals",
"value": "dcr"
}
}
Adds GPT-6 Sol and GPT-6 Luna model support for agents on the OpenAI provider. Not checked yet Adds channel-only mode for Slack agents so admins can turn off direct messages; users who DM the agent are redirected to mention it in a channel. Not checked yet Adds queued agent messages so follow-ups sent while an agent is working run in order, with the ability to edit, reorder, or remove queued messages. Not checked yet Adds shareable, bookmark-able filtered Policies views for admins, and connector notices now deep-link to Policies filtered to the relevant connector. Not checked yet Adds Gemini support through OpenAI-Compatible providers pointed at generativelanguage.googleapis.com, sending API keys in the format Google expects rather than as a Bearer token Bearer token A credential that grants access to whoever presents it, without a separate proof of possession. Protecting the token matters because a stolen copy can be used by someone else. . Not checked yet
+2 more
show less
Adds Shadow AI access controls limiting saved Shadow AI skill and plugin files to resource managers and security or analytics reviewers; organization-wide Shadow AI REST APIs REST APIs A convention for building HTTP-based interfaces where resources are addressed by URL and manipulated with standard verbs like GET, POST, and DELETE, giving cyber tools a predictable way to integrate with external services. and MCP tools now require organization-wide audit log access. Not checked yet Enables Slack setup for agents through Runlayer MCP without requiring an elevated role, for any user who can edit the agent. Not checked yet
Adds channel-only mode for Slack agents so admins can turn off direct messages; users who DM the agent are redirected to mention it in a channel. Not checked yet Adds queued agent messages so follow-ups sent while an agent is working run in order, with the ability to edit, reorder, or remove queued messages. Not checked yet Adds shareable, bookmark-able filtered Policies views for admins, and connector notices now deep-link to Policies filtered to the relevant connector. Not checked yet Adds Gemini support through OpenAI-Compatible providers pointed at generativelanguage.googleapis.com, sending API keys in the format Google expects rather than as a Bearer token Bearer token A credential that grants access to whoever presents it, without a separate proof of possession. Protecting the token matters because a stolen copy can be used by someone else. . Not checked yet Adds Shadow AI access controls limiting saved Shadow AI skill and plugin files to resource managers and security or analytics reviewers; organization-wide Shadow AI REST APIs REST APIs A convention for building HTTP-based interfaces where resources are addressed by URL and manipulated with standard verbs like GET, POST, and DELETE, giving cyber tools a predictable way to integrate with external services. and MCP tools now require organization-wide audit log access. Not checked yet
2 more in Everything
└──▷ BREAKING ON UPGRADE
! AI Watch Enforce now blocks MCP launchers whose --host does not point at your Runlayer deployment or that name an unknown or disabled connector; previously allowlisted launchers from the Shadow AI activity view that fall into these categories are also blocked and can no longer be allowlisted from that view.! Slack channel monitors no longer post a reply for every run — silent runs are suppressed. The reply-behavior setting that previously controlled this is removed.
Runlayer: Adds backend_desired_count input to override the backend service's initial desired_count without replacing the full services_configurations map; seeds only services never previously created, with Application Auto Scaling owning the live count afterwards.
└──▷ USE IT
Set per-role Aurora CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. alarms and an ACU ceiling alarm so a saturated writer or a single hot reader pages before the cluster is fully pinned.
hcl
copy
rds_writer_cpu_utilization_threshold = 75
rds_reader_cpu_utilization_threshold = 85
rds_writer_acu_utilization_threshold = 90
Inject a private CA bundle so backend and worker HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. clients trust an internal PKI PKI A framework of policies, roles, and cryptographic standards for issuing and managing digital certificates that bind public keys to identities, letting tools verify authenticity and encrypt communications without pre-shared secrets. without rebuilding the container image.
hcl
copy
trusted_ca_pem = file("${path.module}/certs/internal-ca-bundle.pem")
Temporarily pause ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. task-replacement loops on a ToolGuard service where worker-recycle drain flips /health to 503 and every task owns a whole GPU GPU A graphics processing unit, a processor that performs many calculations in parallel. AI workloads use GPUs to speed up model training and inference. .
hcl
copy
runlayer_tool_guard_health_check_grace_period_seconds = 2147483647
└──▷ BREAKING ON UPGRADE
! AWS provider must be >= 6.64.0, < 7.0.0; upgrade any older AWS provider selection in your dependency lock file before running terraform plan after upgrading this module.
Runlayer adds write-only OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. telemetry ingestion for AI clients including Claude Code and Glean.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Enable OTLP telemetry collection from an AI client (e.g. Claude Code) by provisioning an MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. -managed API key — the only way to obtain the write-only OTLP scope.
📍 In the Runlayer console, go to Settings → MDM configuration and apply a configuration targeting your AI client fleet. Runlayer will automatically mint API keys with the OTLP Telemetry scope for each enrolled device.
Adds automatic API key minting via Settings → MDM configuration for AI Watch scan, hook, and OTLP submissions — keys with this scope cannot be created manually.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 detail in Everything
1.28.811 (2026-09-25)
Sep 25, 2026
·
issue 086
Runlayer 1.28.811 adds per-entry MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. policy management with search/pagination and a minimal environment for local MCP servers.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds minimal environment isolation for local MCP servers: runlayer run now starts local MCP servers with only the connector's configured variables plus proxy, TLS, and locale settings, instead of inheriting the full AI client environment.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds per-entry management to Enforce/Protect policy lists for allowed and denied MCP URLs, local packages, and built-in servers, with search and pagination instead of a single bulk save — and lets Shadow AI overview add a discovered MCP straight to the allowlist. Not checked yet Splits an agent's Slack settings into four sections (Replies, Channel access, Monitoring, and Sending) navigable from the left panel, with Channel monitoring showing channels and condition only while active. Not checked yet
Adds minimal environment isolation for local MCP servers: runlayer run now starts local MCP servers with only the connector's configured variables plus proxy, TLS, and locale settings, instead of inheriting the full AI client environment.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
2 more in Everything
Runlayer: Adds Figma's remote MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server to the catalog (now generally available), with OAuth app registration and per-user Figma account connection.
└──▷ TRY IT
Verify which org API key or enrollment key AI Watch is using on a managed device without exposing the full secret.
copy
$ aiwatch config show
Adds create_artifact tool behavior alignment: artifacts an agent creates with the Runlayer MCP create_artifact tool now follow that agent's Artifact sharing setting. Not checked yet Adds agents-on-Amazon-Bedrock support for OpenAI models (gpt-6 Astra and global./us./eu.-prefixed OpenAI model IDs); a bare openai.gpt-6… ID is automatically served under its global. inference profile. Not checked yet Adds Top spenders drilldown linking to a searchable, paginated view of every user's model spend or token usage. Not checked yet Adds AI Watch client config backups for all supported clients (Cursor, VS Code, Codex, Gemini CLI, and others), retaining only the 5 most recent backups per file. Not checked yet
4 more in Everything
└──▷ BREAKING ON UPGRADE
! AI Watch Enforce now blocks MCP launchers whose --host does not point at your Runlayer deployment, names an unknown or disabled connector, or carries unsupported options — and these launchers can no longer be allowlisted from the Shadow AI activity view.! Saved Shadow AI skill and plugin files are now restricted to resource managers and security or analytics reviewers; organization-wide Shadow AI REST APIs REST APIs A convention for building HTTP-based interfaces where resources are addressed by URL and manipulated with standard verbs like GET, POST, and DELETE, giving cyber tools a predictable way to integrate with external services. and MCP tools now require organization-wide audit log access.
Runlayer Terraform ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. module adds per-role Aurora CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. /ACU alarms, trusted-CA injection, and a ToolGuard health-check grace period input︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Set per-role Aurora CPU thresholds so writer and reader alarms fire independently — useful when a pinned writer saturates while an idle replica would mask a cluster-average alarm.
hcl
copy
rds_writer_cpu_utilization_threshold = 75
rds_reader_cpu_utilization_threshold = 85
rds_writer_acu_utilization_threshold = 90
Inject a private CA bundle so backend and worker HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. clients trust an internal PKI PKI A framework of policies, roles, and cryptographic standards for issuing and managing digital certificates that bind public keys to identities, letting tools verify authenticity and encrypt communications without pre-shared secrets. without rebuilding the container image.
hcl
copy
trusted_ca_pem = file("${path.module}/certs/internal-ca-bundle.pem")
Pin the ToolGuard ECS health-check grace period to int32 max as a stopgap when ECS loops on task replacement due to /health returning 503 during worker-recycle drain.
hcl
copy
runlayer_tool_guard_health_check_grace_period_seconds = 2147483647
Adds rds_writer_cpu_utilization_threshold input to fire a writer-cpu CloudWatch alarm when Aurora WRITER CPUUtilization exceeds the threshold for 3 consecutive 5-minute periods, evaluated on the Role = WRITER dimension rather than the cluster average.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds rds_reader_cpu_utilization_threshold input to fire a per-instance reader-cpu alarm gated on AuroraReplicaLag, so it tracks role swaps on failover and avoids masking a saturated reader behind an idle one. Not checked yet Adds rds_writer_acu_utilization_threshold input to fire a writer-acu alarm when Aurora Serverless v2 ACUUtilization hits or exceeds the threshold for 6 consecutive 5-minute periods; alarm is only created when database_config.min_capacity < max_capacity. Not checked yet Adds trusted_ca_pem input accepting a PEM bundle of additional trusted CA certificates, merged with the image public roots for backend, shared worker, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. execution worker HTTPS clients; private keys are rejected. Not checked yet Adds runlayer_tool_guard_health_check_grace_period_seconds input (0–2147483647) to override the ECS health-check grace period for the ToolGuard service, defaulting to 900 s to cover GRID driver install and model load. Not checked yet
+3 more
show less
Adds a dedicated security group input for ECR ECR Amazon Elastic Container Registry, AWS's managed service for storing and distributing Docker and OCI container images, giving cyber tools a private, IAM-gated registry without self-hosting infrastructure. API, ECR DKR, CloudWatch Logs, and Secrets Manager interface endpoint ENIs used by tunnel tasks when connecting through an existing VPC VPC A logically isolated virtual network inside a public cloud provider's infrastructure, letting tools deploy resources with private addressing, controlled routing, and firewall rules without managing physical hardware. . Not checked yet Adds GPU GPU A graphics processing unit, a processor that performs many calculations in parallel. AI workloads use GPUs to speed up model training and inference. fleet autoscaling with a second target-tracking policy on fleet-average GPU utilization (target 60 %, 60 s metric cadence) alongside a 900 s scale-in cooldown; predictive scaling is automatically disabled in unsupported regions with a plan warning. Not checked yet Requires AWS provider >= 6.64.0, < 7.0.0 for alarm warm-up used by ToolGuard registration monitoring; the dependency lock file must be updated before planning. Not checked yet
Adds rds_writer_cpu_utilization_threshold input to fire a writer-cpu CloudWatch alarm when Aurora WRITER CPUUtilization exceeds the threshold for 3 consecutive 5-minute periods, evaluated on the Role = WRITER dimension rather than the cluster average.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds rds_reader_cpu_utilization_threshold input to fire a per-instance reader-cpu alarm gated on AuroraReplicaLag, so it tracks role swaps on failover and avoids masking a saturated reader behind an idle one. Not checked yet Adds rds_writer_acu_utilization_threshold input to fire a writer-acu alarm when Aurora Serverless v2 ACUUtilization hits or exceeds the threshold for 6 consecutive 5-minute periods; alarm is only created when database_config.min_capacity < max_capacity. Not checked yet Adds trusted_ca_pem input accepting a PEM bundle of additional trusted CA certificates, merged with the image public roots for backend, shared worker, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. execution worker HTTPS clients; private keys are rejected. Not checked yet Adds runlayer_tool_guard_health_check_grace_period_seconds input (0–2147483647) to override the ECS health-check grace period for the ToolGuard service, defaulting to 900 s to cover GRID driver install and model load. Not checked yet
+2 more
show less
Adds a dedicated security group input for ECR ECR Amazon Elastic Container Registry, AWS's managed service for storing and distributing Docker and OCI container images, giving cyber tools a private, IAM-gated registry without self-hosting infrastructure. API, ECR DKR, CloudWatch Logs, and Secrets Manager interface endpoint ENIs used by tunnel tasks when connecting through an existing VPC VPC A logically isolated virtual network inside a public cloud provider's infrastructure, letting tools deploy resources with private addressing, controlled routing, and firewall rules without managing physical hardware. . Not checked yet Adds GPU GPU A graphics processing unit, a processor that performs many calculations in parallel. AI workloads use GPUs to speed up model training and inference. fleet autoscaling with a second target-tracking policy on fleet-average GPU utilization (target 60 %, 60 s metric cadence) alongside a 900 s scale-in cooldown; predictive scaling is automatically disabled in unsupported regions with a plan warning. Not checked yet
1 more in Everything
└──▷ BREAKING ON UPGRADE
! The module now requires AWS provider >= 6.64.0, < 7.0.0; any older AWS provider version pinned in your dependency lock file must be upgraded before running terraform plan.
Runlayer: Adds GPU GPU A graphics processing unit, a processor that performs many calculations in parallel. AI workloads use GPUs to speed up model training and inference. utilization autoscaling via a second target-tracking policy on the RunlayerToolGuard/GPUUtilization CloudWatch metric (target 60%, Environment dimension, Average statistic), complementing the existing CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. policy so the fleet scales on whichever signal is higher.
└──▷ USE IT
Trust a corporate private CA for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server TLS connections in an ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. self-hosted deployment.
hcl
copy
trusted_ca_pem = file("${path.module}/company-ca.pem")
Roll out the authenticated egress proxy in stages to enforce per-agent network access policies on sandbox internet traffic.
hcl
copy
sandbox_egress_mode = "proxy_only"
sandbox_egress_proxy_egress_ports = [443, 8443]
sandbox_egress_proxy_image_uri = ".../runlayer/sandbox-egress-proxy:1.28.500"
Enable Microsoft Teams integration by supplying all five required environment values to the ECS module.
hcl
copy
ms_teams_app_client_secret = var.ms_teams_app_client_secret
# remaining values passed via TF_VAR_* or tfvars:
# MS_TEAMS_APP_CLIENT_ID = "00000000-0000-0000-0000-000000000000"
# MS_TEAMS_RUNLAYER_TENANT_ID = "00000000-0000-0000-0000-000000000000"
# MS_TEAMS_AZURE_SUBSCRIPTION_ID = "00000000-0000-0000-0000-000000000000"
# MS_TEAMS_AZURE_RESOURCE_GROUP = "runlayer-ms-teams-bots"
# MS_TEAMS_APP_URL = "https://<domain_name>"
Adds sandbox_egress_mode Terraform variable (values proxy and proxy_only) and sandbox_egress_proxy_egress_ports / sandbox_egress_proxy_image_uri variables to route ECS sandbox internet traffic through an authenticated egress proxy enforcing per-agent network access policies. Not checked yet Adds container_insights = "enabled" pairing requirement for GPU predictive scaling; terraform plan warns when Container Insights is not enabled alongside the GPU policy. Not checked yet Accelerates ToolGuard GPU metric publishing from every 5 minutes to every 60 seconds, enabling finer-grained GPU autoscaling decisions. Not checked yet
Adds sandbox_egress_mode Terraform variable (values proxy and proxy_only) and sandbox_egress_proxy_egress_ports / sandbox_egress_proxy_image_uri variables to route ECS sandbox internet traffic through an authenticated egress proxy enforcing per-agent network access policies. Not checked yet
2 more in Everything
└──▷ BREAKING ON UPGRADE
! Upgrading changes the ToolGuard launch template on every GPU profile and triggers an ASG rolling instance refresh, replacing hosts and restarting tasks (each restart reloads the model); expect a capacity dip per replacement batch.! MS_TEAMS_APP_URL (the domain name) is effectively immutable after agents are provisioned — changing it orphans existing Azure Bot resources until each is deleted and recreated.
Runlayer agents gain granular Slack messaging controls: separate toggles for DMs, channel posts, and inbound direct messages.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Lock down an agent so it only responds to channel mentions and thread follow-ups, preventing users from bypassing audit trails via direct messages.
📍 In the agent's Slack settings, go to Inbound messaging controls and turn off Direct messages to the agent and Replies . Under Sending, confirm Direct messages to people and Channel posts are set to off.
Adds Direct messages to people and Channel posts switches (both default off) under Sending in the agent's Slack settings to control whether the agent can initiate DMs or post to channels.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 detail in Everything
Runlayer: Adds a browser extension to monitor and protect AI web chats in Chrome, Edge, and Firefox.
Adds JumpCloud deployment support for AI Watch on macOS (.pkg) and Windows (.msi) via JumpCloud Private Repo, shipping Detect, endpoint modes, and Sessions in one package per OS. Not checked yet
1 detail in Everything
Runlayer 1.28.811 adds per-entry Enforce/Protect policy management, improved agent Slack UI, and clearer network deny messages.
runlayer run now starts local MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers with a minimal environment (connector variables + proxy/TLS/locale) instead of passing through the AI client's entire environment Not checked yet Manage Enforce/Protect policy lists (allowed/denied MCP URLs, local packages, built-in servers) one entry at a time with search and pagination via the UI or API Not checked yet Agent Slack settings page splits into four sections: Replies, Channel access, Monitoring, and Sending Not checked yet Network deny messages for blocked hook verification requests now explicitly identify the blocking component (firewall, VPN VPN A virtual private network, an encrypted tunnel between devices or networks. It carries traffic across another network as though the endpoints had a private connection. , etc.) and point to the relevant client Not checked yet
4 details in Everything
1.28.780 (2026-09-24)
Sep 24, 2026
·
issue 085
Runlayer 1.28.780 adds Google AI Studio, JumpCloud MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. deployment, on-demand agent tools, and inline approval decisions in agent chats.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Confirm which org API key or enrollment key AI Watch is using on a managed device before troubleshooting enrollment issues.
copy
$ aiwatch config show
Skip Slack setup when programmatically creating an agent via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. so it is immediately usable without requiring Slack connector access.
copy
$ enable_channels=[]
Add the Google AI Studio provider so agents can be backed by Gemini models.
📍 In Runlayer, go to Settings → AI Providers, select Google AI Studio , paste your Gemini API key, and enter the model IDs you want available to agents.
Adds aiwatch config show command, displaying managed org API keys as a prefix (e.g.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ rl_org_Ab1C2d3...) and enrollment keys as prefix plus last four characters, to confirm which key a device is using. Not checked yet Deploys AI Watch to macOS and Windows through JumpCloud from the MDM configuration wizard, with pre-filled configuration profiles and Private Repo Command Line Options for the signed MSI. Not checked yet AI Watch Enforce now treats a local runlayer run MCP launcher as Runlayer-managed only when its --host points at your Runlayer deployment and names an active connector; launchers without --host, aimed at another host, or naming an unknown/disabled connector are blocked. Not checked yet Adds a dedicated Google AI Studio provider so agents can run on Google Gemini models — configure via Settings → AI Providers with your Gemini API key and model IDs. Not checked yet Enables inline approve/deny of agent tool-call approval requests directly in Agent Playground, Runlayer Assistant, and Home Build, with the agent continuing in the same conversation after the decision. Not checked yet
+12 more
show less
Pi agents discover connector tools on demand, keeping unused tool definitions out of the model's context. Not checked yet Supports interactive HTML Artifact previews inside Slack using existing Runlayer permissions (requires embeds enabled for the workspace's Runlayer app). Not checked yet Surfaces artifacts (interactive apps, images, videos, documents) inline in agent chat directly under the agent's answer, openable full-page from the caption. Not checked yet Adds a Slack badge on an agent's Sessions tab that links directly to the Slack message or thread that started a given run. Not checked yet Allows deleting a skill even when agents use it, with a confirmation dialog listing the affected agents. Not checked yet Slack channel monitors now reply only when the agent has something useful to add, with silent runs still appearing in activity. Not checked yet Run details for Slack channel monitor-triggered runs now show the channel, the message reacted to, and why it matched the monitor's condition. Not checked yet Adds recommended per-tool security scanner settings for 39 more connectors, reviewable and applicable via a dialog on the connector page after adding from the catalog. Not checked yet Every agent account now has an accountable owner shown in the account summary, with the creator set as owner by default. Not checked yet Supports enable_channels=[] parameter when creating an agent through MCP to skip Slack setup. Not checked yet Adds persistent, named Runlayer Assistant sessions resumable from History as you navigate Runlayer. Not checked yet Agent run panel on the Sessions tab now leads with live status, elapsed time, cost, and failure reason alongside the Retry action. Not checked yet
Adds aiwatch config show command, displaying managed org API keys as a prefix (e.g.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ rl_org_Ab1C2d3...) and enrollment keys as prefix plus last four characters, to confirm which key a device is using. Not checked yet Deploys AI Watch to macOS and Windows through JumpCloud from the MDM configuration wizard, with pre-filled configuration profiles and Private Repo Command Line Options for the signed MSI. Not checked yet Adds a dedicated Google AI Studio provider so agents can run on Google Gemini models — configure via Settings → AI Providers with your Gemini API key and model IDs. Not checked yet Enables inline approve/deny of agent tool-call approval requests directly in Agent Playground, Runlayer Assistant, and Home Build, with the agent continuing in the same conversation after the decision. Not checked yet Supports interactive HTML Artifact previews inside Slack using existing Runlayer permissions (requires embeds enabled for the workspace's Runlayer app). Not checked yet
+5 more
show less
Adds a Slack badge on an agent's Sessions tab that links directly to the Slack message or thread that started a given run. Not checked yet Run details for Slack channel monitor-triggered runs now show the channel, the message reacted to, and why it matched the monitor's condition. Not checked yet Every agent account now has an accountable owner shown in the account summary, with the creator set as owner by default. Not checked yet Supports enable_channels=[] parameter when creating an agent through MCP to skip Slack setup. Not checked yet Adds persistent, named Runlayer Assistant sessions resumable from History as you navigate Runlayer. Not checked yet
7 more in Everything
└──▷ BREAKING ON UPGRADE
! The reply-behavior setting for Slack channel monitors is removed; monitors now only reply when the agent has something useful to add, with no option to restore the previous post-every-run behavior.! AI Watch Enforce no longer allows runlayer run MCP launchers without --host, aimed at another host, naming an unknown or disabled connector, or carrying unsupported options — and they can no longer be allowlisted from the Shadow AI activity view.
Runlayer adds Claude Opus 5.5, GPT-6 models, DPoP DPoP An IETF standard that binds an OAuth access token to a specific client's cryptographic key pair, so a stolen token cannot be replayed by an attacker who lacks the matching private key. -bound agent tokens, calendar budget windows, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. trigger management, and a Gmail label trigger across this release cycle.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Route a Gemini model through an OpenAI-Compatible provider when you want to use Google Gemini from an agent that already targets an OpenAI-style endpoint.
📍 In the Runlayer console, go to Providers › Add Provider › OpenAI-Compatible, set the base URL to https://generativelanguage.googleapis.com, and paste your Google API key. Runlayer will send it as a Google API key rather than a Bearer token. Then select the provider when creating or editing your agent.
Enforce DPoP binding on a high-privilege agent so its tokens cannot be replayed if intercepted.
📍 In the Runlayer console, open the agent › Settings › Security, enable Require DPoP , then re-issue the agent-account token with a DPoP key bound at issuance. The MCP proxy will reject any token presented without a valid DPoP proof.
Adds DPoP-bound agent tokens: agent-account tokens can be bound to DPoP keys at issuance and enforced at the MCP proxy, with a per-agent require DPoP flag and admin UI. Not checked yet Adds calendar-based budget windows to LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway usage rules, enabling monthly or other calendar-period caps. Not checked yet Adds max_completion_tokens in place of the legacy max_tokens parameter for Azure Foundry agents on gpt-5-family deployments. Not checked yet Adds a Gmail label-added poll trigger that fires an agent when a label is added to a Gmail message. Not checked yet Adds Trigger management over MCP: create, list, and delete agent triggers through Runlayer MCP tools. Not checked yet
+21 more
show less
Adds Salesforce connector to the catalog, carrying the Salesforce server's own tool schemas so agents and triggers call its tools with the correct arguments; setup guide documents the required OAuth scope and INVALID_SCOPES recovery. Not checked yet Adds Vercel integration available through the OAuth broker. Not checked yet Adds zip skill import: create a multi-file skill by importing a single zip file. Not checked yet Adds View as permission group capability for Super Admins to view the workspace as any permission group. Not checked yet Adds per-tool enrollment diff in the recommended security-setting enrollment flow, showing the effective per-tool diff with scan-direction safety checks before applying. Not checked yet Adds Run schedules on demand : run a schedule immediately and retry failed scheduled runs from the schedule list. Not checked yet Adds Slack thread following: after being mentioned, an agent can continue following the conversation in that thread without requiring another mention. Not checked yet Adds inline video artifact playback in the run view, with the artifact size limit raised to 25 MB. Not checked yet Adds sessions timeline with skipped Slack messages: the agent Sessions list now shows messages the agent chose to skip alongside runs, and search covers both. Not checked yet Adds login-host badge on managed devices when a user's login host differs from the MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. -managed host. Not checked yet Adds OAuth token redaction in audit log details. Not checked yet Adds Agent Discovered as a named audit event type for agents found by AI Watch device scans, including back-filling previously recorded Unknown Event rows. Not checked yet Adds google-docs edit_table tool support for setting multiple table cells in one call via set_cells. Not checked yet AI Watch scan exit status now exits 0 with a Submitted; server marked surfaces incomplete warning (naming each surface and reason) for scans the server accepted but could not fully attribute, instead of exiting 3 as Could not submit . Not checked yet Adds Slack progress cards for long agent runs: agents spending more than a few minutes on one step continue progress on a fresh card without showing a warning icon. Not checked yet Adds Playground Stop button that cancels the active run. Not checked yet Adds Runs continue after approval for MCP- and REST-triggered agent runs, and allows continuing your own run from any surface. Not checked yet Skill scanning now catches combined short-flag recursive deletes such as rm -rf. Not checked yet Adds richer audit events: managed Slack provisioning is audited, and agent-run tool-call audit events carry the agent and run IDs. Not checked yet Model picker hover cards now show pricing and context data from the LiteLLM catalog. Not checked yet The agent channel intro message is now off by default, configurable per agent. Not checked yet
Adds DPoP-bound agent tokens: agent-account tokens can be bound to DPoP keys at issuance and enforced at the MCP proxy, with a per-agent require DPoP flag and admin UI. Not checked yet Adds calendar-based budget windows to LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway usage rules, enabling monthly or other calendar-period caps. Not checked yet Adds a Gmail label-added poll trigger that fires an agent when a label is added to a Gmail message. Not checked yet Adds Trigger management over MCP: create, list, and delete agent triggers through Runlayer MCP tools. Not checked yet Adds Salesforce connector to the catalog, carrying the Salesforce server's own tool schemas so agents and triggers call its tools with the correct arguments; setup guide documents the required OAuth scope and INVALID_SCOPES recovery. Not checked yet
+9 more
show less
Adds Vercel integration available through the OAuth broker. Not checked yet Adds zip skill import: create a multi-file skill by importing a single zip file. Not checked yet Adds View as permission group capability for Super Admins to view the workspace as any permission group. Not checked yet Adds Run schedules on demand : run a schedule immediately and retry failed scheduled runs from the schedule list. Not checked yet Adds Slack thread following: after being mentioned, an agent can continue following the conversation in that thread without requiring another mention. Not checked yet Adds inline video artifact playback in the run view, with the artifact size limit raised to 25 MB. Not checked yet Adds login-host badge on managed devices when a user's login host differs from the MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. -managed host. Not checked yet Adds OAuth token redaction in audit log details. Not checked yet Adds Playground Stop button that cancels the active run. Not checked yet
12 more in Everything
└──▷ USE IT
Trust a corporate private CA for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers and HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. proxies in your ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. Runlayer deployment by passing your CA bundle to the Terraform module.
main.tf
copy
module "runlayer" {
source = "runlayer/ecs"
version = ">= 6.64.0, < 7.0.0"
trusted_ca_pem = file("${path.module}/company-ca.pem")
# ... other required variables
}
Enable Microsoft Teams bot integration on a self-managed ECS deployment by supplying all five required Teams variables to the Terraform module.
main.tf
copy
module "runlayer" {
source = "runlayer/ecs"
version = ">= 6.64.0, < 7.0.0"
ms_teams_app_client_secret = var.ms_teams_app_client_secret # via TF_VAR_ms_teams_app_client_secret
# remaining four values supplied as environment variables:
# MS_TEAMS_APP_CLIENT_ID = "00000000-0000-0000-0000-000000000000"
# MS_TEAMS_RUNLAYER_TENANT_ID = "00000000-0000-0000-0000-000000000000"
# MS_TEAMS_AZURE_SUBSCRIPTION_ID = "00000000-0000-0000-0000-000000000000"
# MS_TEAMS_AZURE_RESOURCE_GROUP = "runlayer-ms-teams-bots"
# MS_TEAMS_APP_URL = "https://<domain_name>"
# ... other required variables
}
└──▷ BREAKING ON UPGRADE
! The MS_TEAMS_APP_URL (domain name) is effectively immutable once agents are provisioned: each agent's Azure Bot resource stores the messaging endpoint at creation time and is never rewritten, so changing the domain orphans existing bots until each is deleted and recreated.
Runlayer agents can now reject Slack DMs and restrict interaction to channel mentions only.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Restrict an agent to channel-only interaction so it never processes DMs or assistant-pane conversations.
📍 In the agent's Slack settings, go to Inbound messaging and turn off Direct messages to the agent .
Adds Direct messages to the agent / Inbound messaging toggle in an agent's Slack settings to block inbound DMs — when disabled, the agent replies that it does not accept direct messages and redirects users to mention it in a channel instead.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 detail in Everything
1.28.731 (2026-09-23)
Sep 23, 2026
·
issue 083
Runlayer 1.28.731 adds Claude Opus 5.5, GPT-6 Sol/Luna, channel-only Slack agents, and Shadow AI access controls.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Prevent employees from DMing a sensitive Slack agent directly — force all interactions into auditable channels.
📍 In the agent's settings, go to Slack notifications and disable Allow direct messages . Users who DM the agent will be prompted to mention it in a channel instead.
Route Gemini model calls through an OpenAI-Compatible provider so agents can use Google models without Bearer-token auth failures.
📍 In the provider settings, add an OpenAI-Compatible provider with base URL set to generativelanguage.googleapis.com and supply your Google API key. Runlayer will send it in the format Google expects.
Restricts saved Shadow AI skill and plugin files to resource managers and security or analytics reviewers; organization-wide Shadow AI REST APIs REST APIs A convention for building HTTP-based interfaces where resources are addressed by URL and manipulated with standard verbs like GET, POST, and DELETE, giving cyber tools a predictable way to integrate with external services. and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools now require organization-wide audit log access.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds support for channel-only Slack agents: admins can turn off direct messages to an agent in its Slack settings, redirecting DMs to channel mentions instead. Not checked yet Adds Claude Opus 5.5 as an agent model, available via the Anthropic API or AWS Bedrock, with adaptive thinking effort settings. Not checked yet Adds GPT-6 Sol and GPT-6 Luna as agent model options for the OpenAI provider. Not checked yet Supports Google Gemini through OpenAI-Compatible providers pointed at generativelanguage.googleapis.com, sending API keys in the format Google expects rather than as a Bearer token Bearer token A credential that grants access to whoever presents it, without a separate proof of possession. Protecting the token matters because a stolen copy can be used by someone else. . Not checked yet
Restricts saved Shadow AI skill and plugin files to resource managers and security or analytics reviewers; organization-wide Shadow AI REST APIs REST APIs A convention for building HTTP-based interfaces where resources are addressed by URL and manipulated with standard verbs like GET, POST, and DELETE, giving cyber tools a predictable way to integrate with external services. and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools now require organization-wide audit log access.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds support for channel-only Slack agents: admins can turn off direct messages to an agent in its Slack settings, redirecting DMs to channel mentions instead. Not checked yet Supports Google Gemini through OpenAI-Compatible providers pointed at generativelanguage.googleapis.com, sending API keys in the format Google expects rather than as a Bearer token Bearer token A credential that grants access to whoever presents it, without a separate proof of possession. Protecting the token matters because a stolen copy can be used by someone else. . Not checked yet
2 more in Everything
Runlayer Terraform module gains private CA trust bundles and Microsoft Teams integration for ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. self-hosted deployments.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Trust an internal private CA so ECS workers can reach MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers or HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. proxies signed by that CA.
hcl
copy
trusted_ca_pem = file("${path.module}/company-ca.pem")
Enable Microsoft Teams integration by supplying all five required values; pass the client secret via environment variable to avoid storing it in state.
terraform.tfvars
copy
# terraform.tfvars
MS_TEAMS_APP_CLIENT_ID = "00000000-0000-0000-0000-000000000000"
MS_TEAMS_RUNLAYER_TENANT_ID = "00000000-0000-0000-0000-000000000000"
MS_TEAMS_AZURE_SUBSCRIPTION_ID = "00000000-0000-0000-0000-000000000000"
MS_TEAMS_AZURE_RESOURCE_GROUP = "runlayer-ms-teams-bots"
MS_TEAMS_APP_URL = "https://runlayer.example.com"
# export TF_VAR_ms_teams_app_client_secret=<secret> before running terraform apply
Adds trusted_ca_pem Terraform module variable to inject a PEM certificate bundle (single or concatenated) into ECS deployments, enabling backend, shared worker, and MCP execution worker tasks to trust private CA-signed MCP servers and HTTPS proxies.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Microsoft Teams integration via five module variables — ms_teams_app_client_secret (Terraform variable, recommended via TF_VAR_*) plus MS_TEAMS_APP_CLIENT_ID, MS_TEAMS_RUNLAYER_TENANT_ID, MS_TEAMS_AZURE_SUBSCRIPTION_ID, MS_TEAMS_AZURE_RESOURCE_GROUP, and MS_TEAMS_APP_URL — which together provision a per-agent Entra app registration and Azure Bot Service resource; the integration is off unless all five values are set. Not checked yet Adds rds_writer_cpu_utilization_threshold, rds_reader_cpu_utilization_threshold, and rds_writer_acu_utilization_threshold Terraform variables to control RDS autoscaling targets for ECS deployments. Not checked yet Requires registering https://<domain_name>/api/v1/integrations/ms-teams/admin-consent-callback as a Redirect URI (Authentication → Web) on the multi-tenant Entra app registration for Teams admin consent to succeed. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! The MS_TEAMS_APP_URL (domain name) is effectively immutable after agents are provisioned — changing it orphans each agent's Azure Bot resource, which must be deleted and recreated to restore Teams connectivity.
Runlayer Operator adds Microsoft Teams integration, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Catalog API, AI Watch binary distribution, and OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. observability support on Kubernetes.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Inject the MCP Catalog API key into the platform namespace so onboarding can reach GET /api/v1/catalog/ and setup status loads correctly.
copy
$ kubectl create secret generic runlayer-catalog \
--namespace runlayer-platform \
--from-literal=MCP_CATALOG_API_KEY=<key-from-runlayer>
Apply updated CRDs CRDs A Kubernetes extension that adds a new object type to the cluster, so a tool's configuration is stored, validated and versioned by Kubernetes itself rather than in a file beside it. before upgrading the operator to avoid schema drift between the controller and the cluster.
copy
$ kubectl apply -f crds/platform.runlayer.com_runlayerinstances.yaml \
-f crds/deploy.runlayer.com_mcpservers.yaml
Adds MCP_CATALOG_API_KEY secret (set on the platform namespace) to enable MCP Catalog onboarding; without it, GET /api/v1/catalog/ fails and setup shows Couldn't load setup status . Not checked yet Adds AI Watch binary distribution support, requiring a Runlayer download token and a customer-owned object-storage cache with workload identity workload identity An identity assigned to software, such as a service or container, rather than a person. It lets the workload authenticate and receive permissions without sharing a user's credentials. permissions; missing inputs surface as 'No AI Watch installer is currently resolved' in the UI. Not checked yet Adds OTLP observability support for Kubernetes deployments (requires Kubernetes ≥ 1.29 and reachable OTLP endpoints; hostname endpoints may need extra NetworkPolicy NetworkPolicy A Kubernetes API object that defines which pods may send or receive traffic, enforced by the cluster's CNI plugin to give cyber tools namespace-level network segmentation without host firewall rules. CIDRs). Not checked yet Publishes operator and runlayer-instance Helm chart via Customer Distribution OCI OCI Open Container Initiative standard, maintained by the Linux Foundation, defining the image format and runtime spec that container tools share so images built once run anywhere OCI-compliant. registry at oci://088332244652.dkr.ecr.us-east-1.amazonaws.com/runlayer-helm-charts/runlayer-instance, supporting cross-account ECR ECR Amazon Elastic Container Registry, AWS's managed service for storing and distributing Docker and OCI container images, giving cyber tools a private, IAM-gated registry without self-hosting infrastructure. pulls for EKS EKS Amazon's managed Kubernetes service, run by AWS, that handles control-plane provisioning so teams can deploy containerized workloads without operating the underlying cluster infrastructure themselves. and GAR/private mirror for GKE GKE Google Kubernetes Engine, Google's managed Kubernetes service, which lets cyber tools run containerized workloads without managing the underlying cluster infrastructure. or air-gapped environments. Not checked yet Adds CRD CRD A Kubernetes extension that adds a new object type to the cluster, so a tool's configuration is stored, validated and versioned by Kubernetes itself rather than in a file beside it. manifests crds/platform.runlayer.com_runlayerinstances.yaml and crds/deploy.runlayer.com_mcpservers.yaml shipped with the Helm chart for upgrade workflows. Not checked yet
+3 more
show less
Adds configurable HPA behavior block with documented defaults: 1800s scale-down stabilization for fleet components, 300s for others, max 10% removal per minute, and 60s scale-up with up to 50% or 2 pods per minute; setting behavior replaces the entire default block. Not checked yet Publishes supporting guides covering Kubernetes prerequisites (EKS + GKE cluster requirements), external dependencies (Postgres, Redis, buckets, streams with sample Terraform), Runlayer-provided inputs, and a ServiceAccount → IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. / Workload Identity permission matrix. Not checked yet Adds components.mcpCatalogApi Helm/CR field to optionally enable in-cluster MCP Catalog API; the documentation notes this should not be enabled for the standard customer path. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! Changing MS_TEAMS_APP_URL after initial provisioning does not move already-provisioned bots: each agent's Azure Bot resource keeps the messaging endpoint captured at provisioning time and must be recreated.
Runlayer adds workload identity workload identity An identity assigned to software, such as a service or container, rather than a person. It lets the workload authenticate and receive permissions without sharing a user's credentials. support for EKS EKS Amazon's managed Kubernetes service, run by AWS, that handles control-plane provisioning so teams can deploy containerized workloads without operating the underlying cluster infrastructure themselves. (IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. ) and GKE GKE Google Kubernetes Engine, Google's managed Kubernetes service, which lets cyber tools run containerized workloads without managing the underlying cluster infrastructure. , eliminating long-lived cloud keys from deployments︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Wire IRSA roles to each Runlayer component on EKS so workloads assume cloud permissions without embedded credentials.
yaml
copy
spec:
serviceAccount:
backend:
annotations:
eks.amazonaws.com/role-arn: arn:aws:iam::123456789012:role/runlayer-acme-backend
worker:
annotations:
eks.amazonaws.com/role-arn: arn:aws:iam::123456789012:role/runlayer-acme-worker
auditConsumer:
annotations:
eks.amazonaws.com/role-arn: arn:aws:iam::123456789012:role/runlayer-acme-audit-consumer
siemExport:
annotations:
eks.amazonaws.com/role-arn: arn:aws:iam::123456789012:role/runlayer-acme-siem-export
sessionMaterializer:
annotations:
eks.amazonaws.com/role-arn: arn:aws:iam::123456789012:role/runlayer-acme-session-materializer
Verify that the IRSA annotation is present on the ServiceAccount and that the pod actually assumes the expected role.
copy
$ kubectl -n runlayer-acme get sa acme-prod-backend -o yaml
# expect eks.amazonaws.com/role-arn in annotations
kubectl -n runlayer-acme exec deploy/acme-prod-backend -c backend -- aws sts get-caller-identity
# Arn should be the IRSA role
Deploy Runlayer into a custom namespace instead of the default runlayer-<customerId> when your cluster naming conventions require it.
yaml
copy
spec:
deploy:
platformNamespace: runlayer-acme-prod
Adds spec.serviceAccount field in the RunlayerInstance CR to annotate per-component Kubernetes ServiceAccounts with IRSA role ARNs (eks.amazonaws.com/role-arn) on EKS or GSA emails (iam.gke.io/gcp-service-account) on GKE — no long-lived cloud keys embedded.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds spec.deploy.platformNamespace to the RunlayerInstance CR to override the default runlayer-<customerId> namespace where workload-identity ServiceAccounts are created. Not checked yet Provisions dedicated Kubernetes ServiceAccounts per component — {instance}-backend, {instance}-worker, {instance}-audit-consumer, {instance}-siem-export, {instance}-session-materializer, {instance}-toolguard — each independently annotatable with cloud IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. roles. Not checked yet Publishes a per-component permission matrix covering S3/GCS, Kinesis/Pub/Sub, DynamoDB checkpoints, Bedrock/Vertex LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. invocation, and bedrock-agentcore:InvokeAgentRuntime so operators can scope IAM grants to only enabled features. Not checked yet
4 details in Everything
Runlayer documents external dependency wiring for PostgreSQL, Redis, audit streams, SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. export, AI Watch packages, and session materializer on AWS and GCP.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Wire audit streaming and SIEM export into a RunlayerInstance CR after provisioning the Kinesis stream, EFO consumers, DynamoDB checkpoint tables, and DLQ/destination buckets out-of-band.
yaml
copy
spec:
components:
auditConsumer:
enabled: true
streamBackend: kinesis
kinesis:
streamArn: arn:aws:kinesis:us-east-1:123456789012:stream/myorg-audit-log
consumerArn: arn:aws:kinesis:us-east-1:123456789012:stream/myorg-audit-log/consumer/myorg-audit-log-consumer
checkpointTableName: myorg-audit-log-consumer-checkpoints
deadLetterBucket: myaccount-myorg-audit-log-consumer-dlq
siemExport:
enabled: true
streamBackend: kinesis
kinesis:
streamArn: arn:aws:kinesis:us-east-1:123456789012:stream/myorg-audit-log
consumerArn: arn:aws:kinesis:us-east-1:123456789012:stream/myorg-audit-log/consumer/myorg-siem-export
checkpointTableName: myorg-siem-export-checkpoints
deadLetterBucket: myaccount-myorg-siem-export-dlq
export:
s3Bucket: myaccount-myorg-siem-export
Enable Redis with TLS in the RunlayerInstance CR after provisioning an ElastiCache replication group with transit_encryption_mode: required.
yaml
copy
spec:
redis:
tls: true
Maps PostgreSQL (Aurora/RDS or Cloud SQL) into RunlayerInstance via spec.database.* and Secrets runlayer-db / runlayer-redis.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Maps Redis (ElastiCache or Memorystore) into RunlayerInstance via spec.redis.*, with spec.redis.tls: true when TLS/auth is enabled. Not checked yet Enables optional AI Watch binary package caching via a private S3 bucket configured with BINARY_PACKAGES_S3_BUCKET on runlayer-app, requiring s3:ListBucket, s3:GetObject, and s3:PutObject on the {instance}-backend and -worker IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. roles. Not checked yet Enables optional audit event streaming to Kinesis or GCP Pub/Sub, wired into components.auditConsumer with streamBackend: kinesis or streamBackend: pubsub, plus spec.gcp.projectId for GCP. Not checked yet Enables optional SIEM export as an independent consumer on the same Kinesis or Pub/Sub stream, wired into components.siemExport with streamBackend: kinesis, kinesis.streamArn, kinesis.consumerArn, kinesis.checkpointTableName, kinesis.deadLetterBucket, and export.s3Bucket. Not checked yet
+1 more
show less
Enables optional session materializer component ({instance}-session-materializer) backed by a Kinesis hook-events stream, DynamoDB checkpoint table, S3 session-payloads bucket, and S3 DLQ on AWS; or an ordered Pub/Sub subscription and GCS buckets on GCP. Not checked yet
6 details in Everything
Runlayer adds self-hosted Kubernetes deployment support on EKS EKS Amazon's managed Kubernetes service, run by AWS, that handles control-plane provisioning so teams can deploy containerized workloads without operating the underlying cluster infrastructure themselves. and GKE GKE Google Kubernetes Engine, Google's managed Kubernetes service, which lets cyber tools run containerized workloads without managing the underlying cluster infrastructure. alongside existing ECS ECS Elastic Common Schema, an open specification maintained by Elastic that defines a standard field naming convention for log and event data, letting cyber tools share and correlate records without per-source field mapping. /AWS path︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds Kubernetes self-hosting support on EKS (AWS) and GKE (GCP), requiring Kubernetes 1.29+ and Helm 3.8+, as an alternative to the ECS deployment path.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Introduces Runlayer Operator for EKS/GKE, enabling one or many isolated tenants via MCPServer on the same cluster. Not checked yet Supports per-workload ServiceAccounts with IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. (EKS) or GKE Workload Identity for cloud API access. Not checked yet Supports AWS Bedrock as an AI provider in the EKS self-hosted deployment path, requiring IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. permissions and Anthropic Bedrock use-case form approval. Not checked yet Adds multi-tenant platform topology where platform teams can run Runlayer for multiple internal orgs on a single EKS/GKE cluster. Not checked yet
5 details in Everything
Runlayer adds Agent Accounts with per-agent policies and audit trails, plus Kubernetes self-hosting docs for EKS EKS Amazon's managed Kubernetes service, run by AWS, that handles control-plane provisioning so teams can deploy containerized workloads without operating the underlying cluster infrastructure themselves. and GKE GKE Google Kubernetes Engine, Google's managed Kubernetes service, which lets cyber tools run containerized workloads without managing the underlying cluster infrastructure. , and Figma MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. integration.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds Agent Accounts — give each agent its own identity in Runlayer with independent policies, delegations, tokens, and audit trail.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Kubernetes self-hosting support: cluster prerequisites for EKS and GKE, external dependency guidance (Postgres, Redis, buckets, streams) with sample Terraform for EKS (AWS) and GKE (GCP). Not checked yet Adds Workload Identity mapping for the Runlayer Operator: map operator ServiceAccounts to IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. (EKS) or Workload Identity (GKE) via a per-feature permission matrix. Not checked yet Adds Figma integration: connect Figma's remote MCP server through Runlayer using a customer-registered OAuth app. Not checked yet
4 details in Everything
Runlayer Operator now supports customer-managed Kubernetes clusters on EKS EKS Amazon's managed Kubernetes service, run by AWS, that handles control-plane provisioning so teams can deploy containerized workloads without operating the underlying cluster infrastructure themselves. and GKE GKE Google Kubernetes Engine, Google's managed Kubernetes service, which lets cyber tools run containerized workloads without managing the underlying cluster infrastructure. .︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
1.28.687 (2026-09-22)
Sep 22, 2026
·
issue 083
Runlayer 1.28.687 adds Figma MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector, client-provenance provenance Evidence recording where a software artifact came from and how it was built, including its source and build process. It helps a consumer check that the artifact matches a trusted build. policy conditions, and queued agent messages.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Lock a connector so self-registered MCP clients can never reach it, regardless of whether they go direct or through a plugin.
📍 In the Runlayer console, go to Policies › New policy condition, set the field to meta.client.kind, operator to equals , and value to dcr (or any of: cimd, pre_registered, manual, ema, agent). Add a second condition on meta.plugin.id if you also want to block plugin-routed paths. Set the policy action to Deny and apply it to the target connector.
Adds meta.client.kind (values: dcr, cimd, pre_registered, manual, ema, agent) and meta.plugin.id as policy condition keys so access policies can gate connectors by how an MCP client obtained its credentials and whether it reaches a connector directly or through a plugin.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Figma remote MCP connector to the catalog — register a Figma OAuth app, have Figma approve its client ID, paste credentials into the connector, and users connect with their own Figma account. Not checked yet Adds a recommended security settings dialog on the connector page so admins with the Manage security policies capability can review and apply per-tool scanner settings after deploying a connector, instead of during the deploy wizard. Not checked yet Adds queued agent messages: send follow-ups while an agent is working and they run in order; messages can be edited, reordered, or removed, and resumed after stopping a response. Not checked yet Adds shareable Policies view URLs so admins can bookmark and share filtered policy views, and connector notices now open Policies pre-filtered to the relevant connector. Not checked yet
Adds meta.client.kind (values: dcr, cimd, pre_registered, manual, ema, agent) and meta.plugin.id as policy condition keys so access policies can gate connectors by how an MCP client obtained its credentials and whether it reaches a connector directly or through a plugin.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Figma remote MCP connector to the catalog — register a Figma OAuth app, have Figma approve its client ID, paste credentials into the connector, and users connect with their own Figma account. Not checked yet Adds queued agent messages: send follow-ups while an agent is working and they run in order; messages can be edited, reordered, or removed, and resumed after stopping a response. Not checked yet Adds shareable Policies view URLs so admins can bookmark and share filtered policy views, and connector notices now open Policies pre-filtered to the relevant connector. Not checked yet
1 more in Everything
Runlayer Operator gains Microsoft Teams provisioning via six new MS_TEAMS_* environment variables︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Enable Microsoft Teams bot provisioning on a self-hosted Runlayer Operator deployment by supplying all required MS_TEAMS_* variables — omitting any of them leaves Teams provisioning off.
.env
copy
MS_TEAMS_APP_CLIENT_ID=<entra-app-client-id>
MS_TEAMS_APP_CLIENT_SECRET=<entra-app-client-secret>
MS_TEAMS_RUNLAYER_TENANT_ID=<entra-tenant-id>
MS_TEAMS_AZURE_SUBSCRIPTION_ID=<azure-subscription-id>
MS_TEAMS_AZURE_RESOURCE_GROUP=<resource-group-name>
MS_TEAMS_APP_URL=https://runlayer.example.com
Adds MS_TEAMS_APP_CLIENT_SECRET environment variable to supply the client secret for the Entra provisioning app backing the Microsoft Teams integration.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds MS_TEAMS_APP_CLIENT_ID environment variable to set the application (client) ID of the multi-tenant Entra app used to provision per-agent Teams bots. Not checked yet Adds MS_TEAMS_RUNLAYER_TENANT_ID environment variable to identify the Entra tenant where per-agent Entra apps and Azure Bot resources are created. Not checked yet Adds MS_TEAMS_AZURE_SUBSCRIPTION_ID environment variable to specify the Azure subscription holding the Bot Service resources. Not checked yet Adds MS_TEAMS_AZURE_RESOURCE_GROUP environment variable to specify the resource group within that subscription. Not checked yet
+1 more
show less
Adds MS_TEAMS_APP_URL environment variable to set the public HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. base for the Bot Framework messaging endpoint and admin-consent callback; defaults to the operator's own host and must match the Redirect URI registered on the Entra app or admin consent fails with AADSTS500113. Not checked yet
6 details in Everything
Runlayer Terraform module gains Microsoft Teams integration with per-agent Entra app and Azure Bot Service provisioning.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds Microsoft Teams integration to the Terraform module, configured via five environment variables — MS_TEAMS_APP_CLIENT_ID, MS_TEAMS_RUNLAYER_TENANT_ID, MS_TEAMS_AZURE_SUBSCRIPTION_ID, MS_TEAMS_AZURE_RESOURCE_GROUP, and MS_TEAMS_APP_URL — with the client secret supplied through ms_teams_app_client_secret (recommended via TF_VAR_ms_teams_app_client_secret); the integration is off unless all five values are set.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Provisioning the Teams integration creates a per-agent Entra app registration and Azure Bot Service resource, requiring a multi-tenant app registration with Graph application permissions Application.ReadWrite.All, AppCatalog.ReadWrite.All, and TeamsAppInstallation.ReadWriteForUser.All (admin-consented), a resource group granting Azure Bot Service Contributor to that app, and the Microsoft.BotService provider registered on the subscription. Not checked yet Requires registering https://<domain_name>/api/v1/integrations/ms-teams/admin-consent-callback as a Redirect URI under Authentication → Web on the app registration, or admin consent fails with AADSTS500113. Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! The domain name configured at agent provisioning time is effectively immutable: each agent's Azure Bot resource stores the messaging endpoint captured at creation time and is never rewritten, so changing the domain orphans existing bots until each is deleted and recreated.
Runlayer adds Agent Accounts, giving each agent its own identity with policies, delegations, tokens, and audit trail.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
1.28.574 - Richer session timelines and inline video artifacts (2026-09-18)
Sep 18, 2026
·
issue 079
Runlayer 1.28.574 adds skipped-message timelines, inline video artifacts (25 MB), login-host badges, and OAuth token redaction in audit logs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Agents Sessions list now shows Slack messages the agent chose to skip alongside runs, with search covering both skipped messages and runs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Video artifacts play inline in the run view, and the artifact size limit is raised to 25 MB. Not checked yet Clicking a trace header with a single tool call opens its details directly. Not checked yet Managed devices show a badge when a user's login host differs from the MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. -managed host, and hooks target the managed host. Not checked yet OAuth token keys are redacted in audit log details. Not checked yet
Agents Sessions list now shows Slack messages the agent chose to skip alongside runs, with search covering both skipped messages and runs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Managed devices show a badge when a user's login host differs from the MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. -managed host, and hooks target the managed host. Not checked yet OAuth token keys are redacted in audit log details. Not checked yet
2 more in Everything
Runlayer adds full Microsoft Teams integration: per-agent bots, workspace notifications, and link preview cards.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Enable ambient channel monitoring so a security-focused agent answers every deployment-failure discussion without needing an @mention.
📍 1. Open the agent detail page.
2. Under Microsoft Teams, toggle on Respond without being tagged in channels .
3. In the condition field that appears, enter: only respond to messages about deployment failures
4. Click Save.
5. Reinstall the Teams app (Microsoft Teams → Install, same dialog) so the team owner can grant the extra permission.
Route security scan violation alerts to a dedicated SOC SOC A security operations center, the team or function that monitors threats, investigates alerts and coordinates incident response. Its work can be internal, outsourced or shared. channel and suppress low-severity mask/alert-only noise.
📍 1. Go to Settings → Integrations → Microsoft Teams.
2. Click Create Teams Bot and complete the tenant connection if not already done.
3. @mention the bot at least once from your #soc-alerts channel so it can post there.
4. Set Security alerts channel to #soc-alerts.
5. Enable Only alert on blocked calls.
6. Click Test next to the Security alerts channel to confirm delivery.
Install an agent bot across an entire team in bulk so every channel member can @mention it immediately.
📍 1. Open the agent detail page → Microsoft Teams → Install.
2. In the Install Teams app dialog, choose Team (all channels).
3. Click Install for all teams.
4. Click Install.
Adds Microsoft Teams integration, enabling each agent to have its own bot that responds to @mentions and direct messages in Teams channels; connect via Settings → Integrations → Connect Microsoft Teams for org-wide tenant authorization.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds per-agent Teams bot install from the agent detail page under Microsoft Teams → Install , with options to target a specific user (direct message), a team (all channels), or bulk install for all users or all teams. Not checked yet Adds Respond without being tagged in channels toggle under each agent's Microsoft Teams settings, letting the bot answer channel messages it is not @mentioned in, with an optional natural-language condition to scope which messages trigger a response. Not checked yet Adds agent-initiated outbound posting to a Teams channel — an agent can post a new message into any channel whose ID is provided, independent of any incoming message that triggered it. Not checked yet Adds a shared Runlayer Teams Bot for workspace-level notifications, configurable from Settings → Integrations → Microsoft Teams with a Notification channel , an optional Security alerts channel for security scan violations, and an Only alert on blocked calls toggle. Not checked yet
+1 more
show less
Adds Runlayer link previews in Teams: pasting an agent, skill, plugin, artifact, or session URL into a Teams chat triggers the agent's bot to resolve it into a rich card showing resource type, title, and creator (access-aware, matching Slack's behavior); enabled by reinstalling the Teams app to pick up the updated manifest. Not checked yet
6 details in Everything
1.28.545 - Slack thread following, on-demand schedules, and trigger management over MCP (2026-09-17)
Sep 17, 2026
·
issue 078
Runlayer 1.28.545 adds Slack thread following, on-demand schedule runs, and trigger management via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Immediately re-run a failed scheduled job without waiting for the next scheduled window.
📍 In the Runlayer console, go to Agents › your agent › Schedules, then click Run now on the target schedule or Retry next to a failed run.
Adds trigger management via Runlayer MCP tools — create, list, and delete agent triggers programmatically.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Enables agents to follow a Slack thread continuously after an initial mention, without requiring re-mention for each reply. Not checked yet Adds on-demand schedule execution — run a schedule immediately or retry failed scheduled runs directly from the schedule list. Not checked yet Delivers Office document attachments shared in a Slack thread to the agent sandbox, and surfaces undeliverable files explicitly instead of silently skipping them. Not checked yet Sets Claude Sonnet 5 as the default model for new agents; the managed assistant now runs on Claude Opus 4.8. Not checked yet
+1 more
show less
Turns the agent channel intro message off by default, with a per-agent opt-in to re-enable it. Not checked yet
Adds trigger management via Runlayer MCP tools — create, list, and delete agent triggers programmatically.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Enables agents to follow a Slack thread continuously after an initial mention, without requiring re-mention for each reply. Not checked yet
4 more in Everything
└──▷ BREAKING ON UPGRADE
! The agent channel intro message is now off by default; existing agents that relied on it broadcasting on channel join will no longer do so unless re-enabled per agent.
Runlayer adds Enterprise Grok Bot monitoring and DPoP DPoP An IETF standard that binds an OAuth access token to a specific client's cryptographic key pair, so a stolen token cannot be replayed by an attacker who lacks the matching private key. sender-constrained tokens for agent accounts.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds Central Grok Bot setup for Enterprise Team deployments, enabling credential provisioning and per-member shadow AI monitoring coverage.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds DPoP (RFC 9449) sender-constrained token binding for agent accounts, tying tokens to a client-held ES256 ES256 An ECDSA digital signature algorithm using a P-256 elliptic curve and SHA-256 hash, defined in RFC 7518. Cyber tools use it to sign and verify JWTs with smaller keys than RSA while keeping strong integrity guarantees. key so a leaked token cannot be replayed. Not checked yet
2 details in Everything
1.28.515 - DPoP-bound agent tokens and calendar LLM budgets (2026-09-17)
Sep 17, 2026
·
issue 077
Runlayer 1.28.515 adds DPoP DPoP An IETF standard that binds an OAuth access token to a specific client's cryptographic key pair, so a stolen token cannot be replayed by an attacker who lacks the matching private key. -bound agent tokens, calendar LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. budget windows, recursive delete detection, and zip skill import.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Enforce DPoP-bound tokens for a specific agent to prevent token replay attacks at the MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. proxy.
📍 In the Runlayer admin UI, go to Agents › select the agent › Settings, and enable the require DPoP flag. Tokens issued to this agent will be bound to a DPoP key and rejected at the MCP proxy if presented without a valid DPoP proof.
Cap monthly LLM spend per agent to enforce governance budgets that reset on a calendar cycle.
📍 In the Runlayer admin UI, go to Agents › select the agent › Usage Rules, add a budget window, and set the period to monthly with your desired token or spend cap.
Package a multi-file skill and import it in one step rather than uploading files individually.
📍 In the Runlayer admin UI, go to Skills › Import Skill, select Zip import , and upload a zip file containing all skill files. Runlayer will create the multi-file skill from the archive.
Adds DPoP binding for agent-account tokens at issuance, enforced at the MCP proxy via a per-agent require DPoP flag and admin UI.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds calendar-based budget windows (e.g. monthly caps) to LLM gateway usage rules. Not checked yet Adds per-tool enrollment diff for recommended security-setting enrollment, showing the effective per-tool diff with scan-direction safety checks before applying. Not checked yet Adds recursive delete detection to ToolGuard skill scanning, catching combined short-flag recursive deletes such as rm -rf. Not checked yet Adds zip skill import, allowing a multi-file skill to be created by importing a single zip file. Not checked yet
+5 more
show less
Adds set_cells capability to the edit_table tool for Google Docs, enabling multiple table cells to be set in one call. Not checked yet Extends audit events to cover Managed Slack provisioning and to carry agent and run IDs on agent-run tool-call events. Not checked yet Adds View as permission group capability for Super Admins to view the workspace as any permission group. Not checked yet Agent runs triggered via MCP or REST now continue after an approval decision, and users can continue their own run from any surface. Not checked yet Rejected access requests now include an explanation of why the request was rejected. Not checked yet
Adds DPoP binding for agent-account tokens at issuance, enforced at the MCP proxy via a per-agent require DPoP flag and admin UI.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds calendar-based budget windows (e.g. monthly caps) to LLM gateway usage rules. Not checked yet Adds zip skill import, allowing a multi-file skill to be created by importing a single zip file. Not checked yet Adds View as permission group capability for Super Admins to view the workspace as any permission group. Not checked yet
6 more in Everything
1.28.478 - Gmail label-added trigger and Vercel connector (2026-09-16)
Sep 16, 2026
·
issue 077
Runlayer 1.28.478 adds a Gmail label-added poll trigger, a Vercel OAuth connector, and agent approval run continuations.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds a Gmail label-added poll trigger that fires an agent whenever a label is added to a Gmail message.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Vercel as a connector available through the OAuth broker. Not checked yet Agents now post to Slack as the agent bot by default unless explicitly configured to act as the connected user. Not checked yet
Adds a Gmail label-added poll trigger that fires an agent whenever a label is added to a Gmail message.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Vercel as a connector available through the OAuth broker. Not checked yet
1 more in Everything
└──▷ BREAKING ON UPGRADE
! Grok cloud hooks now require explicit opt-in and will no longer activate automatically — existing setups relying on automatic Grok cloud hook enrollment will stop working until opted in.! In monitor mode, hooks now fail open (allow) on credential rejection instead of blocking the editor — workflows that previously relied on monitor-mode hooks to block on rejection will no longer be blocked.
Runlayer 1.28.515 adds DPoP DPoP An IETF standard that binds an OAuth access token to a specific client's cryptographic key pair, so a stolen token cannot be replayed by an attacker who lacks the matching private key. -bound agent tokens, calendar LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. budget windows, zip skill import, and richer audit events for agent runs.
Agent-account tokens can be bound to DPoP keys at issuance with a per-agent require DPoP flag. Not checked yet LLM gateway usage rules now support calendar-based budget windows, such as monthly caps. Not checked yet Multi-file skills can be imported via a single zip file. Not checked yet Admin UI lets Super Admins view the workspace as any permission group. Not checked yet
4 details in Everything
Runlayer v1.28.478 adds Gmail label trigger, Vercel integration, monitor-mode hook fail-open, and Playground Stop.
Adds Gmail label-added poll trigger to fire agents when a label is added to a message Not checked yet Adds Vercel connector via the OAuth broker Not checked yet Configures monitor-mode hooks to fail open on credential rejection instead of blocking the editor Not checked yet Requires explicit opt-in for Grok cloud hooks Not checked yet
4 details in Everything
1.28.428 - Webhook signing, scan budgets, and Windows browser auto-deploy (2026-09-14)
Sep 14, 2026
·
issue 076
Runlayer 1.28.428 adds webhook HMAC HMAC A keyed hash that proves a message came from someone holding a shared secret and was not altered. Webhooks and API request signing commonly use it. signing, scan budgets with fail-open/closed control, Terraform-managed agents, and Windows browser auto-deploy.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds runlayer_agent resource and data source to the Terraform provider so agents can be fully managed as infrastructure-as-code.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds HMAC signing for agent webhooks — create, rotate, and disable signing secrets from the webhook dialog, with a scheme picker and curl examples. Not checked yet Adds scan budgets to ToolGuard: configure latency and payload budgets with fail-open/fail-closed behavior, allow/truncate/block payload actions, and budget-exceeded events written to audit logs. Not checked yet Adds new get_table, delete_between_text, and delete_table tools to the Google Workspace connector. Not checked yet Adds usage APIs by IdP IdP A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. groups and departments. Not checked yet
+10 more
show less
Adds X API MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. to the connector catalog. Not checked yet Unifies event triggers into Connector Events with audience fan-out, an event volume signal, and chat-list visibility for event-triggered runs. Not checked yet Enables Chrome, Edge, and Firefox auto-deploy on managed Windows devices via the AI Watch browser extension, with native identity hosts per browser. Not checked yet Enables AI Watch extension auto-deploy to Microsoft Edge on managed macOS devices. Not checked yet Removes the per-agent artifact limit. Not checked yet Adds server-side PDF text extraction to the Google Drive connector. Not checked yet Adds spend breakdowns per person, team, and department — with clients drilling down to models — and browseable usage by current teams and departments. Not checked yet Adds a work ledger for units-of-work pricing showing how each unit's cost was attributed, with branch checkouts steering attribution and Runlayer artifacts and skills counted as outputs with in-app preview. Not checked yet Relays upstream progress notifications through the proxy so long-running tools report progress to clients. Not checked yet Adds dynamic plugin routing per client, with Codex configured for plugin routing and org installs learning client-routed tools. Not checked yet
Adds runlayer_agent resource and data source to the Terraform provider so agents can be fully managed as infrastructure-as-code.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds HMAC signing for agent webhooks — create, rotate, and disable signing secrets from the webhook dialog, with a scheme picker and curl examples. Not checked yet Adds scan budgets to ToolGuard: configure latency and payload budgets with fail-open/fail-closed behavior, allow/truncate/block payload actions, and budget-exceeded events written to audit logs. Not checked yet Adds new get_table, delete_between_text, and delete_table tools to the Google Workspace connector. Not checked yet Adds usage APIs by IdP IdP A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. groups and departments. Not checked yet
+7 more
show less
Adds X API MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. to the connector catalog. Not checked yet Enables Chrome, Edge, and Firefox auto-deploy on managed Windows devices via the AI Watch browser extension, with native identity hosts per browser. Not checked yet Adds server-side PDF text extraction to the Google Drive connector. Not checked yet Adds spend breakdowns per person, team, and department — with clients drilling down to models — and browseable usage by current teams and departments. Not checked yet Adds a work ledger for units-of-work pricing showing how each unit's cost was attributed, with branch checkouts steering attribution and Runlayer artifacts and skills counted as outputs with in-app preview. Not checked yet Relays upstream progress notifications through the proxy so long-running tools report progress to clients. Not checked yet Adds dynamic plugin routing per client, with Codex configured for plugin routing and org installs learning client-routed tools. Not checked yet
3 more in Everything
Runlayer 1.28.428 adds webhook HMAC HMAC A keyed hash that proves a message came from someone holding a shared secret and was not altered. Webhooks and API request signing commonly use it. signing, scan budgets, Terraform agent management, and Edge auto-deploy.
Agent webhooks now support HMAC signing with secret creation, rotation, disabling, and a scheme picker Not checked yet Configurable scan budgets for latency and payload limits with fail-open/closed, allow/truncate/block actions, and audit log events Not checked yet Policies reject tokens from mismatched OAuth clients to harden token handling Not checked yet AI Watch browser extension auto-deploys to Chrome, Edge, and Firefox on managed Windows devices Not checked yet Edge AI Watch extension auto-deploys to managed macOS via Browser Extension Not checked yet
+15 more
show less
Extension health checks detect missing Chromium installations and refresh managed browser policy caches Not checked yet Skill removal tracking reconciles removed skills from host scans for accurate installation counts Not checked yet Connector Events unifies event triggers with audience fan-out, volume signals, and chat-list visibility Not checked yet Terraform provider adds runlayer_agent resource and data source for agent management Not checked yet Triggers UI now includes a polished Add Trigger flow and dedicated Triggers page Not checked yet Per-agent artifact limit is removed, allowing unlimited artifacts per agent Not checked yet Eager sandbox reconnects and immediate aborts on upstream rate limiting improve run steadiness Not checked yet Spend breakdowns allow analysis per person, team, and department with model drilling via new APIs Not checked yet Units of work pricing uses session time slices with a work ledger for cost attribution Not checked yet New usage APIs support querying by IdP IdP A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. groups and departments Not checked yet Google Drive connector extracts text from PDFs server-side Not checked yet Google Workspace connector adds get_table, delete_between_text, and delete_table tools Not checked yet X API MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector is available in the Connectors catalog Not checked yet Upstream progress notifications are relayed through the proxy for long-running tools Not checked yet Dynamic plugins route per client, with Codex configured for client-routed tool installation Not checked yet
20 details in Everything
└──▷ BREAKING ON UPGRADE
! No breaking changes found in this release.
Runlayer 1.28.318 adds Amazon Nova defaults for agents, inline skill editing, and units of work analytics
Agents can now run non-Claude Bedrock models with Amazon Nova defaults, enabling gateway routing and catalog pricing reports Not checked yet Read an agent’s sharing configuration (owner and user/group/role/team grants) through MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools via Runlayer MCP Not checked yet Long-running clients can read run-token expiry and self-fence before it lapses Not checked yet Inline skill editing allows markdown files to be edited directly in the skill view using a block markdown instructions editor Not checked yet AI outputs are grouped into units of work with a rebuilt timeline where drafted Slack messages count as output Not checked yet
5 details in Everything
Runlayer 1.28.281 adds broad policy principals, agent polling triggers, Slack file attachments, and output analytics.
all-users and all-agents policy principals allow targeting every user or agent in a single authorization entry Not checked yet get_deployment_logs MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool exposes container logs for deployments Not checked yet Agent responses can now attach files to their Slack replies via the Slack file attachments feature Not checked yet Output analytics tab adds business-function output inspection and output model participation metrics Not checked yet
4 details in Everything
Runlayer 1.28.208 adds human approval policies and one-click Slack agent installation
Adds Human approval policies Beta to hold an agent’s tool call for person-to-approve or deny before execution Not checked yet Enables One-click install for Slack agents via Managed Apps, removing OAuth screens during setup Not checked yet
2 details in Everything
Runlayer 1.28.206 adds Slack routing, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. rules, Claude Fable 5.1, and Nimble connector
Adds Slack security channel to route security notifications separate from general alerts Not checked yet Adds Scanner recommendations on connectors to surface catalog defaults before changes Not checked yet Adds Policy overrides from Shadow AI allowing allow/deny actions directly in the Activity tab Not checked yet Adds LLM usage rules that cascade across the LLM gateway via admin UI Not checked yet Adds Claude Fable 5.1 as a new model option for agents Not checked yet
+1 more
show less
Adds Nimble MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector to the catalog Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! Session grants no longer resolve for a grantor whose account has been deactivated
Runlayer v1.28.201 adds a reasoning effort picker to the agent tab and improves chat rendering.
Adds a reasoning effort picker in the agent tab UI to select an agent's reasoning effort from a compact menu Not checked yet Pretty-prints JSON payloads sent as user messages in the agent chat instead of displaying them as dense lines Not checked yet
2 details in Everything
Runlayer 1.28.200 adds scoped incident remediation and changed-file indicators to skill versions.
Adds changed-file indicators to skill version history Not checked yet Enables scoped incident remediation at local family/tool and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector/tool scope Not checked yet
2 details in Everything
Runlayer 1.28.191 adds Markdown rendering in approvals, inline results, and LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. routing for Claude Code/Codex.
Approval requests in the web app now render full Markdown — callouts, semantic entities, and formatted content instead of raw text Not checked yet The outcome of an approval shows inline in the request, so you can see what was decided without leaving the page Not checked yet Runlayer can now write LLM routing config for Claude Code and Codex clients Not checked yet
3 details in Everything
Runlayer 1.28.192 adds Agent Monitor dashboard, personal inbox for request decisions, delegation lifetime caps, and DCR auditing.
Adds Monitor dashboard tab to agents to view agent status Not checked yet Introduces personal inbox for items emitted when requests are decided Not checked yet Adds ability to set per-agent-account cap on delegation and access-token lifetime Not checked yet Enables auditing of failed dynamic client registrations and stamps successful ones with the org Not checked yet
4 details in Everything
Runlayer 1.28.188 adds per-scope memory, agent ownership, Slack channel allowlists, and TraeWork detection.
Notes and SQL memory are scoped per agent, team, or workspace instead of globally. Not checked yet Runlayer Assistant runs on your org's configured AI providers instead of a default provider. Not checked yet A Popular skills tab appears on the build home, ranked by real skill invocations. Not checked yet The in-app MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server now serves docs and help tools from your tenant via Connectors . Not checked yet Slack channel allowlist restricts which Slack channels an agent may post in. Not checked yet
+3 more
show less
Agents, plugins, connectors, and artifacts record an owner on creation with existing resources backfilled. Not checked yet Memory actor binding binds agent memory to verified runtime actors and enforces run-level authority. Not checked yet Detection coverage includes TraeWork detection and reliable detection of large JetBrains AI plugins. Not checked yet
8 details in Everything
Runlayer v1.28.183 adds AgentGuard sensitivity config, broadened AI Watch detection scope, and allowlist-only OAuth redirects.
AgentGuard sensitivity is now a configurable option for the AgentGuard behavior scan. Not checked yet Broaden AI Watch detection to cover top-50 AI clients, global npm installs, IDE plugins, runtimes, containers, and disguised skills (e.g., Claude Code via VS Code extension). Not checked yet Allowlist-only OAuth redirects enables restricting dynamic client registration redirect URIs to an allowlist in Connectors . Not checked yet Sessions panel now opens in a drawer with a key moments rail. Not checked yet Skill usage is visible in session timelines. Not checked yet
+3 more
show less
Pending requests are displayed on the Monitor page. Not checked yet Agent analytics includes a top erroring agents card and links agent names on the Usage page to the agent detail screen. Not checked yet Team artifact discovery allows adding and discovering team-shared artifacts from team and workspace pages. Not checked yet
8 details in Everything
Runlayer v1.28.181 adds agent monitor filters, Zed skill sync, fetch_artifact tool, list_ai_providers MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool, and stricter OAuth validation.
Filter agent runs by user and source with run_source and actor shown on each card Not checked yet Sync skills to Zed via the CLI with new Zed native skill support Not checked yet Install test devices on macOS or Windows in one command using hosted install scripts Not checked yet Fetch artifact content in sandbox agent runs with the new fetch_artifact tool Not checked yet List AI providers over MCP with the new list_ai_providers MCP tool Not checked yet
+6 more
show less
Filter manage skills list by device sync status Not checked yet Support writable file metadata in Google Drive connector Not checked yet Attribute token spans to the producing model in sessions Not checked yet Audit LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway and AI provider configuration changes Not checked yet Detect Claude Desktop and Cowork skills with AI Watch Shadow AI scanning Not checked yet Validate redirect URI allowlists consistently at client registration for stricter OAuth Not checked yet
11 details in Everything
Runlayer 1.28.179 adds runlayer doctor CLI, managed Slack onboarding, verified skills and DeepSeek V4 Pro support
Adds runlayer doctor CLI command to check OAuth and connectivity before deployment. Not checked yet Adds DeepSeek V4 Pro as a new model option for agent runs. Not checked yet Enables admins to mark skills as verified to indicate trusted status. Not checked yet Adds one-click Slack consent allowing approval of paused agent runs via Slack messages. Not checked yet Adds guided managed Slack setup during onboarding for connecting managed Slack accounts. Not checked yet
+4 more
show less
Allows setting event trigger conditions for agent event triggers. Not checked yet Expands detection scanning to include Pi, Kimi Code, Kilo Code, Junie, and Devin CLI tools. Not checked yet Supports upstream MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers using public OAuth clients without a client secret. Not checked yet Makes audit log action and resource types queryable over MCP. Not checked yet
9 details in Everything
Runlayer 1.28.177 adds live Slack progress cards, per-agent prompts, scheduled run audiences, artifact versioning, Windows/Linux skill sync, Grok hooks, header asset creation
Adds Live Slack progress card to replace per-tool-call checklists with one live-updating card for agent progress. Not checked yet Enables Per-agent Slack suggested prompts to assign unique suggested prompts to each agent in Slack. Not checked yet Introduces Scheduled run audiences with audience badges on schedules to control which recipients a scheduled agent run posts to. Not checked yet Adds Artifact versioning to maintain version history for artifacts, mirroring agent and skill versioning. Not checked yet Extends Automatic skill sync scheduling support to Windows and Linux platforms in addition to existing platforms. Not checked yet
+3 more
show less
Introduces Grok hooks to monitor local Grok CLI activity; note that Grok Bot cloud hooks are experimental. Not checked yet Enables Add team assets from the header creation directly from the team header instead of per-tab dropdowns. Not checked yet Streams Session events to your SIEM by allowing users to send session data to their own SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. bucket. Not checked yet
8 details in Everything
Runlayer 1.28.175 adds per-type scan actions for scanning rules and emergent org tags.
Adds per-type actions for scanning rules: choose a different action per PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. label and credential type instead of one action for the whole rule Not checked yet Emergent org tags are automatically applied to connectors, plugins, skills, and agents to group and find related resources Not checked yet
2 details in Everything
Runlayer 1.28.176 adds Bedrock provider support, artifact tagging, and container/WSL WSL Windows Subsystem for Linux, a Microsoft-built compatibility layer that lets a Linux environment run directly on Windows without a virtual machine, giving cyber tools access to Linux binaries, filesystems, and syscalls on a Windows host. detection to the agent platform.
Adds Amazon Bedrock as a configurable LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway provider for agent runs Not checked yet Introduces artifact tagging and filtering by team or workspace (readable via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. ) Not checked yet Increases the subagent limit from previous versions to 50 per agent definition Not checked yet Enables Runlayer Slack app installation through Enterprise Grid managed installs Not checked yet Adds Scan risk signals to skill reads over MCP for security context Not checked yet
+1 more
show less
Expands MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. detection capability to include Containers and WSL environments Not checked yet
6 details in Everything
New audit log coverage for org settings, Slack user-identity indicators, and desktop tray access controls
Audit logs now record changes to organization settings with ATLAS techniques on MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. log summaries Not checked yet Admins can see recent sessions and approve access requests directly from the Desktop tray Not checked yet The agent UI indicates when Slack MCP actions send as the connected user rather than the bot (Slack user-identity ) Not checked yet Scheduled agent runs now execute as the identity of the schedule creator Not checked yet Shared connector deployment warns before deploying a connector that is already in use by others Not checked yet
+3 more
show less
Guided setup for Slack agents walks through prerequisites before installation Not checked yet Agents can read usage-page token and spend data over MCP with clearer cost formatting Not checked yet Team and All Workspace plugin tabs support infinite scroll and server-side search Not checked yet
8 details in Everything
Runlayer v1.28.172 adds Anthropic tool-result scanning via ToolGuard and imported skill auto-update
create_agent reports the result of the Slack install operation. Not checked yet New Anthropic inference hooks adapter brings Anthropic-based clients under hook enforcement. Not checked yet Agents can now read a session’s activity and business-outcome summary over MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. . Not checked yet
3 details in Everything
Runlayer 1.28.173 adds skill scan failure visibility in the webapp and a per-agent Slack channel intro toggle.
Added skill security scan failure visibility in the webapp with summary details Not checked yet Added CLI self-update capability that aligns the installed version to the build source Not checked yet Added per-agent toggle for Slack channel intro messages Not checked yet
3 details in Everything
Runlayer v1.28.170 adds browser extension targeting, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. condition operator enumeration, and agent run privacy redaction.
Adds extension version targeting for the browser extension rollout, allowing administrators to choose which extension version rolls out to which devices Not checked yet Adds PBAC condition operator enumeration over MCP so agents can build policies without guessing available operators Not checked yet Adds agent run privacy redaction in Runlayer MCP tools so other users' agent-run content is not visible Not checked yet
3 details in Everything
Runlayer 1.28.169 adds Cursor coverage reporting, incident badge popovers, larger skill uploads, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. -based agent management APIs.
cursor surface coverage reporting alongside existing AI surfaces Not checked yet Compact incident rows with ATLAS technique badges that open explanatory popovers Not checked yet Skill upload limit increased to 5 MB Not checked yet delete_agent tool for agent removal via MCP Not checked yet Paging support (has_more) on list_agents and list_skills endpoints Not checked yet
5 details in Everything
Runlayer v1.28.167 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. support for MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. , blocking, sessions, evaluators and richer agent control, plus Slack agent routing.
Adds session topics and spend capabilities via MCP: enumerate session topics, pull spend rollups, and filter sessions by topic Not checked yet Adds eval scorers as a new MCP tool to discover available agent eval scorers Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! The CLI enforces a higher minimum MCP security level.
Runlayer 1.28.165 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools (Artifacts, Agent prompts), shared mailbox connectors, and recursive delete detection.
New MCP tool Artifacts allows reading artifacts and their contents over the Model Context Protocol Model Context Protocol Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Not checked yet New MCP tool Skill import from URL enables importing skills directly from a public repository URL Not checked yet New MCP tool Incident sessions lists the sessions behind an incident Not checked yet New MCP tool AI Watch status reads AI Watch client and status information Not checked yet New MCP tool Agent starter prompts allows reading and updating an agent’s starter prompts Not checked yet
+1 more
show less
Outlook connections now support shared mailboxes Not checked yet
6 details in Everything
Runlayer v1.28.163 adds AI policy drafting, new CLI tools (schedule), and broader client support.
runlayer schedule command for per-user scheduled tasks with macOS LaunchAgent support Not checked yet Ask AI drafting in the Policy builder rework Not checked yet Windsurf, Qwen Code, and Gemini CLI session hooks and enforcement support Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! Public/private team distinctions removed from the Teams catalog page
Runlayer 1.28.160 adds Intune macOS deployment, codex auto-sync, Slack notification toggles, and agent reasoning settings
Deploy agents to macOS fleets via Intune from the MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. wizard Not checked yet Codex configuration syncs automatically instead of requiring manual trigger Not checked yet Agents run with a max reasoning effort setting Not checked yet Toggle Slack security notifications between incidents and alerts Not checked yet Track ToolGuard scanner status in the dashboard alongside model changelog Not checked yet
+3 more
show less
Session scan results split into discrete cards Not checked yet Severity scored from outcomes with a recalibrated reason map Not checked yet Wider MCP-server MCP-server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. source-code signatures for Shadow detection; weak client evidence classified as traces Not checked yet
8 details in Everything
Runlayer 1.28.158 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. eval tools, sync-only API keys, list operators in PBAC and expanded browser enforcement.
skill_sync org-key role for creating sync-only API keys Not checked yet New Runlayer MCP tools to create and read agent eval runs Not checked yet contains / not_contains policy operators now accept list values Not checked yet Browser extension now enforces Lovable, Bolt, Poe, Meta, and Grok surfaces Not checked yet
4 details in Everything
Runlayer v1.28.157 adds Slack MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. connector, drift detection runtime shadows, and Intune .intunewin packaging.
Adds Slack MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. (OAuth) connector for connecting Slack MCP through a managed OAuth profile in the broker Not checked yet Detect now surfaces configured-vs-running state with runtime shadows to spot drift between declared and actually-running MCP setups Not checked yet Intune deployment card offers .intunewin package plus a signed detection script for easier MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. rollout Not checked yet Adds approval policy surfaces across the dashboard and Runlayer MCP Not checked yet Dashboard now shows source origin for each scanner policy (scanner policy provenance provenance Evidence recording where a software artifact came from and how it was built, including its source and build process. It helps a consumer check that the artifact matches a trusted build. ) Not checked yet
+1 more
show less
New controls to govern outbound messaging from Slack-based agents Not checked yet
6 details in Everything
Global policies unified view, skill auto-sync, Kimi K3 via Baseten
Global Policies page now displays every policy in a single view with a pinned pagination footer for easier navigation Not checked yet Skills sync automatically as first-class entities with assigned-skills visibility in ai-watch Not checked yet
2 details in Everything
Runlayer 1.28.150 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. denylist protection, ToolGuard feedback API, live AI Watch settings sync, and enhanced agent visibility.
Adds allow-unless-denied source governance for MCP denylists in Protect mode via remote URL, npm/PyPI package, or client built-in checks Not checked yet Introduces POST /api/v1/security/feedback endpoint for reporting ToolGuard false positives and false negatives using existing API keys and roles Not checked yet Enables automatic dashboard-to-agent sync of AI Watch settings without requiring MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. policy rebuilds Not checked yet Expands Agent MCP activity view to include tool calls and other MCP events beyond lifecycle and delegation rows Not checked yet Improves Slack-based agent support to reliably read image and PDF attachments shared in threads Not checked yet
5 details in Everything
Runlayer 1.28.153 adds Claude Opus 5 support for agents and introduces agent/skill version history with restore capabilities.
Adds Claude Opus 5 as a selectable model for agents Not checked yet Enables viewing and restoring previous versions of agents and skills Not checked yet Records version context on update audit events for agents and skills Not checked yet Adds server-side search across the /admin/requests inbox for admin requests Not checked yet
4 details in Everything
Runlayer 1.28.144 adds offline agent evals with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge, webhook run-as-agent, plugin v2 multisearch, and CLI manual OAuth.
Adds Offline agent evals to replay agent runs with overrides, scored by an LLM judge plus custom scorers Not checked yet Adds Webhook run-as-agent-account to allow webhooks to run as an agent account for true machine-to-machine runs Not checked yet Integrates Plugin v2 with multisearch Not checked yet Adds Manual OAuth support in the local CLI Not checked yet
4 details in Everything
Runlayer 1.28.147 adds Audited remote MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. and Google Forms connectors, Codex client recognition, session-linked audit logs, WSL WSL Windows Subsystem for Linux, a Microsoft-built compatibility layer that lets a Linux environment run directly on Windows without a virtual machine, giving cyber tools access to Linux binaries, filesystems, and syscalls on a Windows host. scanning, MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. toggles via UI, and unified /adm
Adds Audited remote MCP servers to the connector catalog for vetted remote tool use tool use A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. . Not checked yet Adds write tools for Google Forms in the connector ecosystem. Not checked yet Recognizes the Codex MCP client as a supported runtime. Not checked yet Associates audit log entries with their session for end-to-end tracing. Not checked yet Extends home-directory artifact scanning to WSL home directories. Not checked yet
+3 more
show less
Adds MDM process and container detection toggles directly in the config UI. Not checked yet Unifies the requests inbox at /admin/requests with infinite scroll. Not checked yet Enables adding or removing skills, plugins, and agents from any All Workspace tab. Not checked yet
8 details in Everything
Runlayer 1.28.142 adds org logo upload and expands AI Watch scan coverage.
Adds organization logo upload to brand the Runlayer workspace Not checked yet Expands AI Watch scan coverage to include more agent definitions and container artifacts Not checked yet
2 details in Everything
Runlayer 1.28.141 adds Sourcegraph MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector and active-hours agent schedules
Sourcegraph connector added to the catalog (official MCP server integration) Not checked yet Active-hours window support for agent schedules to restrict execution times Not checked yet
2 details in Everything
AI Watch detects shadow/managed clients, correlates MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. runtime sightings, supports client_credentials client_credentials An OAuth 2.0 grant type where a service authenticates directly with an authorization server using its own ID and secret, with no user involved, to obtain an access token for machine-to-machine API calls. OAuth and auto-provisions users.
AI Watch now detects installed AI clients during scans and classifies them as shadow or managed, with a new client catalog and installation tables in the Shadow AI overview Not checked yet MCP processes and MCP configs found inside running containers are correlated as runtime sightings in the UI Not checked yet Allowlist discovered AI clients and drill into per-client audit detail Not checked yet Enforcement can now be disabled for individual users Not checked yet Download the AI Watch installers selected by your policy Not checked yet
+3 more
show less
Users surfaced during AI Watch scans that don’t match an existing account are now automatically provisioned Not checked yet Remote MCP servers now support the client_credentials upstream OAuth mode Not checked yet Owner opt-in for standalone machine-to-machine MCP access grants Not checked yet
8 details in Everything
Runlayer v1.28.139 adds AI Watch auto-updating, customizable block messages and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. -based incident/session viewing.
Adds AI Watch agent auto-update for Windows and Linux endpoints Not checked yet Adds customizable security block message configuration for scanner violations Not checked yet Enables viewing incidents and sessions through Runlayer MCP tools Not checked yet
3 details in Everything
Runlayer 1.28.137 adds Carta/Egnyte/Make/Replit connectors, AI Watch device filters, and unused agent cleanup
Adds Carta , Egnyte , Make , and Replit as new MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server connectors in the catalog Not checked yet Adds an Unused tab on the Agents page with a last-used badge to identify zombie agents for cleanup Not checked yet Unpacks Usage Activity into six dedicated widgets for at-a-glance insights in Analytics Not checked yet Adds unified device filters across AI Watch views via AI Watch device filters Not checked yet Redacts environment secrets from get_deployment MCP tool output Not checked yet
+1 more
show less
Applies lifetime-relative inline-refresh floor to OAuth for reliable short-lived token refresh Not checked yet
6 details in Everything
Runlayer 1.28.133 adds per-client scanner overrides, AI Watch container support, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. allowlists and sub-day audit filters.
Security scanner settings can now be overridden per-MCP client to apply stricter scanning without changing global configuration Not checked yet Credential masking controls now allow choosing exactly which credential types the scanner masks via new ToolGuard settings Not checked yet New containerized deployment options for AI Watch Detect using standalone images, DaemonSets or CronJob manifests on Kubernetes Not checked yet Enforce policies now support MCP server allowlists and blocking built-in client tools with a dedicated allowlist editor Not checked yet Audit logs now support sub-day (hour-level) time filters and include new events for agent enable/disable and scanner setting changes Not checked yet
5 details in Everything
Runlayer 1.28.128 adds a new admin Monitor dashboard, Kubernetes deploy support, and multi-select plugin creation.
Adds a new Monitor home for admins with workspace-wide insights; admins now land on Monitor after login. Not checked yet Enables deploying Runlayer MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers on Kubernetes (enterprise) with pod logs and status visible in the deployment UI. Not checked yet Allows multi-selecting connectors and skills to create or extend a plugin, and recommends the Runlayer Plugin in add-to-client flows. Not checked yet
3 details in Everything
AI Watch supports Linux agent memory with scoped persistence
Adds AI Watch detection mode for Linux via native packages Not checked yet Adds scoped agent memory to persist and recall data across runs Not checked yet
2 details in Everything
Runlayer 1.28.71 adds a Microsoft Teams MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector for managing chats and channels
Runlayer 1.28.119 adds guided agent creation, beta OAuth connector support, skill scan transparency, and Web AI Watch capture for 10 clients.
Adds a new dedicated agent creation page with a guided flow in the UI Not checked yet Enables catalog connectors to register with vendor-required OAuth client names and be flagged as beta, unblocking integrations like Figma remote MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Not checked yet Provides skill import transparency by showing exact source snippets behind security findings and allowing shadow skills to open in a viewer with inline risk annotations Not checked yet Adds pagination for deployment logs in the Deploy interface Not checked yet Introduces a search box in the Settings sidebar Not checked yet
+1 more
show less
Expands Web AI Watch browser extension capture to 10 specific AI chat web clients to reduce false positives Not checked yet
6 details in Everything
Runlayer 1.28.112 adds Claude Sonnet 5 agents, model governance, MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. -configurable AI Watch, Ashby connector, and UI pagination.
Adds Claude Fable 5 and Sonnet 5 as available agent models when Anthropic or AWS Bedrock is configured Not checked yet Adds Model governance to restrict which LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. models each role may use and configure a recommended model Not checked yet Adds Ashby as a new catalog connector Not checked yet Makes AI Watch project depth and timeout MDM-configurable Not checked yet Adds infinite scroll and server-side pagination on the agents, skills, and connectors pages for faster large workspaces Not checked yet
5 details in Everything
Runlayer v1.28.70 syncs agent icons to Slack bot profiles in seconds.
Agent Slack app icon sync: Agent icons are now synced to Slack app bot profile images. Not checked yet
1 detail in Everything
Runlayer 1.28.109 adds GitHub Copilot CLI hooks, customizable no-access messages, and agent sorting.
Adds GitHub Copilot CLI to AI Watch session monitoring and enforcement scope Not checked yet Adds a customizable no-access message for connector policy blocks Not checked yet Adds account rename and disconnect actions in the connector account menu Not checked yet
3 details in Everything
Runlayer v1.28.102 adds LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. spend analytics by agent, shareable agent artifacts, and a Tinybird connector.
Adds Agent spend analytics that breaks down LLM spend by agent Not checked yet Makes Agent artifacts shareable with other users Not checked yet Adds Tinybird as a new catalog connector Not checked yet
3 details in Everything
Runlayer 1.28.99 adds self-improving agents with cost budgets, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. artifact APIs, and browser extension delivery via MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. .
Adds opt-in self-improving agent capability that distills reusable Skills from successful runs Not checked yet Adds agent_cost_budgets per-agent LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. cost budget configuration Not checked yet Adds programmatic artifact management (create, update, list, delete) via Runlayer MCP Not checked yet Enables native skill installation into Codex Not checked yet Adds AI Watch browser extension delivery through MDM configuration in the CLI Not checked yet
+2 more
show less
Adds team settings dialog for renaming teams, setting icons, and controlling visibility Not checked yet Replaces the Runlayer-built Snowflake server with an official Snowflake Cortex MCP connector Not checked yet
7 details in Everything
Runlayer AI Watch for Windows now uses device-local Scheduled Tasks instead of Intune Remediations.
AI Watch on Windows registers device-local Scheduled Tasks (SYSTEM hook + per-user S4U scan fan-out) to run scans in each user’s context without interactive logon Not checked yet Intune P2 / Remediations dependency removed for AI Watch on Windows; use detect-install.ps1 as the custom detection rule instead Not checked yet
2 details in Everything
Runlayer 1.28.96 adds Azure AI Foundry provider, device monitoring dashboard, and incident filtering.
Adds Azure AI Foundry as a new LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. provider option for agents Not checked yet Introduces the AI Watch Devices tab on the Shadow dashboard for per-feature check-in and health monitoring of device inventory Not checked yet Adds VS Code hooks to enable session monitoring and enforcement within VS Code Not checked yet Adds Goose hooks support for the Goose client Not checked yet Enables team owners to share skills with their team via Teams: skill sharing Not checked yet
+3 more
show less
Adds filtering capability to the incidents list and renames Severity to Priority for better Slack formatting Not checked yet Allows admins to change an agent’s owner from the Share modal via Agent ownership transfer Not checked yet Includes unique user counts in Connector metrics activity data Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! The Severity field is renamed to Priority
Runlayer 1.28.89 adds runlayer catalog CLI commands and an Artifacts tab for agents
runlayer catalog subcommands enable browsing skills, plugins, and connectors directly from the terminal Not checked yet Agent pages now include an Artifacts tab listing published files Not checked yet Sidebar sections in the UI can now be collapsed and persist per browser session Not checked yet
3 details in Everything
Runlayer 1.28.82 adds AI Providers settings, AWS Bedrock support, interactive test connections, and OAuth redirect-URI consent
Adds Settings → AI Providers page to configure LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. providers per agent Not checked yet Enables configuring AWS Bedrock as an agent LLM provider Not checked yet Generates automatic titles for sessions Not checked yet Adds interactive tool runner in the Test Connection drawer for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools Not checked yet
4 details in Everything
Runlayer adds row overwriting and cell padding to Google Docs table editing
edit_table.set_row_text now accepts a list of values to overwrite an entire row in one call Not checked yet style_cell gains a padding option to set cell padding on all four sides (in points) Not checked yet
2 details in Everything
Runlayer 1.28.77 adds Artifacts gallery, single-org AI Watch deployment with capability flags, and auto-created access policies for new connectors.
Adds Artifacts gallery to browse all artifacts published by agents Not checked yet Changes AI Watch MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. deployment to use one org API key with capability flags instead of per-feature credentials Not checked yet Enables hosted stdio connectors to prompt each user for their own environment variables (e.g. personal API keys) Not checked yet Adds icon picker when creating a custom connector Not checked yet Auto-creates an access policy for every new connector at creation time Not checked yet
5 details in Everything
Runlayer v1.28.66 enables onedrive_read_file to extract text from Office files server-side.
Runlayer 1.28.65 improves SharePoint and Outlook integration fidelity: exact site resolution for sharepoint_search_sites and lightweight calendar summaries for list views.
Runlayer 1.28.73 adds skill editing in UI, unredacted audit log filters, and native Metabase and Deel MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connectors.
Enables direct editing and renaming of skills within the web interface Not checked yet Adds an Unredact filterable event type to the Audit Logs view Not checked yet Replaces the Runlayer-deployed server with a native Metabase MCP connector Not checked yet Introduces a new hosted Deel MCP connector Not checked yet
4 details in Everything
Runlayer v1.28.64 adds outlook_create_reply_draft tool for saving editable Microsoft Outlook reply drafts in-thread.
Adds the outlook_create_reply_draft tool which saves a Reply or Reply-All as an editable draft nested inside the original conversation. Not checked yet
1 detail in Everything
Runlayer v1.28.24 adds Identity Forward to all HTTP connectors, web UI .md skill upload, and a new MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. config wizard.
Enable X-Runlayer-* headers or signed JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. Identity Forward on any Streaming HTTP or SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. connector via its configuration Not checked yet Upload a single .md file as SKILL.md in the web UI to create skills with auto-derived names Not checked yet Install full event/session hook set by default for MDM deployments; toggle enforcement-only with MDM field set to false Not checked yet Access Settings → MDM Configuration wizard to guide platform selection, detect/enforce mode, and artifact download Not checked yet
4 details in Everything
Runlayer 1.28.63 adds HITL HITL Human in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues. notify-only mode, quarterly agent schedules, Slack channel blocklists, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. export noise reduction
Adds asynchronous HITL Notify-Only approval mode for agents Not checked yet Allows agent schedules to use :00, :15, :30, and :45 cadences Not checked yet Adds Slack channel blocklist support in admin settings Not checked yet MCP export_audit_logs trims verbose internal details by default with an opt-in flag Not checked yet
4 details in Everything
Runlayer 1.28.23 adds webhook API-key auth, bulk audit log export via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. , and customer-owned SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. S3 bucket support.
Webhook dialog can now require API-key authentication for agent webhooks Not checked yet Adds export_audit_logs tool to Runlayer MCP for exporting logs as JSON or CSV Not checked yet Runlayer Hooks TypeScript SDK supports client_credentialsclient_credentials An OAuth 2.0 grant type where a service authenticates directly with an authorization server using its own ID and secret, with no user involved, to obtain an access token for machine-to-machine API calls. token exchange token exchange An OAuth 2.0 protocol extension (RFC 8693) that lets a service trade one token for another with different scopes, audience, or type, enabling delegation and impersonation across service boundaries without re-authenticating the user. for agent account auth Not checked yet SIEM export allows writing directly to a customer-owned S3 bucket Not checked yet Shadow page includes new Skills section with discovery timeline and breakdowns Not checked yet
+4 more
show less
Agent run timelines now render subagent tool calls and events inline Not checked yet Claude Opus 4.8 is available as an agent model when Anthropic is configured Not checked yet Server-level Policies tab renamed to Permissions in the UI Not checked yet New catalog connectors: AWS MCP, Supernova Relay MCP Not checked yet
9 details in Everything
Runlayer adds Microsoft Outlook Calendar MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector with 11 tools for event CRUD CRUD The four basic database operations — Create, Read, Update, Delete — used as shorthand for any system that manages persistent data records, giving cyber tools a standard model for interacting with stored information. and availability lookups
Runlayer 1.28.21 adds Mask violation action, self-serve SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. role mapping, and agent cloning.
Adds Mask violation action to Security Scanners to redact detected PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. or credentials while allowing the request to continue Not checked yet Enables admin-only configuration of SCIM groups-to-roles mapping in Settings → Workspace → Manage Directory Sync for self-serve directory sync Not checked yet Introduces agent cloning capability via the renamed Clone action, copying configuration, connectors, and tools to a new agent Not checked yet
3 details in Everything
Runlayer 1.28.20 adds PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. regex detection, Helm CA/bundle config, new MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools, and expanded client scanning.
Adds model and icon parameters to the create_agent MCP tool. Not checked yet Adds is_disabled parameter support to the update_agent MCP tool. Not checked yet Expands create_server and update_server MCP tools to support all REST API REST API A web API design style where clients interact with resources over HTTP using standard methods like GET, POST, and DELETE, giving cyber tools a predictable, language-agnostic way to integrate with external services. fields including OAuth, audit log sensitivity, and deployment association. Not checked yet Adds PII pattern-based detection using regex validators for SSN, credit card, phone, email, passport, driver’s license, IBAN, IP address, date of birth, MRN, VIN, Bitcoin address, and Ethereum address. Not checked yet Allows organization API keys to be scoped with the Deploy role. Not checked yet
+7 more
show less
Enables mounting a custom trusted CA bundle for outbound HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. in self-hosted Helm deployments. Not checked yet Adds support for referencing an existing Kubernetes Secret for backend credentials in Helm chart configuration. Not checked yet Adds ability to configure a read-replica endpoint for offloading read traffic in Helm deployments. Not checked yet Expands AI Watch detection to discover MCP configs in Cline, Cline CLI, Gemini CLI, Antigravity, and GitHub Copilot CLI. Not checked yet Adds codex mcp add <name> --url <proxy> command for native client setup. Not checked yet Shows user attribution for shadow MCP servers in discovery reports. Not checked yet Adds Ramp Data as a new catalog connector with read-only financial data support. Not checked yet
12 details in Everything
Runlayer 1.28.19 adds artifact publishing, agent memory toggle via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. , and shareable session links
Adds publish_artifact tool to agents for sharing workspace files as URLs Not checked yet Adds enable_memory parameter to create_agent and update_agent MCP tools Not checked yet Enables shareable direct links for agent run sessions from the sessions list Not checked yet
3 details in Everything
Runlayer v1.28.18 adds skill risk badges, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. client analytics, Slack DM mode via slack_terminal_run_dm_mode, and refreshed agent templates.
Adds the slack_terminal_run_dm_mode config key to control run-result Slack DMs (always, errors_only, disabled) via the update_agent MCP tool Not checked yet Introduces a Skill risk assessment widget on the Skills tab with per-skill risk level badges (High, Medium, Low, Minimal, Unknown) Not checked yet Adds a Plugin usage by client widget to the Plugins tab showing which MCP clients generate the most plugin activity Not checked yet Replaces agent creation templates with new default patterns: 1:1 Prep, Release Notifier, Account Intelligence, Daily Briefing Not checked yet
4 details in Everything
Runlayer 1.28.17 adds GPT-5.5 support, OneDrive/SharePoint MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connectors, and expanded agent permissions.
Adds GPT-5.5 as an available agent model when OpenAI is configured as the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. provider. Not checked yet Adds OneDrive and SharePoint MCP connectors for Microsoft 365 integration. Not checked yet Expands Runlayer MCP server management to allow creating, updating, and deleting connectors via admin-only commands. Not checked yet Adds a Connectors section to the Shadow page UI showing shadow servers, users, migration targets, and MCP client usage. Not checked yet Allows all workspace members (not just admins) to view agent accounts, create delegations, and create session grants. Not checked yet
+4 more
show less
Enables agent say tool on webhook and scheduled runs when the Slack MCP connector is attached. Not checked yet Makes Agent memory an opt-in feature available via advanced settings. Not checked yet Includes tool calls and results from prior turns in agent conversation context for better multi-step continuity. Not checked yet Adds Skyvern to the connector catalog. Not checked yet
9 details in Everything
Runlayer 1.28.16 adds scoped PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. detection, new connectors (Kubernetes, Tines), shadow analytics, and Outlook MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. guide
Adds PII scan direction configuration to scope PII detection to tool inputs, outputs, or both, configurable globally in Settings → Security Scanners or per connector. Not checked yet New Shadow vs Managed breakdown chart and Shadow Server Discoveries timeline available on the Shadow page for better visibility into unauthorized connectors. Not checked yet Adds new connectors for Fellow, Tines, Kubernetes, and Superhuman Mail to the catalog. Not checked yet Adds a dedicated Outlook setup guide for the Outlook MCP connector. Not checked yet New workspace setting in Settings → Workspace allows admins to show full admin-facing client setup instructions to all users. Not checked yet
5 details in Everything
Runlayer 1.28.15 adds identity forwarding via headers/JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. , timezone-aware agent schedules, and new catalog connectors.
HTTP-based MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connectors (Streaming HTTP or SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. ) now receive the authenticated caller's identity via X-Runlayer-* headers or a signed JWT when enabled in connector configuration Not checked yet Agent schedules support a Local wall clock mode that evaluates cron expressions in the selected timezone and automatically adjusts for DST transitions Not checked yet New catalog connectors Pinpoint ATS, Clay, and pganalyze are now available Not checked yet
3 details in Everything
Runlayer 1.28.14 adds configurable risk policies, Intune Remediation support, and new catalog connectors.
Adds per-tier actions (Block, Warn, Allow) for high-risk and medium-risk skills in Settings → Security Scanners Not checked yet Adds Remediation deployment method to the Intune deployment guide Not checked yet Adds Smartsheet and DataGrail Vera to the connector catalog Not checked yet Hides Draft status connectors from MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. endpoint and proxy visibility Not checked yet
4 details in Everything
Runlayer Assistant GA, Onelayer plugin default visibility, Slack run context in Activity view, new Amazon Redshift connector.
Adds runlayer_assistant generally available for all workspaces with agents enabled. Not checked yet The onelayer plugin is now visible in the plugin list for all users without a feature flag gate. Not checked yet Agent runs triggered from Slack now display conversation, channel, and trigger details in the Activity view, with a direct link to the originating Slack message. Not checked yet Adds Amazon Redshift as a new catalog connector (read-only SQL — discover, explore, and query Redshift clusters and serverless workgroups). Not checked yet
4 details in Everything
Runlayer 1.28.12 adds Claude Opus 4.7 agent support, custom deployment icons, PPPC profiles for macOS Detect, and ZoomInfo connector.
Adds Claude Opus 4.7 as an available agent model when Anthropic is configured as the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. provider Not checked yet Enables setting a custom icon during agent creation in the UI Not checked yet Allows setting or updating custom icons for deployments via the deployment settings dialog Not checked yet Adds a Resume action in the Activity view to continue past agent runs in the Playground with prior context Not checked yet Updates Slack messages to display the LLM model used per response and removes inline tool outputs Not checked yet
+3 more
show less
Auto-grants developer access to the deploying user when deploying a connector via the CLI Not checked yet Adds the ZoomInfo connector to the new catalog connector list Not checked yet Promotes the Ashby connector from beta to generally available Not checked yet
8 details in Everything
Runlayer 1.28.11 adds agent tool call analytics, auto-sync plugins via Onelayer, connector alias resolution in CLI, and new Render/Hugeicons connectors
Adds top agents by tool calls ranking widget in the Agents tab alongside the existing top-by-runs metric. Not checked yet Adds a built-in persistent SQLite database for agent memory; documented with no extra storage setup required. Not checked yet Adds an Auto Sync toggle to the Onelayer org install dialog, pushing plugins via runlayer setup sync. Not checked yet Expands runlayer setup sync to install both connectors AND plugins marked for auto-sync. Not checked yet Allows runlayer run to accept a connector alias in addition to a UUID UUID A universally unique identifier, usually a 128-bit value used to identify an object across systems. It is designed to make independently generated identifiers unlikely to collide. for target resolution. Not checked yet
+2 more
show less
Adds the new recipes page with copy-paste examples for M2M tokens, OBO flows, session grants, and external user mapping. Not checked yet Adds Render and Hugeicons connectors to the catalog. Not checked yet
7 details in Everything
Runlayer 1.28.10 adds Terraform Provider beta, session grant-based OAuth auth, Slack messaging, and admin revocation.
Adds a Terraform Provider Beta for managing Runlayer policies and resources Not checked yet Uses session grants for agent account authentication to OAuth-protected connectors Not checked yet Automatically revokes all of a user's session grants when an admin deactivates the user Not checked yet Introduces the Slack say tool so agents can post additional messages back to a conversation thread Not checked yet
4 details in Everything
Runlayer 1.28.9 adds Agents analytics tab, agent duplication, OpenAI org install, connector search, and schedule badges.
Adds Agents tab to the Analytics dashboard featuring an inventory card and runs-over-time chart Not checked yet Enables workspace members to duplicate agents from the detail page or agent card menu, cloning configuration, connectors, and tools Not checked yet Adds OpenAI support to the Add to Organization flow for the Onelayer plugin with MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector registration and skills upload in ChatGPT Not checked yet Disables manual role and group editing in the UI when SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. directory sync is enabled, displaying an explanatory banner instead Not checked yet Adds global command palette (Cmd/Ctrl+K) and query parameter on the servers API for connector search by name or description Not checked yet
+1 more
show less
Displays a badge on agent cards indicating the count of active schedules for that agent Not checked yet
6 details in Everything
Runlayer 1.28.8 adds Goose MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. client support, S3 SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. export, agent UI filters, and CLI skills/plugins commands.
Goose is now a supported MCP client with hosted and local setup guides Not checked yet Audit logs can now be continuously exported to an S3 bucket for SIEM ingestion via the SIEM export (S3) feature Not checked yet CLI 0.23.0 adds new skills find and plugins find commands for browsing and installing skills or plugins from the terminal Not checked yet The Agents page supports sorting by newest, oldest, alphabetical, and last-used, plus a status filter (active / disabled) Not checked yet The Playground now automatically injects Runlayer tools (search, run, manage) so agents can reason about the workspace without manual connector setup Not checked yet
+2 more
show less
Connectors requiring authorization now show a guided access setup dialog directly during agent creation, with per-connector status indicators Not checked yet The tool picker in policies now includes an annotation-based category dropdown next to Select All for faster bulk selection Not checked yet
7 details in Everything
Runlayer 1.28.7 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. subagent management, Ravenna connector, Slack link, and scheduled run retries
Add, update, and delete subagents on an agent directly through Runlayer MCP tools (confirm-required). Not checked yet New catalog connector for Ravenna (AI knowledge management — search knowledge bases, manage channels, and automate support workflows). Not checked yet Agent Slack settings now include a direct link to manage the agent’s Slack app on api.slack.com. Not checked yet Scheduled agent runs now retry transient authentication errors automatically instead of failing immediately. Not checked yet
4 details in Everything
Runlayer 1.28.6 adds agent creation from plugins, AirOps/Pendo connectors, CLI deploy URL output, and Analytics v2 UI overhaul.
deploy command (CLI) now prints the deployment URL after a successful deploy Not checked yet Agent inheritance: creating an agent from a plugin detail page automatically inherits that plugin’s connectors and skills Not checked yet Connector catalog additions: AirOps (50 tools) and Pendo; Datadog now uses its full toolset by default Not checked yet Analytics v2 Overview tab: new Tasks chart (human vs agent), Usage card, Most Used Clients, and redesigned Security Alerts widget Not checked yet
4 details in Everything
Runlayer 1.28.5 adds sensitive audit log redaction for connectors, scheduled run failure DMs, and a new Connectors analytics tab.
Adds the ability to mark connectors as sensitive, triggering automatic redaction of tool call arguments, results, and security scan details from audit log entries Not checked yet Enables Agent owners to receive a Slack DM notification when a scheduled agent run fails Not checked yet Introduces a dedicated Connectors tab in Analytics containing top-by-tool-call, connector health, and usage-by-client widgets Not checked yet
3 details in Everything
AI Watch adds Codex/OpenCode plugin scanning; Enforce supports Claude Code MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. interception; new Zoom connector and Agent Policies UI.
Adds detection of installed plugin artifacts in Codex and OpenCode for AI Watch via CLI 0.22.0 Not checked yet Enables shadow MCP tool call interception for Claude Code on macOS in Enforce Not checked yet Adds a dedicated Policies section in the Agent detail page for managing per-agent access rules Not checked yet Displays skill usage timelines and top skills rankings in the Analytics Skills tab Not checked yet Introduces Zoom connector to the catalog with meeting search, recording access, and Docs creation tools Not checked yet
5 details in Everything
Runlayer 1.28.4 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. policy CRUD CRUD The four basic database operations — Create, Read, Update, Delete — used as shorthand for any system that manages persistent data records, giving cyber tools a standard model for interacting with stored information. , configurable ToolGuard sensitivity levels, and security warning classification.
Tool Guard now supports Strict , Balanced , and Moderate sensitivity levels configurable per connector Not checked yet Adds Create, Update, Delete (CRUD) operations for policies via Runlayer MCP governance tools Not checked yet Classifies hidden-character masking and sensitive-token masking findings as security warnings instead of violations Not checked yet
3 details in Everything
Runlayer 1.28.2 adds agent subagents, v2 analytics tabs, audit events, and API rename.
Adds AGENT_RUN, AGENT_RUN_SUCCESS, and AGENT_RUN_FAILURE audit log events for agent runs Not checked yet Introduces shadow subagents that inherit parent connectors but follow separate instructions Not checked yet Adds a Delete All option in Deployments to remove connected servers alongside the deployment Not checked yet Includes Kandji in Shadow MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. device filtering Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! The public Agents API routes have been renamed from /assistants to /agents.
Runlayer 1.28.1 adds native Codex plugin install, agent templates, and Kandji/Vimeo connectors.
codex plugin support is now installed via CLI for first-class integration Not checked yet Agent templates (workspace agent, research agent, weekly summary, morning brief) pre-fill name, prompt, connectors, and tools Not checked yet Failed agent runs can be retried from the Activity view Not checked yet Agent owner is displayed on the agent detail page Not checked yet Grant access button appears on connector cards for authorization-required connectors Not checked yet
+3 more
show less
Kandji MDM MDM Mobile device management, centrally configuring and managing enrolled devices. Administrators use it to apply settings, distribute applications and enforce device security policies. support added for auto-provisioning Not checked yet Vimeo connector available in the connector catalog Not checked yet Workday deployments now support configurable OAuth scopes Not checked yet
8 details in Everything
Runlayer 1.28.0 adds granular admin roles, shadow skill detection, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. proxying and CLI keychain storage
Adds Security Admin , IT Admin , Helpdesk , Developer and Analytics Admin roles alongside Super Admin for separation of duties Not checked yet Enables Shadow AI coverage now includes skills to discover, classify and surface analytics on shadow skills in supported clients Not checked yet Supports workspace-level LLM provider settings with Anthropic, OpenAI, and OpenAI-compatible gateways Not checked yet Routes OpenAI model traffic through the backend proxy layer via new proxying configuration Not checked yet Adds per-agent SQLite-backed memory scoped to individual agents Not checked yet
+18 more
show less
Allows disabling agents without deletion, blocking Slack, webhook and scheduled execution until re-enabled Not checked yet Introduces SkillWatch analytics with skill discovery metrics, risk breakdowns and outdated-skill visibility Not checked yet Captures install analytics to track adoption of skills and plugins Not checked yet Rebuilds deploy UX around guided dialogs, inline CLI commands and clearer setup states Not checked yet Adds Build with Runlayer MCP entry point connecting deployment setup with the MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Builder workflow Not checked yet Supports renaming deployments directly from the UI Not checked yet Expands plugin publishing workflow to support Claude-format plugin publishing via CLI and inline manifest support Not checked yet Reads mcpServers from .claude-plugin/plugin.json with fallback to legacy .mcp.json Not checked yet Adds native install guidance for clients including VS Code Not checked yet Improves plugin push stability, root skill path handling and removal by UUID UUID A universally unique identifier, usually a 128-bit value used to identify an object across systems. It is designed to make independently generated identifiers unlikely to collide. Not checked yet Supports multiple principals (users, groups, roles or agents) per permission rule Not checked yet Enables capability-gated UI and API navigation so users only see what their role allows Not checked yet Provides read-only troubleshooting and analytics access for Helpdesk and Analytics workflows Not checked yet Updates global and connector-level policy flows with a better editing UX Not checked yet Ensures audit parity for plugins and skills by logging installs, updates and upstream token refresh events Not checked yet Stores CLI credentials in the OS keychain instead of plain local config Not checked yet Folds verified-local into run to simplify local run flow Not checked yet Adds Guru as a supported OAuth Broker vendor Not checked yet
23 details in Everything
Runlayer 1.27 adds Tool Intent Guard, org API keys, configurable PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. scanning, and a Security Scanning API endpoint.
Adds Tool Intent Guard runtime model that detects intent drift, output poisoning, data exfiltration data exfiltration Moving data out of a system or organization without authorization. It can happen through network transfers, removable media or other channels. , and prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. by analyzing tool inputs and outputs together. Not checked yet Provides /score/tool_guard_io API endpoint for programmatic security scanning of tools via CI workflows or custom integrations. Not checked yet Introduces organization-level API keys scoped by role (Detect Scan , Security Scan ) with auto-provisioning via enrollment keys. Not checked yet Enables configurable PII scanning per connector, allowing users to enable/disable built-in types and add custom regex rules. Not checked yet Adds Just-in-Time (JIT JIT A runtime compilation strategy where code is translated from an intermediate form to native machine instructions at execution time, giving tools the speed of compiled code without sacrificing dynamic flexibility. ) Auth which prompts for credentials only on the first tool call, utilizing a three-tier cache. Not checked yet
+2 more
show less
Releases 25+ new catalog connectors including Lemlist, Webflow, Google Analytics, Neon, Pylon, DX, official Slack MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. , Deepwiki, CircleCI, Ashby, Figma Desktop, Miro, Jamf, Cloudflare (16 servers), Datadog, Vanta, Granola, and LaunchDarkly. Not checked yet Moves BigQuery BigQuery A serverless, cloud-hosted analytical database from Google that runs SQL queries across massive datasets without managing infrastructure, giving cyber tools scalable storage and fast querying over large volumes of log or event data. and Slack connectors out of beta status. Not checked yet
7 details in Everything
Runlayer v1.25.0 introduces Deploy from Catalog, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Watch, Agent Accounts, and security scanner management tools.
Adds ability to deploy servers directly from the Catalog with Runlayer Deploy Not checked yet Adds MCP Watch for shadow MCP discovery, tracking, and migration identification in Analytics Not checked yet Adds capability to trigger re-analysis of discovered MCP servers from the UI via MCP Watch Not checked yet Adds Microsoft Agent 365 integration with full OAuth broker support and catalog servers Not checked yet Adds per-server metrics tab showing tool call health, usage, and performance charts Not checked yet
+14 more
show less
Introduces Agent Accounts Beta to register AI applications for programmatic authentication and MCP tool calls Not checked yet Adds Runlayer self-MCP server capability to run Runlayer as an MCP server for automation Not checked yet Adds security scanner management tools within Runlayer MCP for programmatic settings control Not checked yet Adds dedicated MCP Catalog API service with API key authentication for downstream security scanners Not checked yet Makes catalog tool lists available alongside catalog data to support static analysis and compatibility checks Not checked yet Adds MCP Watch CLI workflow to collect device-side MCP configuration scans Not checked yet Expands MCP Watch client support to include Goose and Zed Not checked yet Adds request IDs to audit logs for faster investigations and support workflows Not checked yet Adds typed actor/resource fields to audit log records for compatibility with long-lived deployments Not checked yet Adds CLI login via device flow for authentication from constrained environments Not checked yet Adds new CLI command cache clear for simpler troubleshooting Not checked yet Updates ToolGuard with new threat detection capabilities Not checked yet Improves deployment logs by redacting sensitive environment variables by default Not checked yet Allows force-triggering new deployments and redeploys more explicitly in Runlayer Deploy Not checked yet
19 details in Everything
Runlayer 1.13.1 adds permission warnings, ToolGuard area details, CLI pull, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. catalog updates.
Users now see a warning before connecting an MCP client if they lack the necessary permissions Not checked yet Security violations now show the specific area of concern that triggered the detection Not checked yet Added Pulumi and Parallel Search to the MCP catalog Not checked yet New pull command for downloading runlayer.yaml deployment configurations in the CLI Not checked yet New optional MCP caching setting for tools/list requests to improve performance Not checked yet
+1 more
show less
Increased rate limit to 1000 requests/hour for OAuth client registrations Not checked yet
6 details in Everything
Runlayer 1.12.0 adds a visual audit log query builder, security alert emails for admins, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. catalog integrations.
Adds a visual Query Builder UI for filtering Audit Logs Not checked yet Enables configurable Security Alert Email notifications for workspace administrators Not checked yet Adds Grain, Fireflies, Iterable, Box, and Contentful to the MCP catalog Not checked yet
3 details in Everything
Runlayer v1.10 introduces Human-in-the-Loop security review via audit logs, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. catalog extensions, and duplicate server detection.
Adds ability for admins to review, approve, or reject security violations from the audit logs Not checked yet Adds Snowflake, ClickUp, and HubSpot to the MCP catalog Not checked yet Adds duplicate server detection to warn when creating a server with a configuration that already exists Not checked yet
3 details in Everything
Runlayer 1.9.0 adds Runlayer Deploy for deploying MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers via managed infrastructure.
Runlayer v1.8.0 adds CLI deploy command, token masking scanner, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server submission settings.
Adds deploy subcommand to Runlayer CLI for deploying Docker-based services Not checked yet Introduces Token Masking Scanner that redacts sensitive tokens instead of blocking them Not checked yet
2 details in Everything
Runlayer 1.7.0 introduces policy-based access controls with advanced condition operators, OAuth refresh token refresh token A credential used to obtain a new access token without signing in again. It is sent to the authorization service rather than used directly to call the protected API. rotation, and redesigned UI pages.
Adds contains, matches, in operators for policy conditions to enforce fine-grained access control over MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. client/server attributes Not checked yet Enables automatic OAuth refresh token rotation for improved security posture Not checked yet
2 details in Everything
Runlayer 1.6.0 adds OAuth auth from MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. clients, server config drawer, and audit logs redesign.
Enables authenticating to upstream OAuth servers directly from MCP clients like ChatGPT, Claude, Cursor Not checked yet New streamlined interface for viewing and editing MCP servers in the Server Configuration Drawer Not checked yet Improved audit logs table layout and navigation Not checked yet
3 details in Everything
Runlayer 1.5.0 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Prompts support, popularity sorting, and server editing.
MCP Prompts Support with full integration for the MCP prompts specification Not checked yet Enhanced Catalog features popularity-based sorting Not checked yet Server Editing allows changing server name and description from the details page Not checked yet
3 details in Everything
Runlayer 1.4.0 adds ChatGPT and Gumloop MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. client support with improved OAuth error handling and prompt detection.
Adds ChatGPT, Gumloop, and additional AI platforms as supported MCP clients Not checked yet
1 detail in Everything
Runlayer 1.3.0 adds local MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. v2, Management API for automation, and redesigned MCP details UI.
Use local MCP servers with the same security, authz, observability and auditing as remote MCPs Not checked yet Automate server and user provisioning via REST API REST API A web API design style where clients interact with resources over HTTP using standard methods like GET, POST, and DELETE, giving cyber tools a predictable, language-agnostic way to integrate with external services. with API key authentication Not checked yet Rebuilt server details with tabbed navigation, client-specific setup instructions (Claude, Codex, others), and one-click deeplinks Not checked yet Migrated catalog to standardized MCP registry schema Not checked yet Enforced strict timeouts on all MCP operations Not checked yet
+1 more
show less
Captures stderr output, exit codes, and connection errors for faster troubleshooting of MCP server failures Not checked yet
6 details in Everything
Runlayer 1.1.3 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server integrations and non-admin analytics access.
Made analytics available for non-admin users, showing only their usage data Not checked yet
1 detail in Everything
Runlayer 1.0.0 adds SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. user/group sync and role mapping for SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management.
Adds support for syncing Users and Groups from SCIM providers. Not checked yet Adds role mapping capability to map IdP IdP A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. Groups to Runlayer roles. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! The auth_client_id Terraform variable must be updated to the new client ID provided by Runlayer support.
Runlayer 0.65.0 adds manual OAuth client configuration for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers without DCR
Adds Manual OAuth Configuration capability for MCP servers lacking Dynamic Client Registration (DCR) Not checked yet Adds a guided UI flow for automatic detection of manual setup requirements Not checked yet Updates MCP specification support to version 2025-06-18 Not checked yet
3 details in Everything
Runlayer 0.63.0 introduces Prompt Guard V2 with improved accuracy and lower latency
Adds Prompt Guard V2 as the new default prompt attack detection system in security settings UI Not checked yet
1 detail in Everything
Runlayer 0.60.12 adds dual JSON/form editing for server configuration with .env import
Runlayer 0.59.0 adds a load testing framework and per-server granular security controls with admin-only interface
Adds configurable test scenarios for load testing workloads including SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. response validation and compliance checks. Not checked yet Enables per-server security settings to override specific global scanner defaults via an Admin-only interface. Not checked yet
2 details in Everything