Is a proposed skill change safe to approve, or should it be rolled back?

shows the pending proposal in the Skill Workshop dashboard with a file preview and revision history, and keeps rollback metadata so an approved change can be reverted from the same review flow

Which agent is actually running a given task across a multi-agent plan?

tracks board runs and task comments in the Workboard so each task's owning agent and status are visible in one place

Where did an install-time script or plugin come from, and can it be trusted?

checks GitHub-backed skill installs against pinned commits and install-policy rules, and records install telemetry so a bad or unexpected install shows up after the fact

Which of my installed plugins came from the official source versus a third party?

separates externalized plugins like the Copilot runtime and Tokenjuice into their own published packages with npm and ClawHub metadata, so provenance is visible per plugin

Is a message channel still healthy after the Gateway restarts or migrates state?

keeps inbound channel queues and iMessage monitor state in SQLite so queued messages and monitor status survive a reload instead of resetting

Will my system have enough headroom after an upgrade?

runs a disk space check alongside the other post-upgrade probes and flags low space as part of that validation pass

OpenClaw release history — The Cyber Toolchain

v2026.8.33 Sep 29, 2026 · release notes

OpenClaw v2026.8.33 adds Meta Muse Spark 1.3 and Anthropic Fable 5.1 support with new Prometheus authorization

└──▷ GET THIS VERSION

$ git clone --branch v2026.8.33 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.8.33

v2026.9.3 Sep 8, 2026 · release notes

OpenClaw v2026.9.3 adds Team Reports plugin, configurable CLI agents, bounded recursive spawning, and several new capabilities with breaking changes to SDKs and Node runtime.

└──▷ GET THIS VERSION

$ git clone --branch v2026.9.3 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.9.3

└──▷ TRY IT

Limit plugin discovery docs to the first 5 results for faster iteration in large repos

$ openclaw docs --limit 5

Install the optional Team Reports plugin to browse authenticated GitHub activity and explicitly configured Discord discussion sources, with stored history, model summaries, people timelines, calendars, and coverage warnings
Set gateway.cliAgents.enabled to control whether supported create-capable CLI agents appear in the new-session model picker (enabled by default)
Enable bounded recursive session spawning by default, retaining explicit depth and concurrency limits and existing sandbox restrictions
Limit displayed terminal or JSON documentation results with openclaw docs --limit <N> in CLI and plugin discovery
Copy social-preview links for private sessions that show a generic OpenClaw card without reading private session content

+1 more show less

Publish revocable read-only views of existing and future conversation text via public session links, accessible to anyone with the URL

6 details in Everything

└──▷ BREAKING ON UPGRADE

!Node runtime requirement raised; Node 24.16.0+ on 24.x or Node 26.1.0+ required, Node 26 recommended. Node 22, 25, and earlier 24.x/26.x builds are no longer supported.
!Retired exec-mode and comparator helpers in infra-runtime; migrate to execPolicy on openclaw/plugin-sdk/agent-harness-runtime and use resolveExecModePolicy.
!Replace generic forwarding evaluator with native channel route gates; adapt session filtering to the full matchesApprovalRequestFilters contract.
!Rename channel-inbound.buildChannelTurnMediaPayload to buildChannelInboundMediaPayload and infer the result of abortAndDrainAgentHarnessRun instead of importing the removed AbortAndDrainAgentHarnessRunResult named type.
!Read bounded Find/Grep text from details.content instead of details.truncation.content in search result callbacks.
!Use LsToolDetails.content and optional nextAfter in place of retired truncation and entryLimitReached fields; pass nextAfter as after to continue listing in directory result callbacks.
!Replace workspace ownership with one writable Workshop collection per agent and retire skills.workshop.allowSymlinkTargetWrites.

v2026.9.2 Sep 5, 2026 · release notes

OpenClaw v2026.9.2 adds GPT-6 Astra support, Swarm orchestration, and cross-agent session visibility controls

└──▷ GET THIS VERSION

$ git clone --branch v2026.9.2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.9.2

Adds openai/gpt-6-astra model selection with Responses tool calls and reasoning controls via OpenAI API-key or ChatGPT/Codex accounts
Enables Swarm concurrent sub-agent orchestration by default for structured results and live progress
Exposes tools.sessions.visibility configuration key to control session access scope (all-session, agent, or self)
Adds Experimental plugin UI feature via Settings → Labs → Custom plugin UI path for Control UI pages, panels, and composer customization
Supports assets/icon.png asset location for plugin icons, replacing top-level manifest URL requirement

+1 more show less

Adds /think ultra orchestration command for OpenClaw and native Codex runtimes

6 details in Everything

v2026.9.1 Sep 3, 2026 · release notes

OpenClaw v2026.9.1 adds Mermaid diagram rendering, per-identity skill libraries, new CLI subcommands and config keys for sessions and channels.

└──▷ GET THIS VERSION

$ git clone --branch v2026.9.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.9.1

└──▷ TRY IT

Connect a channel specifically for the analyst agent

$ openclaw channels add --agent analyst telegram my_channel

Check MCP plugin status without parsing verbose logs

$ openclaw mcp --json

Configure a session to skip missed cron jobs if the gateway was down

$ openclaw config set cron.skipMissedJobs true

Adds openclaw skills library to manage personal skill libraries on shared Gateways, including import from ZIP archives.
Adds --agent flag to the channel management CLI commands (channels add/login/logout/remove/resolve).
Adds mcp --json support to emit a JSON failure envelope for machine-readable error handling.
Adds openclaw memory reset to rebuild derived memory indexes without deleting sessions.
Adds --expect-current-json, --expect-current-absent, --dry-run, and --strict-json options to the config set CLI command.

+2 more show less

Adds cron.skipMissedJobs configuration key to skip missed recurring jobs at startup.
Adds blockedHostnames SSRF policy setting to block configured hosts for browser, web fetch, and webhooks.

7 details in Everything

v2026.8.2 Sep 1, 2026 · release notes

OpenClaw v2026.8.2 adds Linux .deb/AppImage support, dockable Home UI via Cmd/Ctrl+Shift+H, standalone Chrome relay wake-up, and config tools.sessions.visibility.

└──▷ GET THIS VERSION

$ git clone --branch v2026.8.2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.8.2

Adds .deb and AppImage installers for x86-64 Linux with signature-verified AppImage updates and system tray/keyboard shortcut Quick Chat access
Adds Cmd/Ctrl+Shift+H keyboard shortcut to dock the Home agent view in a right or bottom panel without switching pages
Adds support for standalone local relays that start on demand to wake paired Chrome extensions and share browser with the Gateway
Adds tools.sessions.visibility config key (values: tree, self) to control default session visibility for unsandboxed sessions
Adds four new UI themes (CRT, Manuscript, Rosé, Miami) with offline-preserved theme choices applied without flashing on reload

+1 more show less

Adds readable /beam/ URLs named after sessions to share transcripts while preserving access checks

6 details in Everything

v2026.8.1 Aug 31, 2026 · release notes

OpenClaw v2026.8.1 adds cloud worker bootstrap, external supervisor mode, personal conversation recall, and shared credential store.

└──▷ GET THIS VERSION

$ git clone --branch v2026.8.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.8.1

└──▷ USE IT

Delegate Gateway restarts and updates to an external supervisor process.

shell

export OPENCLAW_SUPERVISOR_MODE=external

Repair configuration artifacts after upgrading past OpenProse and OpenAI route migrations.

shell

openclaw doctor --fix

Add OPENCLAW_SUPERVISOR_MODE=external environment variable to delegate Gateway lifecycle to an external process.
Add openclaw doctor --fix command to repair migration artifacts from OpenProse removal and OpenAI route updates.
Add named Cloud worker bootstrap that uses the running Gateway’s verified runtime artifact for cloud nodes.
Enable Personal conversation recall with Active Memory to retrieve bounded private context on personal installs by default.
Add Shared credential store with CLI and Settings access to manage team-scoped secrets in SQLite.

+2 more show less

Add --force requirement for arbitrary executable plugin sources in CLI or chat install to enforce provenance.
Add Incognito threads that keep Control UI transcripts and compaction state in Gateway memory until restart.

7 details in Everything

└──▷ BREAKING ON UPGRADE

!Remove the bundled OpenProse plugin and /prose command; migrate using the upstream Agent Skill migration.
!Migrate shipped codex/* and openai-codex/* model refs, provider config, stored sessions, and automation routes to openai/*.

v2026.6.33 Aug 8, 2026 · release notes

OpenClaw v2026.6.33 hardens approval authority, scopes MCP session grants, and adds extended-stable channel support.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.33 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.33

Adds extended-stable channel support so package installations can select, update from, and receive availability notices for the extended-stable release line without silently falling back to another channel.
Scopes external MCP loopback clients to short-lived session-bound attach grants instead of inheriting mutable child-process authority, limiting lateral movement from compromised MCP sessions.
Restricts narrow tool allowlists to the factory that constructs them, preventing privilege escalation through allowlist inheritance.
Ensures Gateway message actions retain trusted requester provenance and reject untrusted callers, closing an authorization bypass in action bridges.
Improves long-running agent reliability by distinguishing genuine stalls from active long model calls and wedged backends in run-release, liveness-check, and watchdog logic.

+1 more show less

Preserves SecretRef-backed Telegram credentials across service restarts, preventing credential loss on restart.

6 details in Everything

v2026.7.1 Jul 13, 2026 · issue 015

OpenClaw v2026.7.1 adds openclaw attach for Claude Code, GPT-5.6/Tencent Hy3/Muse Spark 1.1 support, guarded terminals, and a redesigned Control UI.

└──▷ GET THIS VERSION

$ git clone --branch v2026.7.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.7.1

└──▷ TRY IT

Approve an unknown sender's pairing request so they can interact with the assistant via a connected channel.

$ openclaw pairing approve <channel> <code>

Run the guided onboarding wizard to set up the gateway daemon and verify connections before saving.

$ openclaw onboard --install-daemon

Adds openclaw attach command to give Claude Code temporary access to a selected session, enabling tracked Codex delegation and native subagent workflows.
Supports GPT-5.6 across OpenAI and Codex routes, adds Tencent Hy3 with a complete setup path, and adds Meta Muse Spark 1.1 via the Meta Model API.
Introduces guarded workspace terminals accessible across web, iOS, and Android.
Enables scheduled cron jobs to wake only when something changes (change-triggered wake mode).
Supports pairing remote signed-in browser tabs and safely saving completed downloads from those tabs.

+3 more show less

Adds new onboarding flow that checks connections before saving them and preserves earlier choices when setup is interrupted.
Expands Copilot with broader provider choices.
Adds egress-time credential injection with process-local sentinels to keep secrets out of logs.

8 details in Everything

v2026.6.11 Jun 30, 2026 · release notes

OpenClaw v2026.6.11 adds per-contact model assignment, Mattermost /oc_queue slash command, and QQBot slash-command scoping controls.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.11 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.11

└──▷ TRY IT

Tune active-run queue behaviour (mode, debounce, cap, drop handling) without leaving Mattermost.

$ /oc_queue

Supports assigning different models to individual direct-message contacts across supported chat channels, while existing group and wildcard model choices continue to work.
Adds /oc_queue native slash command for Mattermost operators to tune active-run queuing mode, debounce timing, cap, and drop handling directly in Mattermost.
Enables QQBot group admins to control how broadly slash commands are available, with private-only commands directing users to a private chat instead of being exposed or silently ignored in groups.
Mattermost thread participation now persists across gateway restarts without requiring users to re-mention the bot, surviving up to seven days of thread idle time.

4 details in Everything

v2026.6.10 Jun 24, 2026 · issue 014

OpenClaw v2026.6.10 adds /fast auto mode, expanded GLM-5.2 reasoning, new catalog models, and a session-transcript SDK API for plugins.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.10 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.10

└──▷ TRY IT

Enable automatic fast mode so quick back-and-forth replies start immediately while heavier reasoning falls back to normal mode transparently.

$ /fast auto

Run a high-reasoning agent task with the newly catalogued Kimi K2.7 Code model via OpenCode Go from the CLI.

$ openclaw agent --message "Review this diff for privilege escalation risks" --thinking high

Check gateway configuration health (core checks now appear before extension checks for cleaner output).

$ openclaw doctor

Adds /fast auto command to start short conversational calls quickly, then return longer or fallback work to normal mode while keeping effective state visible.
Shows the effective automatic fast-mode state in status (not just on/off), including through fallback transitions and connected-agent sessions.
Expands zai/glm-5.2 thinking choices beyond binary on/off — high and max requests now map to the intended Z.AI reasoning effort.
Adds GLM-5.2 and Kimi K2.7 Code to the OpenCode Go model catalog so both can be selected from OpenClaw.
Adds a durable session-transcript SDK contract so plugins can read, append, publish, and lock the intended transcript without relying on legacy file paths as identity.

+2 more show less

Exposes /think level menus for live Ollama models on Telegram, Slack, and Discord, showing all supported reasoning levels instead of hiding them.
Preserves scheduled-message delivery context for the next agent turn so replies in the delivery channel know what was just sent without leaking cron metadata.

7 details in Everything

v2026.6.9 Jun 21, 2026 · issue 014

OpenClaw v2026.6.9 adds Codex Hosted Search, auto plugin approvals, OpenTelemetry log export, standalone provider npm packages, and richer Telegram delivery.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.9 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.9

└──▷ TRY IT

Install the StepFun provider plugin directly from npm so it is auto-discovered by the Gateway at next startup.

$ npm install -g openclaw-provider-stepfun
openclaw gateway status

Adds Codex Hosted Search as a new search provider available without a separate API key.
Adds automatic plugin approvals and SecretRefs for Codex integrations.
Exposes remote-node exec as a dynamic tool in Codex when a connected node is available.
Adds OpenTelemetry log export for observability pipelines.
Publishes official provider plugins as standalone npm packages; Gateway auto-discovers installed channel plugins at startup.

+4 more show less

Adds StepFun provider, installable via npm or ClawHub.
Adds a session workspace rail and extension health indicators to the Control UI.
Adds Apple Watch controls on iOS and chat context on Android.
Supports GPT-5.3 Spark OAuth routing through Codex.

9 details in Everything

v2026.6.8 Jun 16, 2026 · release notes

OpenClaw v2026.6.8 adds GLM-5.2 and Claude Haiku 4.5 support, Telegram rich-message delivery, WhatsApp ACP bindings, /btw CLI command, and built-in usage footer rendering.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.8 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.8

Adds GLM-5.2 and Claude Haiku 4.5 catalog entries with normalized provider-qualified model IDs across OpenRouter and Google Vertex paths.
Adds Telegram rich-message delivery: tables, lists, expandable blockquotes, preserved intentional line breaks, and CLI-backed replies.
Adds WhatsApp ACP binding support so configured ACP bindings are honored on delivery.
Adds /btw command support in CLI-backed sessions.
Adds built-in full footer renderer for /usage and reply payload hooks, including a default footer template, per-turn usage state, credential-aware limits, and fixed-decimal formatting for usage-bar templates.

+1 more show less

Keeps key-free web search providers (Parallel Free, DuckDuckGo, Ollama, Codex Hosted Search) as explicit opt-ins rather than automatic fallbacks when no API-backed provider is configured.

6 details in Everything

v2026.6.6 Jun 12, 2026 · release notes

OpenClaw v2026.6.6 adds OpenRouter OAuth, Claude Fable 5, QQBot group mentions, trusted diagnostics tool I/O capture, and ClawHub reusable package publishing.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.6 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.6

└──▷ TRY IT

Check for managed plugin version drift across installed ClawHub packages before a deployment.

$ openclaw doctor

Adds OpenRouter OAuth support as a new provider authentication path.
Adds Claude Fable 5 model support.
Adds QQBot group mention toggle for channel integrations.
Emits Claude CLI commentary progress events and bridges inter-tool commentary into channel progress.
Enables trusted diagnostics channels to capture tool input/output content for observability.

+9 more show less

Adds first-assistant-event tracing and slow-initial-reply warnings to the Control UI.
Supports reusable ClawHub package publishing with dry-run skip-approval option.
Moves the local llama.cpp runtime into its own provider plugin and batches embeddings across files.
Persists the agent model catalog cache to speed up startup.
Exposes the active connection host in the TUI footer.
Improves iPad and iPhone control surfaces.
Prewarms TUI runtime plugins for faster startup.
Supports declared installed trusted hooks for plugins.
Reports managed plugin version drift via the doctor command.

14 details in Everything

v2026.6.5 Jun 9, 2026 · release notes

OpenClaw v2026.6.5 adds Parallel web search, GitHub-backed ClawHub skills, native Google Chat approval cards, QMD rerank, and a QQBot @mention toggle.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.5 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.5

└──▷ TRY IT

Toggle whether your QQBot responds to group messages without an @mention, useful for dedicated bot channels that should always reply.

$ /bot-group-allways on

Adds Parallel bundled web-search plugin with API-key discovery, guarded api.parallel.ai/v1/search endpoint support, cache-safe session IDs, and onboarding integration.
Adds GitHub-backed ClawHub skill installation: downloads pinned GitHub commits, applies install-policy checks, and reports install telemetry on success.
Adds native Google Chat approval card actions and click handling so approvals use platform-native cards instead of generic message flow.
Adds /bot-group-allways on|off slash command in QQBot (with named-account and default-account support) to toggle whether group messages require an @mention before the bot replies.
Adds QMD memory search rerank toggle for more precise memory retrieval.

+2 more show less

Adds Matrix voice-message preflight and thread-aware read/reply behavior.
Adds clearer expiring, unavailable, unresolved, and attention states to Android provider/model screens.

7 details in Everything

v2026.6.1 Jun 3, 2026 · release notes

OpenClaw v2026.6.1 adds Skill Workshop, Workboard multi-agent coordination, MiniMax M3, Tailscale routing, and Android inspection commands.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.1

└──▷ TRY IT

Check disk space health alongside other system probes during post-upgrade validation.

$ openclaw doctor

Access the Skill Workshop proposal dashboard in Control UI to view, revise, and approve pending skill proposals.

📍In the Control UI, navigate to the Skill Workshop tab to view the styled dashboard, switch between the board and today views, open the revision dialog for a pending proposal, and preview support files via the file preview modal.

Adds Skill Workshop with pending proposals, CLI/Gateway review actions, rollback metadata, and the skill_workshop agent tool for governed skill lifecycle management.
Adds Control UI Skill Workshop dashboard with proposal today view, revision dialog, file preview modal, searchable preview files, and localized strings.
Adds Workboard orchestration primitives and agent coordination tools for multi-agent planning and run tracking.
Adds task-backed board runs and task comment display in the Workboard edit modal.
Adds Android installed-app inspection commands, notification picker helpers, and updated-system-app classification.

+15 more show less

Adds MiniMax M3 model support.
Supports Tailscale Serve service names for local service routing in the Gateway.
Adds a Dreaming-tab agent selector in Control UI, propagating the selected agent through Dreaming status, diary, and diary actions.
Adds disk space health checks to the Doctor command.
Externalizes Tokenjuice as the official @openclaw/tokenjuice plugin with npm and ClawHub publish metadata.
Externalizes the GitHub Copilot agent runtime as the official @openclaw/copilot plugin with npm and ClawHub publish metadata.
Adds typed presentation command actions and the bounded resolve_exec_env hook to the Plugin SDK for plugin-provided exec environment contributions.
Adds a SecretRef provider integration manifest contract for plugins.
Persists the plugin install index in SQLite so installed package lookup survives reloads without full filesystem scanning.
Stores inbound channel queues in SQLite and migrates iMessage monitor state to SQLite-backed tracking.
Adds hosted push relay defaults, realtime Talk playback, and a guarded WebSocket ping path for more reliable iOS mobile sessions.
Supports native iPad display layouts.
Adds internal namespaces for scoped agent/global sessions and exact namespace tool dispatch in Code mode.
Allows validated host-local text document media sends while keeping unsafe plain-text media sends blocked.
Adds calmer chat composer controls, local draft typing state, and first-output latency instrumentation in Control UI.

20 details in Everything

v2026.5.28 May 30, 2026 · release notes

OpenClaw v2026.5.28 adds Claude Opus 4.8, encrypted PDF extraction, GitHub Copilot agent runtime, policy conformance checks, and Workboard agent coordination tools.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.28 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.28

└──▷ TRY IT

Check the status of all running agents, including active subagent details introduced in this release.

$ openclaw status

Adds Claude Opus 4.8 as a supported provider model.
Adds GitHub Copilot agent runtime and Codex Supervisor plugin package for delegated Codex workflows.
Supports encrypted PDF extraction via ClawPDF integration.
Surfaces MCP structured content in agent tool results.
Adds Fal Krea image model schemas and NVIDIA featured model catalogs.

+11 more show less

Adds MiniMax streaming music response support.
Adds provider-backed voice model catalogs.
Adds Workboard agent coordination tools for tracking and handing off active agent work.
Adds policy comparison, ingress-channel conformance, and sandbox-posture conformance checks.
Shows active subagent details in status output.
Adds Plugin SDK reply payload sending hook for plugins that deliver channel-owned replies.
Adds ClawHub plugin display names plus skill verification and trust surfaces.
Externalizes GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata.
Shows commentary in progress drafts for live Discord runs.
Adds iOS Pro app refresh including Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback.
Expands default Diffs language coverage with a split language pack.

16 details in Everything

v2026.5.27 May 28, 2026 · release notes

OpenClaw v2026.5.27 adds native OpenAI-compatible embeddings, Pixverse video generation, full DeepInfra catalog, and plugin approval metadata.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.27 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.27

Adds a core OpenAI-compatible embedding provider supporting local and hosted OpenAI-style endpoints, with config, doctor, and docs integration.
Adds the Pixverse video generation provider with API region selection, docs, and external plugin packaging support.
Loads the full credential-aware DeepInfra model catalog when users browse models during onboarding, preserving configured API-key catalogs.
Exposes plugin approval action metadata via the Plugin SDK.
Adds plugin display metadata to ClawHub so catalog and package listings use cleaner names.

+3 more show less

Wires configured VLLM thinking params to provider requests.
Loads Claude CLI OAuth overlays for PI auth profiles.
Supports bare direct Anthropic model IDs without requiring a cached catalog.

8 details in Everything

└──▷ BREAKING ON UPGRADE

!Memory-specific embedding provider registration in the Plugin SDK is marked deprecated; non-bundled usage is now surfaced in plugin compatibility diagnostics.
!Old channel turn runtime aliases are removed from the Channel SDK.
!Vitest test helpers are no longer exported from the public Plugin SDK surface.

v2026.5.26 May 27, 2026 · release notes

OpenClaw v2026.5.26 adds transcript capture, named auth profiles, reaction approvals, QA coverage matching, and a live Activity tab.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.26 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.26

└──▷ TRY IT

Discover matching QA scenarios from existing metadata before committing to a full live or remote run — useful for scoping a proof lane to a specific feature area.

$ openclaw qa coverage --match "transcript capture"

Adds core transcript capture and source-provider support for transcript-backed meeting summaries, with a new CLI surface and cleaned user-turn persistence.
Adds named model login profiles with credential migration for Hermes, OpenCode, and Codex auth profiles, including explicit opt-out and non-interactive controls.
Adds qa coverage --match <query> subcommand for focused proof selection against existing scenario metadata before running live or remote lanes.
Adds Signal, iMessage, and WhatsApp thumb/reaction approval support so mobile approval flows work without textual /approve commands.
Adds Android pair-new-gateway action and iOS direct realtime Talk mode with compact toolbar status and responsive voice waveform feedback.

+10 more show less

Adds an alpha-bucket model picker for Discord when provider or model lists exceed 25 items, grouping entries by first-letter ranges instead of prev/next pagination.
Adds an ephemeral Activity tab in Control UI for sanitized live tool activity summaries without persisting raw telemetry.
Adds OpenTelemetry LLM content spans and alertable telemetry signals for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress.
Adds gateway secret-preparation tracing, skill/tool usage classification, and model stream progress surfacing for improved observability.
Forwards OpenAI sampling parameters through the Gateway and exposes estimated context-budget status for active agent runs.
Queues prompts submitted while an agent is busy and shows explicit fast-mode state plus richer systemd Gateway hygiene in status output.
Defaults cron.maxConcurrentRuns to 8 so scheduled automations run in parallel without explicit configuration.
Replaces the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization, removing the Sharp and WhatsApp Jimp dependencies.
Exposes shared realtime voice SDK surface for turn-context tracking, output activity tracking, consult question matching, and activation-name matching, reused across Discord, browser voice, and meeting surfaces.
Adds Plugin SDK reaction approval helpers and makes diagnostic event root exports discoverable across function-name and alias-bound module graphs.

15 details in Everything

└──▷ BREAKING ON UPGRADE

!The Sharp image backend and the WhatsApp Jimp fallback are removed; image processing now uses Rastermill, so any environment relying on Sharp being installed by OpenClaw will no longer have it.

v2026.5.22 May 24, 2026 · release notes

OpenClaw v2026.5.22 adds meeting-notes capture, 4,100× faster model listing, poll sender SDK, embedding provider API, and chat session search.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.22 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.22

└──▷ TRY IT

Access read-only meeting notes captured from Discord voice or manual transcript imports.

$ openclaw meeting-notes

Adds openclaw meeting-notes CLI with auto-start capture, manual transcript imports, and Discord voice as the first live source via a new external meeting-notes plugin.
Pre-warms provider auth-state at gateway startup, dropping /models and model-listing call cost from ~20 s to ~5 ms (~4,100× speedup).
Adds search and Load More pagination to the Control UI chat session picker so older conversations remain reachable.
Enables configurable agentComponents.ttlMs callback registry lifetime for Discord long-running component workflows, with per-account overrides and a 24-hour cap.
Adds a generic channel-message poll sender to the Plugin SDK so channel plugins can deliver polls without depending on channel-specific SDK facades.

+10 more show less

Adds a general embeddingProviders capability contract and registration API so embeddings become a reusable provider surface outside memory-specific adapters.
Adds row-level session workflow helpers to the Plugin SDK and deprecates loadSessionStore so plugins can read and patch sessions without the legacy whole-store shape.
Extends the OpenTelemetry smoke harness to prove trace, metric, and log export, and adds first-class Prometheus and observability smoke aliases.
Adds curated mock JSONL replay fixtures and first-drift reporting to QA-Lab for runtime-parity audits.
Reuses xAI OAuth auth profiles for Grok web_search, threads active-agent auth through web search, and adds Grok model aliases.
Starts classic onboarding when bare openclaw runs before an authored config exists, keeping configured installs on Crestodian.
Lazy-loads startup-idle plugin work and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees.
Ships the root npm package and OpenClaw-owned plugins with generated shrinkwrap and bundled plugin runtime dependencies, requiring review for lockfile changes.
Limits default sub-agent bootstrap context to AGENTS.md and TOOLS.md, excluding persona, identity, user, memory, heartbeat, and setup files from delegated workers by default.
Adds openclaw-landable-bug-sweep maintainer skill for producing small, reviewed, CI-green bugfix PRs from issue/PR sweeps.

15 details in Everything

└──▷ BREAKING ON UPGRADE

!Default sub-agent bootstrap context is now limited to AGENTS.md and TOOLS.md; persona, identity, user, memory, heartbeat, and setup files are no longer passed to delegated workers by default.
!Gemini CLI is no longer auto-probed for media understanding; Antigravity CLI is used only as a lower-priority image/video fallback after configured provider APIs.
!The old sender-owner tool gating path is removed; configured tools are now always visible for trusted sessions while command and channel-action auth still carry real sender identity.

v2026.5.20 May 21, 2026 · release notes

OpenClaw v2026.5.20 adds Discord voice follow, bundled Policy plugin, xAI device-code OAuth, and per-agent lean local-model mode.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.20 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.20

└──▷ USE IT

Enable lean local-model mode for a single agent in your config instead of turning it on globally.

json

# In openclaw.json
{
  "agents": {
    "list": [
      {
        "id": "my-local-agent",
        "experimental": {
          "localModelLean": true
        }
      }
    ]
  }
}

Disable auto-injected profile context files in realtime voice sessions when you want a clean, minimal system prompt.

json

# In openclaw.json
{
  "voice": {
    "realtime": {
      "bootstrapContextFiles": []
    }
  }
}

Adds Discord voice-follow: voice sessions now track configured users into channels with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation.
Adds automatic injection of bounded IDENTITY.md, USER.md, and SOUL.md profile context into realtime voice session instructions by default, configurable via voice.realtime.bootstrapContextFiles.
Adds bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair.
Adds agents.list[].experimental.localModelLean config option to enable lean local-model mode per agent instead of globally.
Adds device-code OAuth login for xAI provider, enabling authorization from remote and headless environments without a localhost browser callback.

+1 more show less

Adds provider-level params.provider routing policy support for OpenRouter requests, with model and agent params able to override defaults.

6 details in Everything

└──▷ BREAKING ON UPGRADE

!The old cat SKILL.md && printf ... && <skill-wrapper> allowlist compatibility path for exec approvals is removed; skill files must now be loaded with the read tool and only the real skill executable is auto-allowed.

v2026.5.19 May 20, 2026 · release notes

OpenClaw v2026.5.19 adds typed plugin scaffolding, Android realtime voice, global skill installs, browser dialog handling, and sweeping QA-Lab expansions.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.19 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.19

└──▷ TRY IT

Bootstrap a new typed tool plugin project with manifest generation and context factory stubs — useful when building a custom tool you want to distribute.

$ openclaw plugins init my-tool && openclaw plugins build && openclaw plugins validate

Install a skill into the shared managed location so all users on the machine can access it without per-user installs.

$ openclaw skills install <skill-name> --global

Run a long JavaScript evaluation against an open browser tab where the default timeout would expire before the script finishes.

$ openclaw browser evaluate --timeout-ms 30000 'document.querySelectorAll("a").length'

Adds defineToolPlugin plus openclaw plugins build, validate, and init for scaffolding typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
Adds --global flag to openclaw skills install and openclaw skills update so shared managed skills can be targeted without per-user installs.
Adds openclaw browser evaluate --timeout-ms to extend both the evaluate action and request timeout budgets for long-running in-page functions.
Surfaces pending and recently handled browser modal dialogs in snapshots, returns blockedByDialog when an action opens a modal, and adds browser dialog --dialog-id to answer pending dialogs.
Switches Android Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts.

+18 more show less

Adds openclaw qa suite --runtime-parity-tier to wire standard Codex-vs-Pi tier checks into release gates separately from optional/live-only/soak lanes.
Exposes runtime tool fixture coverage through openclaw qa coverage --tools with optional suite-summary evaluation for parity gate artifacts.
Adds /codex plugins list, enable, and disable for managing configured native Codex plugins from chat without editing config by hand.
Adds OPENCLAW_IMAGE_APT_PACKAGES as the runtime-neutral image build arg for extra apt packages (with OPENCLAW_DOCKER_APT_PACKAGES kept as a legacy fallback).
Adds OPENCLAW_IMAGE_PIP_PACKAGES for opt-in Python package installation in local Docker/Podman image builds.
Supports HTTPS managed forward-proxy endpoints and scoped proxy.tls.caFile CA trust for proxy endpoint TLS.
Exposes config lookup reload metadata so tools can distinguish restart-required, hot-reloadable, and no-op fields before applying config edits.
Adds Telegram allowlisted native DM draft previews for transient tool progress while keeping final answers on the normal persistent delivery path.
Adds admin HTTP RPC support for trusted clients to start and wait for web QR login flows.
Adds a meme-maker skill covering curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
Adds a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
Adds node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
Adds QA-Lab personal-agent benchmark scenarios for approval-denial, local task followthrough, share-safe diagnostics, no-fake-progress verification, and report-only dreaming shadow-trial.
Adds pnpm test:restart:gateway benchmark tooling for measuring repeated restart readiness, downtime, trace, and resource-slope evidence.
Adds QA-Lab live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing.
Adds a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow.
Redesigns Mac app Settings pages with consistent card layouts, cached navigation, and cleaner permissions/voice/skills/cron/exec/debug panes.
Adds presentation capability limits for channel renderers and adapts rich message controls before native rendering.

23 details in Everything

v2026.5.18 May 18, 2026 · release notes

OpenClaw v2026.5.18 adds a meme-maker skill, Python/node debugger skills, typed plugin SDK, HTTPS proxy support, and Android realtime voice.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.18 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.18

└──▷ TRY IT

Scaffold a new typed tool plugin from scratch and validate its generated manifest before publishing.

$ openclaw plugins init my-tool && openclaw plugins build && openclaw plugins validate

Check runtime tool fixture coverage across Codex-native, OpenClaw dynamic, and plugin-backed tools as part of a CI release gate.

$ openclaw qa coverage --tools

Answer a pending browser modal dialog by ID when an automated browser action is blocked.

$ openclaw browser dialog --dialog-id <dialog-id> --action accept

Adds defineToolPlugin plus openclaw plugins build, validate, and init commands for authoring typed simple tool plugins with generated manifest metadata and context factories.
Adds a meme-maker skill supporting curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
Adds a Python debugging skill covering pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
Adds node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
Switches Android Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts.

+12 more show less

Supports HTTPS managed forward-proxy endpoints with scoped proxy.tls.caFile CA trust for proxy endpoint TLS.
Adds OPENCLAW_IMAGE_APT_PACKAGES as a runtime-neutral image build arg for extra apt packages (Docker/Podman), keeping OPENCLAW_DOCKER_APT_PACKAGES as a legacy fallback.
Surfaces pending and recently handled modal dialogs in browser snapshots, returns blockedByDialog when an action opens a modal, and adds browser dialog --dialog-id to answer pending dialogs.
Adds openclaw qa suite --runtime-parity-tier to wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes.
Exposes runtime tool fixture coverage through openclaw qa coverage --tools with optional suite-summary evaluation for parity gate artifacts.
Allows trusted admin HTTP RPC clients to start and wait for web QR login flows.
Redesigns Mac app Settings pages with consistent card layouts, cached navigation, and cleaner permissions/voice/skills/cron/exec/debug panes.
Adds pnpm test:restart:gateway benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence.
Overlaps startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving /readyz sidecar gating.
Adds presentation capability limits for channel renderers and adapts rich message controls before native rendering.
Updates the Obsidian skill to target the official obsidian CLI and require its registered binary instead of the third-party obsidian-cli.
Renames the repo-local Codex closeout review skill and helper to autoreview while preserving the Codex-first fallback behavior.

17 details in Everything

└──▷ BREAKING ON UPGRADE

!The Obsidian skill now requires the official obsidian binary to be registered instead of the third-party obsidian-cli; setups using obsidian-cli will break.
!The repo-local Codex closeout review skill is renamed to autoreview; any config or scripts referencing the old skill name must be updated.
!The minimum supported Node.js 22 line is raised to 22.19; environments running an earlier 22.x patch will no longer be supported.

v2026.5.12 May 14, 2026 · release notes

OpenClaw v2026.5.12 adds ACP fallback backends, persisted scroll mode, leaner installs, and hardened Gateway pairing approval.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.12 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.12

└──▷ USE IT

Keep ACP sessions alive by falling back to a backup runtime when the primary backend is unavailable before any output is emitted.

yaml

# In your openclaw config
acp:
  fallbacks:
    - backend: secondary-runtime
    - backend: tertiary-runtime

Pin a remote gateway's TLS certificate explicitly for node-mode sessions so fresh endpoints fail closed without out-of-band trust.

yaml

# In your openclaw config
gateway:
  remote:
    tlsFingerprint: "sha256:AABBCC..."

Set the auto-scroll preference in WebChat/Control UI to always follow streaming output.

📍In the Control UI or WebChat, open the scroll mode selector and choose Always follow streaming output to lock the view to new content as it arrives.

Adds acp.fallbacks config so ACP turns can try configured backup runtime backends when the primary backend is unavailable before any output is emitted.
Adds a persisted auto-scroll mode selector in Control UI/WebChat: always follow streaming output, stay near-bottom, or disable auto-scroll and use the New Messages button manually.
Externalizes Amazon Bedrock, Bedrock Mantle, Slack, OpenShell sandbox, and Anthropic Vertex provider/plugin packages so core installs only pull AWS/Slack/Vertex SDK dependencies when those providers are explicitly installed.
Requires approval before exposing pending Node pairing commands, capabilities, and permissions in Gateway, and refreshes the live approved surface when pairings change.
Requires v4 Gateway clients and streams explicit chat deltaText/replace frames so SDK clients can consume assistant updates without local diffing.

+8 more show less

Requires system TLS trust before pinning a first-use direct wss:// gateway certificate on macOS, and honors gateway.remote.tlsFingerprint as an explicit pin for remote node-mode sessions.
Discovers provider plugins from setup.providers[].envVars credentials during provider discovery.
Serializes and retries semantic config mutations centrally so concurrent commands can rebase safe changes instead of clobbering each other.
Enforces inbound media size caps on download streams for Feishu, WhatsApp, and Line plugins.
Limits install-time code safety scans to plugin-owned runtime entrypoints while keeping dependency manifest denylist checks.
Classifies ACP spawn-child sessions as kind: "spawn-child" in openclaw sessions and status output.
Reports agentRuntime.id: "acpx" with source: "session-key" for ACP control-plane session rows in openclaw sessions --json, openclaw status, and Gateway session RPC responses.
Honors --no-git-update for existing git checkouts before resolving release refs, preventing pinned source installs from moving during reinstall.

13 details in Everything

└──▷ BREAKING ON UPGRADE

!Provider apiKey values are now resolved only through structured env SecretRefs (secrets.providers[id] / secrets.defaults); broad environment variable strings matching ^[A-Z_][A-Z0-9_]*$ are no longer inferred as provider credentials, which will break setups that relied on that implicit inference.
!Gateway now requires v4 clients and streams explicit deltaText/replace frames; older SDK clients that relied on local diffing of assistant updates will break.

v2026.5.4 May 5, 2026 · release notes

OpenClaw v2026.5.4 adds Gemini voice bridge for Google Meet, new auth/model/status CLI commands, OpenRouter caching, WhatsApp Newsletter targets, and tree-sitter shell explainer.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.4 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.4

└──▷ TRY IT

Audit saved per-agent auth profiles for a specific provider without exposing secret values.

$ openclaw models auth list --provider openai --json

Check Discord channel health including degraded transport and event-loop starvation signals before blaming the network.

$ openclaw status --deep

Run Slack live QA in a Crabbox VNC desktop and capture screenshots alongside QA artifacts.

$ pnpm openclaw qa mantis slack-desktop-smoke

Adds Gemini realtime voice bridge for Google Meet/Twilio dial-in with paced audio streaming, backpressure-aware buffering, and barge-in queue clearing for snappier voice agents.
Adds openclaw models auth list [--provider <id>] [--json] to inspect saved per-agent auth profiles without exposing secrets.
Adds openclaw qa mantis slack-desktop-smoke to run Slack live QA inside a Crabbox VNC desktop with screenshot capture.
Adds degraded Discord transport and gateway event-loop starvation signals to openclaw channels status and openclaw status --deep.
Adds opt-in OpenRouter response caching via X-OpenRouter-Cache, X-OpenRouter-Cache-TTL, and cache-clear headers on verified OpenRouter routes.

+18 more show less

Supports explicit WhatsApp Channel/Newsletter @newsletter outbound message targets with channel session metadata.
Adds a tree-sitter-backed shell command explainer for approval and command-review surfaces.
Adds before_agent_finalize bounded retry instructions in the Plugin SDK so workflow plugins can request one additional model pass.
Adds registerIfAbsent to the plugin runtime-state API for atomic keyed-store dedupe claims.
Adds plugin-owned SessionEntry slot projection and scoped trusted-policy session extension reads to the Plugin SDK.
Adds streaming.progress.render: "rich" for Block Kit progress drafts backed by structured progress line data in Slack.
Adds agents.defaults.toolProgressDetail: "raw" and per-agent overrides to control compact vs. raw tool summaries in /verbose and progress drafts.
Adds startup phase spans, active work labels, stale terminal bridge markers, and default sync-I/O tracing in pnpm gateway:watch for Gateway diagnostics.
Annotates ClawHub 429 errors with the reset window from RateLimit-Reset/Retry-After and appends a sign-in hint for unauthenticated requests.
Supports drive-absolute Docker bind sources on Windows sandbox while keeping blocked-path and allowed-root policy comparisons case-insensitive.
Advertises Codex audio transcription in runtime and manifest metadata, routing active Codex chat models to the OpenAI transcription default.
Preserves realtime.introMessage: "" so realtime Chrome joins can stay silent instead of restoring the default spoken intro.
Adds an agent-first filter to the Control UI chat session picker with responsive layout across phone/tablet/desktop widths.
Collapses consecutive duplicate text messages in the Control UI chat into one bubble with a count.
Makes the New Job sidebar in the Control UI cron view collapsible to reclaim space for the jobs list.
Shows the active agent name in Control UI dashboard breadcrumbs.
Records browser long animation frame or long task entries in the debug event log for slow dashboard render attribution.
Expands OpenRouter app-attribution categories to include coding, programming, writing, chat, and personal-agent usage on verified routes.

23 details in Everything

v2026.5.3 May 4, 2026 · release notes

OpenClaw v2026.5.3 adds a bundled file-transfer plugin, /steer command, WhatsApp Newsletter targets, and unified streaming progress drafts.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.3 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.3

└──▷ TRY IT

Steer a running agent session mid-flight without queuing a new turn — useful when you want to redirect the active run interactively.

$ /steer focus only on the authentication module and skip the database layer

Inspect installed plugins and their npm dependency state to audit which packages are fully resolved vs. broken.

$ openclaw plugins list --json

Adds bundled file-transfer plugin with file_fetch, dir_list, dir_fetch, and file_write agent tools for binary file operations on paired nodes, with default-deny per-node path policy, symlink traversal off by default (opt-in followSymlinks), and a 16 MB per-round-trip ceiling.
Adds /steer <message> command for queue-independent steering of the active current-session run without starting a new turn when the session is idle.
Adds /side as a text and native slash-command alias for /btw side questions.
Adds unified streaming.mode: "progress" drafts with auto single-word status labels and shared progress configuration across Discord, Telegram, Matrix, Slack, and Microsoft Teams.
Supports explicit WhatsApp Channel/Newsletter @newsletter outbound message targets with channel session metadata instead of DM routing.

+9 more show less

Adds trackToolCalls: true option on explicit Discord reaction tool calls to opt into tracking subsequent tool progress on the reacted message.
Adds tree-sitter-backed shell command explainer for approval and command-review surfaces.
Includes package dependency install state in openclaw plugins list --json output.
Annotates ClawHub 429 errors with reset windows and unauthenticated higher-rate-limit hints so operators can tell when downloads recover and when signing in helps.
Stores sandbox container and browser registry entries as per-runtime shard files, reducing unrelated session lock contention.
Adds pnpm openclaw qa mantis discord-smoke runner and manual GitHub workflow to verify Mantis Discord bot connectivity, smoke posting, reactions, and artifact upload.
Adds a Slack live transport QA runner with canary and mention-gating coverage.
Exposes the external Codex plugin as a selectable provider setup choice in Manual setup onboarding.
Tries plugin @beta updates first on the beta OpenClaw channel, falling back to default/latest when no plugin beta release exists.

14 details in Everything

└──▷ BREAKING ON UPGRADE

!Gateway startup and hot reload no longer auto-restore invalid config; invalid config now fails closed and requires openclaw doctor --fix to repair.

v2026.5.2 May 2, 2026 · release notes

OpenClaw v2026.5.2 adds git-based plugin installs, ClawHub search, proxy validation, Google Meet captions, and a structured heartbeat tool.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.2

└──▷ TRY IT

Verify proxy configuration and destination reachability before rolling out proxy-routed OpenClaw commands in a restricted network.

$ openclaw proxy validate

Force a Gateway restart immediately and wait up to 60 seconds for it to come back, useful in automated deployment scripts.

$ openclaw gateway restart --force --wait 60s

Adds openclaw gateway restart --force and --wait <duration> flags, with active task run ID logging before restart deferral and explicit forced-restart reporting.
Adds first-class git: plugin installs with ref checkout, commit metadata, scanner/staging, and plugins update support for recorded git sources.
Adds ClawHub plugin search plus Crestodian plugin list/search/install/uninstall operations with approval and audit coverage.
Adds openclaw proxy validate so operators can verify effective proxy configuration, reachability, and allow/deny behavior before deploying proxy-routed commands.
Includes package dependency install state in openclaw plugins list --json so scripts can detect missing plugin dependencies without runtime-loading plugins.

+21 more show less

On the beta update channel, plugin updates now try @beta first and fall back to default/latest when no plugin beta release exists.
Adds Grok 4.3 to the bundled xAI catalog and makes it the default xAI chat model.
Adds googlemeet end-active-conference command for closing managed Google Meet spaces after a call.
Adds googlemeet test-listen command and matching google_meet test_listen action so transcribe-mode joins wait for real caption or transcript movement before reporting listen-first health.
Adds live caption health monitoring for Chrome transcribe mode in Google Meet, including caption observer state, transcript counters, last caption text, and recent transcript lines in status and doctor output.
Adds SDK-facing tools.invoke RPC with shared HTTP policy, typed approval/refusal results, and SDK helper support.
Adds extraBody/extra_body passthrough for OpenAI-compatible TTS endpoints, enabling custom fields such as lang in /audio/speech requests.
Adds structured heartbeat_respond tool for tool-capable heartbeat runs so agents can record quiet outcomes or explicit notification text.
Adds agents.defaults.skipOptionalBootstrapFiles config key for skipping selected optional workspace files during bootstrap without disabling required workspace setup.
Adds UTC quarter-hour token buckets for the Usage Mosaic in Control UI with reuse for hour filtering.
Adds opt-in channels.bluebubbles.replyContextApiFallback for fetching original messages from the BlueBubbles HTTP API on reply-context cache misses, with SSRF protection and concurrent-request coalescing.
Adds accessGroup:<name> reusable message-channel access groups for Discord channel-audience DM authorization so allowlists can reference named groups across channel auth paths.
Supports explicit WhatsApp Channel/Newsletter @newsletter outbound message targets with channel session metadata.
Allows $include directives in Gateway config to read files from operator-approved OPENCLAW_INCLUDE_ROOTS directories.
Adds a platform-level tool descriptor planner and caches plugin tool descriptors from api.registerTool(...) so repeated prompt-time planning skips plugin runtime loading.
Adds a fast path for canonical absolute POSIX containment checks in hot filesystem walkers, avoiding repeated path.resolve and path.relative work.
Externalizes ACPX behind @openclaw/acpx and diagnostics OpenTelemetry behind @openclaw/diagnostics-otel, keeping heavier runtime stacks out of core until installed.
Keeps active Discord buttons, selects, and forms working across Gateway restarts until they expire, preserving multi-step interactions during upgrades.
Publishes a safe default Slack App Home tab view on app_home_opened and tracks bot-participated threads across restarts so threaded conversations continue auto-replying after Gateway restarts.
Moves macOS menu bar companion recent session context rows into a Context submenu while keeping usage and cost details root-level for compactness.
Loads bundled plugins from the extensions/* pnpm workspace tree in source checkouts so plugin-local dependencies and edits are used directly.

26 details in Everything

└──▷ BREAKING ON UPGRADE

!The split subagent/ACP thread-spawn toggles are replaced by threadBindings.spawnSessions; thread-bound spawns now default on. Run openclaw doctor --fix to migrate the legacy keys.

v2026.4.29 Apr 30, 2026 · release notes

OpenClaw v2026.4.29 adds NVIDIA provider, people-aware memory wiki, opt-in follow-up commitments, OpenGrep scanning, and SQLite plugin state store.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.29 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.29

└──▷ USE IT

Enable opt-in follow-up commitments with a daily cap so the agent proactively follows up on action items via heartbeat.

yaml

commitments.enabled: true
commitments.maxPerDay: 5

Restrict Active Memory recall to specific direct-message conversations, keeping broad group sessions skipped.

yaml

memory:
  active:
    allowedChatIds:
      - "dm:alice"
      - "dm:bob"

Adds NVIDIA provider with API-key onboarding, static catalog metadata, and literal model-ref picker so NVIDIA hosted models can be selected with their provider prefix intact.
Adds agent-facing people wiki with canonical aliases, person cards, relationship graphs, privacy/provenance reports, evidence-kind drilldown, and search modes for person lookup, question routing, source evidence, and raw claims.
Adds opt-in inferred follow-up commitments with hidden batched extraction, per-agent/per-channel scoping, heartbeat delivery, CLI management, and commitments.enabled/commitments.maxPerDay config.
Introduces steer as the default active-run queue mode, draining all pending steering messages at the next model boundary, with a 500ms followup fallback debounce; legacy one-at-a-time steering remains available as queue.
Adds global messages.visibleReplies so operators can require visible output to go through message(action=send) for any source chat, with messages.groupChat.visibleReplies as the group/channel override.

+11 more show less

Surfaces spawnedBy on subagent chat and agent broadcast payloads so clients can route child session events without an extra session lookup.
Adds optional per-conversation allowedChatIds and deniedChatIds filters to Active Memory so recall can be scoped to selected conversations.
Returns bounded partial recall summaries when the hidden memory sub-agent times out, including the default temporary-transcript path, so recovered context is not discarded.
Adds read-only doctor.memory.remHarness RPC so operator clients can preview bounded REM dreaming output without running mutation paths.
Adds SQLite-backed plugin state store (api.runtime.state.openKeyedStore) for restart-safe keyed registries with TTL, eviction, and automatic plugin isolation.
Adds OPENCLAW_SKIP_ONBOARDING environment variable so automated Docker installs can skip interactive onboarding while still applying gateway defaults.
Adds OpenGrep rulepack, source-rule compiler, provenance metadata check, and PR/full scan workflows that upload SARIF to GitHub Code Scanning.
Adds opt-in startup diagnostics timeline that records gateway lifecycle and plugin-load phases behind a config flag for slow-start diagnosis.
Extends Control UI locale registry with Persian (fa), Dutch (nl), Vietnamese (vi), Italian (it), Arabic (ar), and Thai (th) entries.
Adds Tencent Yuanbao channel to the channel listing and sidebar navigation.
Runs pnpm gateway:watch through a named tmux session by default, with gateway:watch:raw and OPENCLAW_GATEWAY_WATCH_TMUX=0 for foreground mode.

16 details in Everything

└──▷ BREAKING ON UPGRADE

!Configured tool sections (tools.exec, tools.fs) no longer implicitly widen restrictive profiles (messaging, minimal); users who need those tools under a restricted profile must add explicit alsoAllow entries — a startup warning identifies affected configs.

v2026.4.27 Apr 29, 2026 · release notes

OpenClaw v2026.4.27 adds Codex Computer Use, DeepInfra provider, QQBot group chat, outbound proxy routing, and GPU passthrough for sandboxed agents.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.27 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.27

└──▷ TRY IT

Route all agent outbound traffic through a corporate forward proxy at startup.

$ OPENCLAW_PROXY_URL=http://proxy.corp.example.com:8080 openclaw start

Enable GPU passthrough so a sandboxed agent can run local GPU workloads inside Docker.

yaml

# In your OpenClaw config:
sandbox:
  docker:
    gpus: all

Adds /codex computer-use status/install commands plus marketplace discovery, optional auto-install, and fail-closed MCP server checks before Codex-mode desktop-control turns start.
Adds bundled DeepInfra provider with DEEPINFRA_API_KEY onboarding, dynamic OpenAI-compatible model discovery, image generation/editing, image/audio media understanding, TTS, text-to-video, and memory embeddings.
Adds Tencent Yuanbao channel plugin (openclaw-plugin-yuanbao) with WebSocket bot DMs, group chats, and a new docs/channels/yuanbao.md quick-start guide.
Adds full QQBot group chat support: history tracking, @-mention gating, activation modes, per-group config, FIFO message queue with deliver debounce, C2C streaming via StreamingController, and chunked sendMedia for large files.
Adds opt-in operator-managed outbound proxy routing via proxy.enabled + proxy.proxyUrl / OPENCLAW_PROXY_URL with strict http:// forward-proxy validation and loopback-only Gateway bypass.

+9 more show less

Adds opt-in sandbox.docker.gpus passthrough so local GPU workloads can run inside Docker sandbox containers when the host runtime supports --gpus.
Adds node.presence.alive authenticated protocol event and node.list last-seen fields so background iOS and Android wakes mark paired nodes recently alive without treating them as connected.
Accepts non-image attachments through chat.send by staging them as agent-readable media paths instead of silently dropping files.
Adds streaming.preview.toolProgress: false config flag to hide interim tool lines in live Matrix preview edits while keeping answer previews.
Adds generic host hooks in Plugin SDK for session state, next-turn context, trusted tool policy, UI descriptors, events, scheduler cleanup, and run-scoped plugin context.
Exposes shared channel route normalization, parser-driven target resolution, raw-target compact keys, parsed-target types, and route comparison helpers through openclaw/plugin-sdk/channel-route.
Wires manifest modelCatalog.aliases and modelCatalog.suppressions into model-catalog planning and built-in model suppression, enabling provider rows/aliases/suppressions to be declared in plugin manifests.
Adds plugin compatibility warnings for deprecated implicit startup loading so plugin authors can migrate to explicit activation.onStartup metadata.
Attaches versioned structured approval metadata to pending Matrix approval messages so capable clients can render richer approval UI.

14 details in Everything

v2026.4.26 Apr 28, 2026 · release notes

OpenClaw v2026.4.26 adds Matrix E2EE setup, a new migrate command, Cerebras provider, and asymmetric embedding config.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.26 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.26

└──▷ TRY IT

Set up Matrix end-to-end encryption, bootstrap recovery keys, and verify status in one command.

$ openclaw matrix encryption setup

Preview a migration from Hermes before committing — useful before upgrading a production agent config.

$ openclaw migrate --dry-run --json

Configure asymmetric embeddings so queries and documents use different input types on an OpenAI-compatible memory backend.

yaml

memorySearch:
  inputType: query
  queryInputType: query
  documentInputType: document

Adds openclaw matrix encryption setup to enable Matrix E2EE, bootstrap recovery, and print verification status in a single flow.
Adds openclaw migrate with plan, dry-run, JSON output, pre-migration backup, onboarding detection, and a bundled Hermes importer for config, memory, plugins, model providers, MCP servers, skills, and credentials.
Adds a bundled Claude importer to preview and apply Claude Code and Claude Desktop instructions, MCP servers, skills, command prompts, and archived state.
Adds Cerebras as a bundled provider plugin with onboarding, static model catalog, docs, and manifest-owned endpoint metadata.
Adds optional memorySearch.inputType, queryInputType, and documentInputType config for asymmetric embedding endpoints on OpenAI-compatible memory backends.

+7 more show less

Adds model-specific retrieval query prefixes for nomic-embed-text, qwen3-embedding, and mxbai-embed-large in Ollama memory-search queries.
Adds a raw config pending-changes diff panel in Control UI that parses JSON5 and redacts sensitive values until revealed.
Adds opt-in agents.defaults.compaction.maxActiveTranscriptBytes preflight trigger to run local compaction when active JSONL grows too large.
Adds openclaw nodes remove --node <id|name|ip> and node.pair.remove to clean stale gateway-owned node pairing records.
Adds a generic browser realtime transport contract, Google Live browser Talk sessions with constrained ephemeral tokens, and a Gateway relay for backend-only realtime voice plugins.
Moves model-id normalization, provider endpoint host metadata, and OpenAI-compatible request-family hints into plugin manifests, removing bundled-provider routing tables from core.
Allows OPENCLAW_PLUGIN_STAGE_DIR to contain layered runtime-dependency roots, resolving read-only preinstalled deps before installing missing deps into the writable root.

12 details in Everything

└──▷ BREAKING ON UPGRADE

!Direct plugin config load/write helpers are deprecated in favor of passed runtime snapshots and transactional mutation helpers with explicit restart follow-up policy; existing callers must migrate to the new snapshot-based API.

v2026.4.25 Apr 27, 2026 · release notes

OpenClaw v2026.4.25 adds TTS overhaul with 6 new providers, expanded OpenTelemetry coverage, browser automation upgrades, PWA/Web Push, and new plugin registry CLI commands.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.25 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.25

└──▷ TRY IT

Toggle auto-TTS on for the current chat session so all replies are read aloud, then turn it off when done.

$ /tts chat on
# ... chat session ...
/tts chat off

Launch a headless browser for a one-shot automation task without touching your saved browser config.

$ openclaw browser start --headless

Inspect the persisted plugin registry and force a refresh to repair stale entries after an upgrade.

$ openclaw plugins registry --refresh

Adds /tts latest read-aloud command and /tts chat on|off|default session-scoped auto-TTS controls for WhatsApp and chat channels.
Adds Azure Speech as a bundled TTS provider with Speech-resource auth, SSML escaping, native Ogg/Opus voice-note output, and telephony output.
Enables per-agent TTS voice overrides via agents.list[].tts and per-account deep-merge of channels.<channel>.accounts.<id>.tts for Feishu and QQBot.
Adds channels.discord.voice.model config key to override the LLM used for Discord voice channel responses.
Adds Google Meet calendar-backed attendance export workflows, export manifests, and dry-run previews.

+15 more show less

Adds PWA install support and Web Push notifications for Gateway chat in the Control UI.
Adds openclaw browser start --headless for one-shot local managed browser launch without modifying persisted browser config.
Adds openclaw browser doctor --deep for live CDP role-snapshot probing on slow hosts, with iframe-aware refs and cursor-clickable detection.
Exposes --background flag on openclaw infer image generate and openclaw infer image edit (with --openai-background as an OpenAI-specific alias), plus --output-format png|jpeg for fal image generation.
Adds openclaw plugins registry command for explicit persisted-registry inspection and --refresh repair.
Adds before-agent-finalize plugin hooks, cron jobId hook context, bounded native permission fingerprints, and Codex MCP hook relay support.
Adds metadata-only model_call_started and model_call_ended plugin hooks for provider/model call telemetry.
Adds a bundled diagnostics-prometheus plugin with a protected gateway scrape route for low-cardinality diagnostics metrics.
Emits OpenTelemetry openclaw.harness.run spans and openclaw.harness.duration_ms metrics for agent harness lifecycle telemetry.
Exports openclaw.tool.loop counters and spans, openclaw.context.assembled spans, and bounded memory histograms/pressure spans via OTEL.
Adds GenAI gen_ai.client.token.usage histogram and gen_ai.client.operation.duration histogram for model usage and latency tracking.
Supports signal-specific OTLP endpoint overrides for traces, metrics, and logs via config or standard OTEL environment variables.
Propagates W3C traceparent headers from trusted model-call trace context to provider transports.
Adds bounded openclaw.agent label to OpenClaw token metrics for per-agent Grafana dashboard grouping.
Adds first-run TUI setup helper, local planner fallback, full-TUI interactive Crestodian, startup progress indicators, and context mode selector.

20 details in Everything

└──▷ BREAKING ON UPGRADE

!Managed plugin install metadata consolidates into plugins/installs.json, replacing plugins/installed-index.json; plugins.installs is no longer an authored config surface.
!OPENCLAW_DISABLE_PERSISTED_PLUGIN_REGISTRY is now a deprecated break-glass switch; operators should use registry repair instead.

v2026.4.24 Apr 25, 2026 · release notes

OpenClaw v2026.4.24 adds Google Meet, DeepSeek V4, realtime voice loops, coordinate-click browser automation, and OTEL diagnostics.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.24 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.24

└──▷ TRY IT

Verify Twilio/provider readiness before placing a live voice test call — the smoke command is dry-run by default.

$ openclaw voicecall smoke

Click a specific viewport coordinate during headless browser automation, useful when element selectors are unavailable.

$ openclaw browser click-coords 640 480

Recover an already-open Google Meet tab so the agent can inspect it without opening a duplicate, and check OAuth health.

$ openclaw googlemeet doctor --oauth

Establish full cross-signing identity trust for self-device verification on a Matrix deployment.

$ openclaw matrix verify self

Adds a bundled Google Meet participant plugin with personal Google auth, Chrome/Twilio realtime transports, paired-node chrome-node support, artifact/attendance exports, and googlemeet doctor --oauth / recover-tab recovery tooling.
Adds DeepSeek V4 Flash and V4 Pro to the bundled model catalog; V4 Flash becomes the new onboarding default.
Enables realtime voice loops backed by the full OpenClaw agent (openclaw_agent_consult) in Talk, Voice Call, and Google Meet sessions.
Adds a Gemini Live realtime voice provider for Voice Call and Google Meet audio bridges, with bidirectional audio and function-call support.
Adds a Gateway realtime brain WebSocket endpoint backed by Gemini Live, with owner-auth gating and async OpenClaw tool handoff.

+19 more show less

Adds viewport coordinate-click support for browser automation, accessible via openclaw browser click-coords for CLI use.
Adds browser.actionTimeoutMs config with a 60-second default action budget to prevent healthy long browser waits from timing out.
Supports per-profile browser.profiles.<name>.headless overrides so individual browser profiles can run headless independently.
Adds voicecall setup and a dry-run-by-default voicecall smoke command to verify Twilio/provider readiness before a live call.
Adds openclaw matrix verify self to establish full cross-signing identity trust for self-device verification from the CLI.
Adds a bundled Gradium text-to-speech provider with voice-note and telephony output support.
Exposes raw vectorScore and textScore alongside the combined score on hybrid memory search results for retrieval contribution inspection.
Adds agents.defaults.contextInjection: "never" config option to disable workspace bootstrap file injection for agents that fully own their prompt lifecycle.
Adds disabled-by-default gateway.nodes.pairing.autoApproveCidrs for automated first-time node pairing from explicit trusted CIDRs.
Exports run, model-call, and tool-execution lifecycle events as OTEL spans, with opt-in diagnostics.otel.captureContent controls for content attributes.
Refines the agent Tool Access panel with compact live-tool chips, collapsible tool groups, direct per-tool toggles, and runtime/source provenance display.
Adds a Steer action on queued chat messages so a browser follow-up can be injected into the active run without retyping it.
Adds a modelCatalog plugin manifest contract for provider-owned model rows, aliases, and suppression rules without loading plugin runtime.
Moves local PDF extraction into a bundled document-extract plugin, decoupling pdfjs-dist from core.
Moves Bonjour LAN Gateway discovery advertising into a default-enabled bundled plugin so users can disable it without affecting wide-area discovery.
Adds a central plugin compatibility registry with dated migration metadata for SDK/config/setup/runtime deprecation records.
Speeds up openclaw models list with static catalogs for bundled providers and narrower registry enumeration.
Lets Gemini TTS prepend configured audioProfile and speakerName prompt text for reusable speech-style control.
Exposes activation plan reasons and a richer plan API so callers can inspect why a plugin was selected.

24 details in Everything

└──▷ BREAKING ON UPGRADE

!The Pi-only api.registerEmbeddedExtensionFactory(...) compatibility path is removed; bundled tool-result rewrites must now use api.registerAgentToolResultMiddleware(...) with contracts.agentToolResultMiddleware declaring the targeted harnesses.

v2026.4.23 Apr 24, 2026 · release notes

OpenClaw v2026.4.23 adds image generation via OpenAI/OpenRouter, per-call generation timeouts, forked subagent contexts, and tunable local embedding context size.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.23 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.23

Adds image generation and reference-image editing for openai/gpt-image-2 via Codex OAuth, eliminating the need for a separate OPENAI_API_KEY.
Adds image generation and reference-image editing for OpenRouter image models via the image_generate tool using OPENROUTER_API_KEY.
Enables agents to pass provider-supported quality, output format, background, moderation, compression, and user hints through the image_generate tool.
Adds optional forked context for native sessions_spawn runs so child agents can inherit the requester transcript while keeping isolated sessions as the default.
Adds optional per-call timeoutMs support for image, video, music, and TTS generation tools so agents can extend provider request timeouts on a per-generation basis.

+2 more show less

Adds configurable memorySearch.local.contextSize (default 4096) so local embedding contexts can be tuned for constrained hosts without patching the memory host.
Adds structured debug logging for embedded harness selection decisions in gateway logs, keeping /status clean while explaining auto-selection and Pi fallback reasons.

7 details in Everything

v2026.4.22 Apr 23, 2026 · release notes

OpenClaw v2026.4.22 adds xAI multimodal support, new STT providers, /models add command, WhatsApp reply quoting, and a local embedded TUI mode.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.22 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.22

└──▷ TRY IT

Register a newly released model from an active chat session without restarting the gateway.

$ /models add xai grok-imagine-image-pro

Adds xAI image generation (grok-imagine-image, grok-imagine-image-pro), reference-image edits, text-to-speech (six voices, MP3/WAV/PCM/G.711), and grok-stt audio transcription including realtime Voice Call streaming.
Adds Voice Call streaming transcription for Deepgram, ElevenLabs, and Mistral; ElevenLabs also gains Scribe v2 batch audio transcription for inbound media.
New local embedded TUI mode lets you run terminal chats without a Gateway while keeping plugin approval gates enforced.
Onboarding now auto-installs missing provider and channel plugins so first-run setup completes without manual plugin recovery.
OpenAI Responses models automatically use OpenAI's native web_search tool when web search is enabled and no managed search provider is pinned.

+23 more show less

New /models add <provider> <modelId> command lets you register a model from chat and use it without restarting the gateway.
Adds configurable native reply quoting via replyToMode for WhatsApp conversations.
Adds per-group and per-direct systemPrompt config for WhatsApp, injected as GroupSystemPrompt context on every turn, with "*" wildcard fallback and account-scoped overrides.
Adds mailbox-style sessions_list filters for label, agent, and search, plus visibility-scoped derived titles and last-message previews.
Adds a browser-local personal identity (name plus avatar) for the operator in the Control UI.
Enables payload-free stability recording by default and adds a support-ready diagnostics export with sanitized logs, status, health, config, and stability snapshots.
Adds the bundled Tencent Cloud provider plugin with TokenHub onboarding, hy3-preview model catalog, and tiered Hy3 pricing metadata.
Adds Claude Opus 4.7 via Amazon Bedrock Mantle's Anthropic Messages route with provider-owned bearer-auth streaming.
Moves GPT-5 prompt overlay into the shared provider runtime; adds agents.defaults.promptOverlays.gpt5.personality as a global friendly-style toggle.
Removes the Codex CLI auth import path (~/.codex) from onboarding; browser login or device pairing replaces it.
Defaults claude-cli runs to warm stdio sessions and resumes from stored Claude session after Gateway restarts or idle exits.
Adds bundled native tokenjuice support as an opt-in plugin that compacts noisy exec and bash tool results in Pi embedded runs.
Adds openClawToolsMcpBridge option that injects a core OpenClaw MCP server for selected built-in tools, starting with cron.
Adds an opt-in debug timing helper for local CLI performance investigations with readable stderr output and JSONL capture.
Marks known local backends (vLLM, SGLang, llama.cpp, LM Studio, LocalAI, Jan, TabbyAPI, text-generation-webui) as streaming-usage compatible for accurate token accounting.
Adds an explicit Runner: field to /status so sessions report whether they run on embedded Pi, a CLI-backed provider, or an ACP harness agent.
Adds Thai translation support for the docs site.
Reduces doctor --non-interactive runtime by ~74% via lazy-loading of doctor plugin paths.
Cuts bundled plugin load time by 82–90% via native Jiti loading for built plugin dist modules.
Adds a bundled-plugin embedded extension factory seam so native plugins can extend Pi embedded runs with async tool_result hooks.
Routes native Codex app-server turns through before_prompt_build, before_compaction, after_compaction, llm_input, llm_output, and agent_end lifecycle hooks.
Adds a bundled-plugin Codex app-server extension seam for async tool_result middleware and fires after_tool_call for Codex tool runs.
Records per-scenario reply RTT in the live Telegram QA report and summary.

28 details in Everything

└──▷ BREAKING ON UPGRADE

!The Codex CLI auth import path (~/.codex) is removed from onboarding and provider discovery; OpenClaw no longer copies OAuth material from ~/.codex into agent auth stores — use browser login or device pairing instead.

v2026.4.20 Apr 21, 2026 · release notes

OpenClaw v2026.4.20 adds Mattermost live-draft streaming, QA CLI failure gates, cron state splitting, group-aware BlueBubbles prompts, and Kimi K2.6 defaults.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.20 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.20

└──▷ TRY IT

Fail a CI pipeline immediately when QA scenarios fail, without needing extra flags — use --allow-failures only for artifact collection runs.

$ openclaw qa suite --allow-failures

Adds Mattermost live-draft preview: streams thinking, tool activity, and partial reply text into a single draft post that finalizes in place.
Adds openclaw qa suite and openclaw qa telegram failure-by-default mode with --allow-failures flag for artifact-only CI runs.
Splits cron runtime state into jobs-state.json so jobs.json remains stable for git-tracked job definitions.
Forwards per-group systemPrompt config into GroupSystemPrompt context for BlueBubbles, with "*" wildcard fallback, so group-specific behavioral instructions are injected on every turn.
Adds opt-in start and completion notices during agent context compaction.

+7 more show less

Defaults bundled Moonshot surfaces (setup, web search, media understanding) to kimi-k2.6, with kimi-k2.5 remaining available for compatibility.
Allows thinking.keep = "all" on moonshot/kimi-k2.6, stripping it for other Moonshot models or when pinned tool_choice disables thinking.
Adds tiered model pricing support from cached catalogs and configured models, including bundled Moonshot Kimi K2.6/K2.5 cost estimates for token-usage reports.
Adds detached runtime registration contract so plugin executors can own detached task lifecycle and cancellation independently of core task internals.
Strengthens default system prompt and OpenAI GPT-5 overlay with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance.
Adds configurable channels.telegram.pollingStallThresholdMs (also per-account) to tune the polling watchdog threshold.
Adds configurable channels.bluebubbles.sendTimeoutMs (also per-account) with a raised default outbound send timeout of 30s.

12 details in Everything

└──▷ BREAKING ON UPGRADE

!Session entry cap and age pruning are now enforced by default; existing deployments with large accumulated session stores will have those stores pruned at load time on upgrade.

v2026.4.15 Apr 16, 2026 · release notes

OpenClaw v2026.4.15 adds Gemini TTS, GitHub Copilot embeddings, LanceDB cloud storage, and a Model Auth status card.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.15 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.15

└──▷ USE IT

Opt back in to legacy inline dreaming storage if your workflow depends on phase blocks appearing inside daily memory files.

yaml

plugins:
  entries:
    memory-core:
      config:
        dreaming:
          storage:
            mode: "inline"

Adds Gemini text-to-speech support to the bundled google plugin, with voice selection, WAV reply output, and PCM telephony output.
Adds a Model Auth status card in Control UI/Overview showing OAuth token health and provider rate-limit pressure, with expiry callouts, backed by a new models.authStatus gateway method.
Adds GitHub Copilot as an embedding provider for memory search, with a dedicated Copilot embedding host helper for plugin reuse.
Adds cloud storage support to memory-lancedb so durable memory indexes can run on remote object storage instead of local disk only.
Adds experimental agents.defaults.experimental.localModelLean: true to drop heavyweight default tools (browser, cron, message) and reduce prompt size for weaker local-model setups.

+1 more show less

Bundles Claude Opus 4.7 as the new default Anthropic model selection, including opus aliases and image understanding.

6 details in Everything

└──▷ BREAKING ON UPGRADE

!The default dreaming.storage.mode changes from inline to separate, so Dreaming phase blocks (## Light Sleep, ## REM Sleep) now land in memory/dreaming/{phase}/YYYY-MM-DD.md instead of memory/YYYY-MM-DD.md. Operators who want the previous behavior must explicitly set plugins.entries.memory-core.config.dreaming.storage.mode: "inline".

v2026.4.14 Apr 14, 2026 · release notes

OpenClaw v2026.4.14 adds forward-compat support for GPT-5.4-pro and surfaces human Telegram forum topic names in agent context.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.14 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.14

Adds forward-compat support for gpt-5.4-pro (OpenAI Codex family), including Codex pricing/limits and list/status visibility before the upstream catalog catches up.
Surfaces human Telegram forum topic names in agent context, prompt metadata, and plugin hook metadata by learning names from Telegram forum service messages.

2 details in Everything

v2026.4.12 Apr 13, 2026 · release notes

OpenClaw v2026.4.12 adds Active Memory sub-agent, LM Studio & Codex providers, MLX speech, exec-policy CLI, and Matrix live markers.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.12 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.12

└──▷ TRY IT

Inspect or lock down which exec tools are approved locally — useful before deploying to a shared or locked-down environment.

$ openclaw exec-policy show
openclaw exec-policy preset strict
openclaw exec-policy set tools.exec.shell false

Run a QA scenario suite inside a throwaway Linux VM so tests cannot pollute your host and results are written back automatically.

$ openclaw qa suite --runner multipass

New Active Memory plugin runs a dedicated memory sub-agent before each reply, auto-surfacing relevant preferences and past context with configurable message/recent/full context modes, live /verbose inspection, and opt-in transcript persistence.
New bundled LM Studio provider supports onboarding, runtime model discovery, stream preload, and memory-search embeddings for local/self-hosted OpenAI-compatible models.
New bundled Codex provider routes codex/gpt-* models through Codex-managed auth, native threads, model discovery, and compaction while keeping openai/gpt-* on the standard OpenAI path.
New openclaw exec-policy command with show, preset, and set subcommands for synchronizing tools.exec.* config with the local exec approvals file.
New commands.list RPC on the Gateway lets remote clients discover runtime-native, text, skill, and plugin commands with surface-aware naming and serialized argument metadata.

+6 more show less

New per-provider models.providers.*.request.allowPrivateNetwork setting enables trusted self-hosted OpenAI-compatible endpoints without broadening global network policy.
New --runner multipass lane for openclaw qa suite runs repo-backed QA scenarios inside a disposable Linux VM and writes back report, summary, and VM logs.
New openclaw qa credentials admin commands and Convex-backed pooled Telegram credential leasing for lab/QA environments.
New openclaw qa telegram lane adds live private-group bot-to-bot checks with hardened artifact handling and native Telegram command reply threading.
Experimental local MLX speech provider for Talk Mode on macOS with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback.
Matrix integration now adds MSC4357 live markers to draft preview sends and edits so supporting clients can render a typewriter animation that stops when the final edit lands.

11 details in Everything

v2026.4.11 Apr 12, 2026 · release notes

OpenClaw v2026.4.11 adds ChatGPT import ingestion, Teams reactions, plugin manifest descriptors, and richer video generation options.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.11 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.11

Adds ChatGPT import ingestion to Dreaming/memory-wiki, plus new Imported Insights and Memory Palace diary subtabs for inspecting imported chats, compiled wiki pages, and full source pages from the UI.
Adds [embed ...] rich output tag to Control UI/webchat, renders assistant media/reply/voice directives as structured chat bubbles, and gates external embed URLs behind config.
Extends Tools/video_generate with URL-only asset delivery, typed providerOptions, reference audio inputs, per-asset role hints, adaptive aspect-ratio support, and a higher image-input cap for richer provider generation modes.
Improves Feishu document comment sessions with richer context parsing, comment reactions, and typing feedback so document-thread conversations behave like chat conversations.
Adds Microsoft Teams reaction support, reaction listing, Graph pagination, and delegated OAuth setup for sending reactions while preserving application-auth read paths.

+4 more show less

Allows plugin manifests to declare activation and setup descriptors for required auth, pairing, and configuration steps without hardcoded core special cases.
Caches Ollama /api/show context-window and capability metadata during model discovery to eliminate redundant refetches on picker refreshes.
Surfaces how configured OpenAI-compatible endpoints are classified in embedded-agent debug logs for easier diagnosis of local and proxy routing issues.
Adds GPT-5.4 vs Opus 4.6 agentic parity report gate with shared scenario coverage checks, stricter evidence heuristics, and skipped-scenario accounting.

9 details in Everything

v2026.4.10 Apr 11, 2026 · release notes

OpenClaw v2026.4.10 adds Active Memory sub-agent, local MLX speech, exec-policy CLI, gateway command discovery, and expanded QA lanes.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.10 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.10

└──▷ TRY IT

Inspect or override your local exec approval policy without editing config files by hand.

$ openclaw exec-policy show
openclaw exec-policy preset strict
openclaw exec-policy set tools.exec.shell allow

Run your full QA suite inside a disposable Linux VM to keep host state clean and capture VM logs alongside the normal report.

$ openclaw qa suite --runner multipass

Adds Active Memory plugin that automatically injects relevant preferences, context, and past details into ongoing chats via a dedicated memory sub-agent before each reply, with configurable context modes and live /verbose inspection.
Adds experimental local MLX speech provider for Talk Mode on macOS, with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback.
Adds bundled Codex provider so codex/gpt-* models use Codex-managed auth, native threads, model discovery, and compaction while openai/gpt-* stays on the standard OpenAI path.
Adds Seedance 2.0 model support to the bundled fal provider, including duration, resolution, audio, and seed metadata fields for video generation.
Adds Microsoft Teams message actions for pin, unpin, read, react, and listing reactions.

+10 more show less

Adds openclaw exec-policy command with show, preset, and set subcommands for synchronizing tools.exec.* config with the local exec approvals file.
Adds commands.list RPC to the gateway so remote clients can discover runtime-native, text, skill, and plugin commands with surface-aware naming and serialized argument metadata.
Adds per-provider models.providers.*.request.allowPrivateNetwork setting to enable trusted self-hosted OpenAI-compatible endpoints.
Adds openclaw qa matrix lane backed by a disposable Matrix homeserver covering threading, reactions, restart, and allowlist transport behavior.
Adds openclaw qa telegram lane for private-group bot-to-bot checks with native Telegram command reply threading.
Adds --runner multipass option to openclaw qa suite for running QA scenarios inside a disposable Linux VM with report and log write-back.
Adds MSC4357 live markers to Matrix draft preview sends and edits, enabling typewriter animation in supporting clients.
Adds opt-in strict-agentic embedded Pi execution contract for GPT-5-family runs so plan-only or filler turns continue acting until a real blocker is reached.
Adds provider-owned OpenAI/Codex tool schema compatibility and surfaces embedded-run replay/liveness state for long-running agent runs.
Adds QQBot per-account streaming mode configuration via streaming.mode ("partial" | "off") instead of hardcoding it off.

15 details in Everything

v2026.4.9 Apr 9, 2026 · release notes

OpenClaw v2026.4.9 adds REM backfill for memory/dreaming, diary timeline UI, character-vibes QA reports, and provider auth aliasing.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.9 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.9

└──▷ TRY IT

Pin an iOS release to a specific CalVer gateway version for a release train.

$ pnpm ios:version:pin -- --from-gateway

Adds grounded REM backfill lane via rem-harness --path so old daily notes can replay into Dreams and durable memory without a second memory stack.
Adds structured diary view in Control UI with timeline navigation, backfill/reset controls, traceable dreaming summaries, and a grounded Scene lane with promotion hints.
Adds character-vibes evaluation reports in QA/lab with model selection and parallel runs for faster candidate behavior comparison.
Adds providerAuthAliases declaration in provider manifests so variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices.
Adds pnpm ios:version:pin -- --from-gateway workflow for iOS release train versioning pinned to explicit CalVer.

+1 more show less

Adds openclaw/plugin-sdk/command-status subpath to the Plugin SDK, splitting command status builders out of auth-only imports.

6 details in Everything

v2026.4.7 Apr 8, 2026 · release notes

OpenClaw v2026.4.7 adds a first-class infer hub, pluggable compaction, webhook ingress, memory-wiki, Arcee AI, and Gemma 4 support.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.7 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.7

└──▷ USE IT

Replace the built-in summarization pipeline with a custom compaction provider plugin to control how long session context is condensed.

yaml

agents:
  defaults:
    compaction:
      provider: my-custom-compaction-plugin

Override the system prompt for a controlled experiment without affecting global agent defaults.

yaml

agents:
  defaults:
    systemPromptOverride: "You are a security analyst. Focus only on CVE triage."

Auto-fallback across image, music, and video providers with intent preservation and capability remapping for size/aspect/resolution/duration hints.
New bundled webhook ingress plugin enables external automation to create and drive bound TaskFlows through per-route shared-secret endpoints.
Pluggable compaction provider registry lets plugins replace the built-in summarization pipeline, configured via agents.defaults.compaction.provider.
New agents.defaults.systemPromptOverride for controlled prompt experiments plus heartbeat prompt-section controls.
Gemma 4 model support added for the Google provider, including reasoning support and explicit thinking-off semantics in compatibility wrappers.

+7 more show less

New bundled Arcee AI provider plugin with Trinity catalog entries and OpenRouter support.
Ollama vision capability auto-detected from /api/show response, enabling image attachments on supported models.
Dreaming corpus now ingests redacted session transcripts with per-day session-corpus notes, cursor checkpointing, and promotion/doctor support.
Plugin SDK assemble() now receives availableTools and citationsMode, plus memory-artifact and memory-prompt seams for companion plugins and non-legacy context engines.
Discord event-create action accepts a cover image URL or local PNG/JPG/GIF file path.
Prompt-cache runtime context exposed to context engines, with current-turn usage aligned to the active attempt.
String-content compatibility added for stricter OpenAI-compatible chat backends (inferrs), with full config example and troubleshooting guidance.

12 details in Everything

v2026.4.5 Apr 6, 2026 · release notes

OpenClaw v2026.4.5 adds built-in video/music generation tools, ComfyUI integration, 12 new providers, Matrix exec approvals, multilingual Control UI, and experimental memory dreaming.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.5 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.5

└──▷ TRY IT

Force-reinstall an existing plugin (e.g. after an update) without triggering the dangerous-code override prompt.

$ openclaw plugins install --force <plugin-or-hookpack-target>

Inspect prompt-cache efficiency and see exactly where cache breaks occur across a running agent session.

$ openclaw status --verbose

Manually trigger a dreaming REM preview run to see which memories would be promoted before committing them.

$ openclaw memory rem-harness

Adds built-in video_generate agent tool so agents can create and return video media directly in replies.
Adds built-in music_generate tool with bundled Google Lyria and MiniMax providers plus ComfyUI workflow-backed support, including async task tracking and follow-up audio delivery.
Adds bundled comfy workflow media plugin for local ComfyUI and Comfy Cloud, covering image_generate, video_generate, and music_generate with prompt injection, reference-image upload, live tests, and output download.
Adds bundled Qwen, Fireworks AI, StepFun, MiniMax TTS, Ollama Web Search, and MiniMax Search providers for chat, speech, and search workflows.
Adds Amazon Bedrock Mantle support plus inference-profile discovery and automatic request-region injection for Bedrock-hosted Claude, GPT-OSS, Qwen, Kimi, GLM, and similar routes.

+19 more show less

Adds Amazon Bedrock embeddings for Titan, Cohere, Nova, and TwelveLabs models with AWS credential-chain auto-detection for memory/search.
Adds localized Control UI for Simplified Chinese, Traditional Chinese, Brazilian Portuguese, German, Spanish, Japanese, Korean, French, Turkish, Indonesian, Polish, and Ukrainian.
Adds openclaw plugins install --force to replace existing plugin and hook-pack targets without using the dangerous-code override flag.
Adds ClawHub search, detail, and install flows directly in the Skills panel.
Adds iOS APNs exec approval notifications that open an in-app approval modal and clear stale state on resolution.
Adds Matrix-native exec approval prompts with account-scoped approvers, channel-or-DM delivery, and room-thread aware resolution.
Adds configurable contextVisibility per channel (all, allowlist, allowlist_quote) to filter supplemental context by sender allowlists.
Adds shared model and media request transport overrides (headers, auth, proxy, TLS) across OpenAI-, Anthropic-, Google-, and compatible provider paths.
Exposes OpenClaw tools to background Claude CLI runs via a loopback MCP bridge with stdin + stream-json streaming for live progress on long replies.
Adds experimental structured plan updates and structured execution-item events for step-by-step agent progress in compatible UIs.
Adds bundled xAI (grok-imagine-video), Alibaba Model Studio Wan, and Runway video providers with live-test and default model wiring.
Adds experimental memory dreaming with weighted short-term recall promotion, /dreaming command, Dreams UI, multilingual conceptual tagging, and three cooperative phases (light, deep, REM).
Adds configurable dreaming aging controls (recencyHalfLifeDays, maxAgeDays) and optional verbose logging for recall decay tuning.
Adds REM preview tooling (openclaw memory rem-harness, promote-explain) and makes deep promotion replay-safe.
Adds Dream Diary surface in Dreams UI with simplified user-facing config (enabled plus optional frequency).
Adds prompt-cache break diagnostics and explicit cache reuse reporting in openclaw status --verbose.
Enriches openclaw config schema JSON Schema output with field titles and descriptions for editor and agent consumers.
Embeds ACP runtime directly in the bundled acpx plugin with a generic reply_dispatch hook, removing the external ACP CLI hop.
Adds plugin-config TUI prompts to guided onboarding/setup flows.

24 details in Everything

└──▷ BREAKING ON UPGRADE

!The legacy config aliases talk.voiceId, talk.apiKey, agents.*.sandbox.perSession, browser.ssrfPolicy.allowPrivateNetwork, hooks.internal.handlers, and channel/group/room allow toggles are removed; use the canonical public paths and enabled instead (openclaw doctor --fix can migrate existing configs).
!Bundled CLI text-provider backends and the agents.defaults.cliBackends config surface are removed; ACP harness sessions and Gemini media understanding remain on native bundled providers.
!The Claude CLI backend and setup-token are removed from new Anthropic onboarding; existing anthropic:claude-cli profiles remain runnable but openclaw doctor will repair or remove stale state.

v2026.4.2 Apr 2, 2026 · release notes

OpenClaw v2026.4.2 adds Task Flow orchestration, a before_agent_reply plugin hook, Android assistant entrypoints, and new Feishu/Matrix collaboration features.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.2

└──▷ TRY IT

Inspect and recover durable Task Flow state after a background orchestration run — useful when a long-running agent flow must be audited or restarted independently of the plugin layer.

$ openclaw flows

Silence the compaction notice in automated or quiet-mode deployments where the status message is noise.

yaml

# In your openclaw config
agents:
  defaults:
    compaction:
      notifyUser: false

Set a stable public proxy origin for diff viewer links so every tool call doesn't need to supply baseUrl manually.

yaml

# In your openclaw config
plugins:
  entries:
    diffs:
      config:
        viewerBaseUrl: "https://diffs.example.com"

Adds openclaw flows inspection and recovery primitives for durable Task Flow state and revision tracking, with managed-vs-mirrored sync modes for persistent background orchestration.
Adds managed child task spawning with sticky cancel intent, letting external orchestrators stop scheduling immediately and settle parent Task Flows to cancelled once active child tasks finish.
Adds api.runtime.taskFlow plugin seam so plugins and trusted authoring layers can create and drive managed Task Flows from host-resolved context without passing owner identifiers on each call.
Adds before_agent_reply plugin hook so plugins can short-circuit the LLM with synthetic replies after inline actions.
Adds Android assistant-role entrypoints and Google Assistant App Actions metadata so OpenClaw can be launched from the assistant trigger and receive prompts into the chat composer.

+9 more show less

Adds provider-owned replay hook surfaces for transcript policy, replay cleanup, and reasoning-mode dispatch.
Adds plugin-owned viewerBaseUrl config so diff viewer links can use a stable proxy/public origin without passing baseUrl on every tool call.
Adds agents.defaults.compaction.model resolution across manual /compact and other context-engine compaction paths, ensuring configured override models apply at all runtime entrypoints.
Adds agents.defaults.compaction.notifyUser config to make the compaction start notice opt-in rather than always displayed.
Adds a dedicated Feishu Drive comment-event flow with comment-thread context resolution, in-thread replies, and feishu_drive comment actions for document collaboration.
Adds spec-compliant m.mentions metadata to Matrix text sends, media captions, edits, poll fallback text, and action-driven edits for reliable mention notifications in clients like Element.
Adds reactionLevel guidance for WhatsApp agent reactions.
Moves provider-specific session conversation grammar into plugin-owned session-key surfaces, preserving Telegram topic routing and Feishu scoped inheritance across bootstrap, model override, restart, and tool-policy paths.
Auto-enables DM-first native chat approvals when supported channels can infer approvers from existing owner config, while keeping channel fanout explicit.

14 details in Everything

└──▷ BREAKING ON UPGRADE

!The xAI x_search settings have moved from tools.web.x_search.* to plugins.entries.xai.config.xSearch.*; auth is now standardized on plugins.entries.xai.config.webSearch.apiKey / XAI_API_KEY. Run openclaw doctor --fix to migrate.
!The Firecrawl web_fetch config has moved from tools.web.fetch.firecrawl.* to plugins.entries.firecrawl.config.webFetch.*, and the web_fetch fallback now routes through the new fetch-provider boundary instead of a Firecrawl-only core branch. Run openclaw doctor --fix to migrate.
!Gateway/node host exec now defaults to YOLO mode (security=full, ask=off); existing setups that relied on approval prompts from host exec will no longer receive them without explicit reconfiguration.

v2026.4.1 Apr 1, 2026 · release notes

OpenClaw v2026.4.1 adds a chat-native task board, SearXNG web search, Bedrock Guardrails, Voice Wake, per-job tool allowlists, and more.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.1

└──▷ USE IT

Cap how many auth-profile rotations occur on rate-limit failures before falling over to a different provider.

yaml

auth:
  cooldowns:
    rateLimitedProfileRotations: 3

Limit webchat history sent to the model to avoid bloated payloads on long sessions.

yaml

gateway:
  webchat:
    chatHistoryMaxChars: 8000

Adds /tasks as a chat-native background task board for the current session, with recent task details and agent-local fallback counts.
Adds a bundled SearXNG provider plugin for web_search with configurable host support.
Adds Amazon Bedrock Guardrails support to the bundled Bedrock provider.
Adds a Voice Wake option on macOS to trigger Talk Mode hands-free.
Adds a dedicated Feishu Drive comment-event flow with comment-thread context resolution, in-thread replies, and feishu_drive comment actions.

+7 more show less

Makes chat.history text truncation configurable via gateway.webchat.chatHistoryMaxChars and a per-request maxChars field.
Adds agents.defaults.params for setting global default provider parameters across all agents.
Adds auth.cooldowns.rateLimitedProfileRotations knob and cross-provider model fallback after rate-limit retries are exhausted.
Adds openclaw cron --tools flag for per-job tool allowlists.
Adds configurable errorPolicy and errorCooldownMs controls for Telegram to suppress repeated delivery errors per account, chat, and topic.
Adds glm-5.1 and glm-5v-turbo models to the bundled Z.AI provider catalog.
Adds reactionLevel guidance for WhatsApp agent reactions.

12 details in Everything

v2026.3.31 Mar 31, 2026 · release notes

OpenClaw v2026.3.31 adds QQ Bot channel, Slack exec approvals, Matrix streaming/proxy, MCP remote HTTP/SSE, WhatsApp emoji reactions, and a unified background task control plane.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.31 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.31

└──▷ TRY IT

List, inspect, or cancel orchestrated background task flows to monitor detached work without digging into raw task records.

$ openclaw flows list
openclaw flows show <flow-id>
openclaw flows cancel <flow-id>

Route Matrix traffic through a corporate HTTP proxy for environments that restrict direct outbound connections.

yaml

channels:
  matrix:
    proxy: "http://proxy.corp.example:3128"
    historyLimit: 20

Connect an MCP server over remote HTTP/SSE with an auth header instead of a local stdio process.

yaml

mcp:
  servers:
    - url: "https://mcp.example.com/sse"
      headers:
        Authorization: "Bearer <token>"

Adds QQ Bot as a bundled channel plugin with multi-account setup, SecretRef-aware credentials, slash commands, reminders, and media send/receive support.
Adds native Slack approval routing so exec approval prompts can be authorized directly in Slack instead of falling back to the Web UI or terminal.
Adds openclaw flows list|show|cancel commands for linear task flow control, surfacing orchestrated work with doctor recovery hints for orphaned flows.
Unifies ACP, subagent, cron, and background CLI execution under one SQLite-backed task ledger with audit, maintenance, and status visibility.
Adds remote HTTP/SSE server support for mcp.servers URL configs, including auth headers and safe credential redaction.

+15 more show less

Adds draft streaming for Matrix so partial replies update the same message in place rather than sending a new message per chunk.
Adds explicit channels.matrix.proxy config for routing Matrix traffic through an HTTP(S) proxy, including account-level overrides.
Adds optional channels.matrix.historyLimit for Matrix group triggers, with per-agent watermarks and retry-safe snapshots.
Adds LINE image, video, and audio outbound sends on the LINE-specific delivery path, including preview/tracking handling for videos.
Adds WhatsApp emoji reactions so agents can react to incoming messages instead of sending a text reply.
Adds a Graph-backed member info action for Microsoft Teams to resolve channel member details directly from Microsoft Graph.
Adds per-agent memorySearch.qmd.extraCollections so agents can opt into cross-agent session search without collapsing all transcripts into one namespace.
Adds native Codex web search support for embedded Pi runs, including config, docs, and wizard coverage.
Adds Android notification-forwarding controls with package filtering, quiet hours, and rate limiting.
Adds per-agent threadReplies overrides for Matrix DMs to keep thread session isolation aligned with the triggering message policy.
Adds bundle MCP tools with provider-safe names (serverName__toolName), optional streamable-http transport selection, and per-server connection timeouts.
Adds a configurable idle-stream timeout for embedded LLM runner requests so stalled model streams abort cleanly.
Adds structured provider diagnostics and fallback attempt analytics for TTS.
Adds an explicit default-off ACPX plugin-tools MCP bridge config with documented trust boundary.
Adds OpenAI text.verbosity forwarding across Responses HTTP and WebSocket transports, surfaced in /status.

20 details in Everything

└──▷ BREAKING ON UPGRADE

!The nodes.run shell wrapper is removed from the CLI and agent nodes tool; node shell execution must now go through exec host=node.
!Legacy provider compat subpaths, older bundled provider setup, and channel-runtime compatibility shims in the Plugin SDK are deprecated and emit migration warnings; use openclaw/plugin-sdk/* entrypoints and local api.ts/runtime-api.ts barrels going forward.
!Built-in dangerous-code critical findings and install-time scan failures now fail closed by default; plugin installs and gateway-backed skill dependency installs that previously succeeded may now require --dangerously-force-unsafe-install to proceed.
!trusted-proxy in Gateway/auth now rejects mixed shared-token configs, and local-direct fallback requires the configured token instead of implicitly authenticating same-host callers.
!Node commands now stay disabled until node pairing is approved; device pairing alone no longer exposes declared node commands.
!Node-originated runs now stay on a reduced trusted surface; notification-driven or node-triggered flows that previously relied on broader host/session tool access may need adjustment.

v2026.3.28 Mar 29, 2026 · release notes

OpenClaw v2026.3.28 adds xAI x_search, MiniMax image gen, async approval hooks, ACP channel binds, and a new config schema command.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.28 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.28

└──▷ TRY IT

Enable xAI web search during interactive onboarding to configure x_search with your shared xAI key and pick a model.

$ openclaw configure --section web

Print the full JSON schema for openclaw.json to validate your config file or generate editor autocompletion.

$ openclaw config schema

Turn the current Discord or iMessage conversation into a Codex-backed ACP workspace without spawning a child thread.

$ /acp spawn codex --bind here

Adds first-class x_search tool for the xAI/Grok provider via the Responses API, auto-enabled from existing web-search and tool config with no manual plugin toggles required.
Adds optional x_search setup (including model picker) during openclaw onboard and openclaw configure --section web for the bundled Grok web-search plugin.
New MiniMax image generation provider supporting the image-01 model with generate, image-to-image editing, and aspect ratio control.
Adds async requireApproval to before_tool_call plugin hooks, enabling plugins to pause tool execution and prompt for approval via the exec overlay, Telegram buttons, Discord interactions, or /approve.
Adds ACP current-conversation binds for Discord, BlueBubbles, and iMessage so /acp spawn codex --bind here turns the active chat into a Codex-backed workspace without spawning a child thread.

+9 more show less

Enables apply_patch by default for OpenAI and OpenAI Codex models, aligned with write sandbox permissions.
Auto-loads bundled provider and CLI-backend plugins from explicit config refs, removing the need for manual plugins.allow entries for Claude CLI, Codex CLI, and Gemini CLI.
New upload-file Slack action for routing file uploads through the Slack upload transport with optional filename, title, and comment overrides.
Extends upload-file action with explicit Microsoft Teams and Google Chat support, and exposes BlueBubbles file sends through upload-file (legacy sendAttachment alias preserved).
Matrix TTS auto-replies now sent as native Matrix voice bubbles instead of generic audio attachments.
New openclaw config schema command prints the generated JSON schema for openclaw.json.
Exposes runHeartbeatOnce in the plugin runtime system namespace so plugins can trigger a single heartbeat cycle with an explicit delivery target override.
Simplifies Podman rootless container setup and documents the host-CLI openclaw --container <name> ... workflow.
Outbound Tavily API requests now tagged with X-Client-Source: openclaw for traffic attribution.

14 details in Everything

└──▷ BREAKING ON UPGRADE

!The qwen-portal-auth OAuth integration for portal.qwen.ai is removed; migrate to Model Studio with openclaw onboard --auth-choice modelstudio-api-key.
!Automatic config migrations older than two months are dropped; very old legacy keys now fail validation instead of being rewritten on load or by openclaw doctor.
!MiniMax model catalog is trimmed to M2.7 only; legacy M2, M2.1, M2.5, and VL-01 models are removed.
!Regular-mode runtime fallback for old bundled tts.<provider> API-key shapes is removed (legacy diagnostics remain available via Doctor).

v2026.3.24 Mar 25, 2026 · release notes

OpenClaw v2026.3.24 adds OpenAI-compatible endpoints, Teams streaming, a --container flag, Discord auto-thread naming, and a revamped Skills UI.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.24 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.24

└──▷ TRY IT

Run any openclaw command inside an already-running Docker or Podman container without shelling in manually.

$ openclaw --container my-openclaw-container skills list

Point an OpenAI-compatible RAG client or SDK at the OpenClaw gateway to list available models before sending completions.

$ curl http://localhost:3000/v1/models -H 'Authorization: Bearer <api-key>'

Check which tools are available to the current agent right now, with full detail, before crafting a prompt.

$ openclaw skills info openai-whisper-api

Adds /v1/models and /v1/embeddings Gateway endpoints and forwards explicit model overrides through /v1/chat/completions and /v1/responses for OpenAI-compatible client and RAG pipeline support.
Adds --container flag and OPENCLAW_CONTAINER env var to run openclaw commands inside a running Docker or Podman OpenClaw container.
Adds before_dispatch plugin hook with canonical inbound metadata, routing handled replies through the normal final-delivery path and preserving TTS and routed delivery semantics.
Enhances /tools endpoint to show tools the current agent can actually use right now, with a compact default view, optional detailed mode, and a live Available Right Now section in the Control UI.
Migrates Microsoft Teams integration to the official Teams SDK with streaming 1:1 replies, welcome cards with prompt starters, feedback/reflection, typing indicators, status updates, and native AI labeling.

+9 more show less

Adds message edit and delete support for sent Teams messages, including in-thread fallbacks when no explicit target is provided.
Adds one-click install recipes to bundled skills (coding-agent, gh-issues, openai-whisper-api, session-logs, tmux, trello, weather) for dependency installation via CLI and Control UI.
Adds Control UI skills status-filter tabs (All / Ready / Needs Setup / Disabled) with counts and a click-to-detail dialog showing requirements, toggle, install action, API key entry, source metadata, and homepage link.
Adds optional autoThreadName: "generated" Discord config for asynchronous LLM-generated auto-thread titles.
Adds expandable <details> lazy-loaded inline markdown preview for agent workspace files in Control UI, with comprehensive .sidebar-markdown styles.
Integrates @create-markdown/preview v2 with frosted-backdrop dialog and auto-adapting light/dark system theme for agent workspace file previews in Control UI.
Replaces macOS app horizontal pill navigation with a collapsible tree sidebar using disclosure chevrons and indented subsection rows.
Surfaces API key setup guidance (where to get a key, CLI save command, storage path) in openclaw skills info output.
Adds Node 22.14+ as the supported floor for openclaw update, with preflight engines.node checks that fail clearly on outdated runtimes instead of attempting unsupported installs.

14 details in Everything

v2026.3.23 Mar 23, 2026 · release notes

OpenClaw v2026.3.23 adds pay-as-you-go Qwen endpoints, Knot theme overhaul, SHA-256 CSP hashing, and cron timezone-aware scheduling.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.23 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.23

└──▷ TRY IT

Schedule a one-shot cron task at a specific local time in a DST-observing timezone without UTC math.

$ openclaw cron add --at '2026-11-01T09:00' --tz America/New_York 'openclaw run my-morning-task'

Adds standard pay-as-you-go DashScope endpoints for China and global Qwen API keys under the relabeled Qwen (Alibaba Cloud Model Studio) provider group.
New Knot UI theme with black-and-red palette meeting WCAG 2.1 AA contrast, discrete roundness stops, config icons for Diagnostics/CLI/Secrets/ACP/MCP sections, and improved aria-labels.
Adds SHA-256 hash computation for inline <script> blocks in index.html, included in the script-src CSP directive to allow only explicitly hashed bootstrap code.
Adds --tz <iana> support to openclaw cron add|edit --at for correct local wall-clock scheduling of one-shot datetimes, including DST boundaries.
Adds asDocument as a user-facing alias for forceDocument on Telegram image and GIF sends.

5 details in Everything

v2026.3.22 Mar 23, 2026 · release notes

OpenClaw v2026.3.22 adds ClawHub skill flows, SSH/OpenShell sandbox backends, Exa/Tavily/Firecrawl web-search plugins, Android call-log and SMS search, and Telegram topic-label automation.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.22 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.22

└──▷ TRY IT

Install a ClawHub-backed skill by name, bypassing npm resolution, to get tracked update metadata.

$ openclaw plugins install clawhub:exa

Configure the Exa bundled web-search plugin with content extraction enabled for deeper research tasks.

yaml

plugins:
  entries:
    exa:
      config:
        webSearch:
          extractContent: true
          searchMode: neural

Point the built-in image generation tool at Gemini after removing the old nano-banana-pro skill wrapper.

yaml

agents:
  defaults:
    imageGenerationModel:
      primary: "google/gemini-3-pro-image-preview"

Adds openclaw skills search|install|update and openclaw plugins install clawhub:<package> flows with tracked update metadata for ClawHub-backed skill installs.
Adds commands.plugins config gating and owner-gated /plugins and /plugin chat commands for plugin list, show, enable, and disable flows.
Adds browser.profiles.<name>.userDataDir support so the existing-session browser backend can attach to Brave, Edge, and other Chromium-based browsers via their own user data directories.
Adds plugins.entries.exa.config.webSearch.* config namespace and Exa as a bundled web-search plugin with native date filters, search-mode selection, and optional content extraction.
Adds plugins.entries.tavily.config.webSearch.* config namespace and dedicated tavily_search and tavily_extract tools via a bundled Tavily web-search plugin.

+22 more show less

Adds firecrawl_search and firecrawl_scrape tools and a bundled Firecrawl plugin with onboard/configure search-provider support and web_fetch fallback alignment.
Adds channels.telegram.silentErrorReplies setting (default off) so Telegram bot error replies can be delivered silently.
Adds openclaw update --tag main and installer --version main to allow package-manager installs from GitHub main branch.
Adds pluggable sandbox backends: ships an OpenShell backend with mirror and remote workspace modes, making sandbox list/recreate/prune backend-aware instead of Docker-only.
Adds a core SSH sandbox backend with secret-backed key, certificate, and known_hosts inputs and shared remote exec/filesystem tooling in core.
Adds agents.defaults.imageGenerationModel.primary config key (e.g. google/gemini-3-pro-image-preview) for built-in image generation, replacing the removed nano-banana-pro bundled skill.
Adds anthropic-vertex provider for Claude via Google Vertex AI, including GCP auth/discovery and main run-path routing.
Adds a bundled Chutes provider plugin with OAuth/API-key auth, dynamic model discovery, and default-on extension wiring.
Adds android node tool callLog.search plus shared Call Log permission wiring so Android nodes can search recent call history through the gateway.
Adds android node tool sms.search plus shared SMS permission wiring so Android nodes can search device text messages through the gateway.
Adds talk.speak gateway route for Talk speech synthesis, keeping Talk secrets server-side and switching Android playback to final-response audio.
Adds per-account custom Bot API endpoint (apiRoot) support across Telegram send, probe, setup, doctor repair, and inbound media download paths for proxied or self-hosted deployments.
Adds autoTopicLabel per-account and per-DM Telegram override for LLM-generated DM forum topic labels on first message.
Adds topic-edit Telegram action for forum-topic renames and icon updates.
Adds /btw chat command for quick tool-less side questions about the current session without altering future session context.
Switches the default OpenAI setup model to openai/gpt-5.4 and adds forward-compat entries for gpt-5.4-mini and gpt-5.4-nano in the OpenAI provider catalog.
Adds per-agent thinking/reasoning/fast defaults with auto-revert for disallowed model overrides.
Moves OpenRouter, GitHub Copilot, and OpenAI Codex provider logic into bundled plugins with dynamic model fallback, runtime auth exchange, and cache-TTL policy.
Adds compatible Codex, Claude, and Cursor bundle discovery and install support, mapping bundle skills into OpenClaw skills.
Adds an expand-to-canvas button on assistant chat bubbles and in-app session navigation from Sessions and Cron views.
Adds a Roundness slider to the Appearance settings for adjusting corner radius from sharp to fully rounded, with unified theme border radii across Claw, Knot, and Dash.
Adds system-aware dark theme across Android onboarding and post-onboarding screens so the app follows the device theme through setup, chat, and voice flows.

27 details in Everything

└──▷ BREAKING ON UPGRADE

!openclaw plugins install <package> now prefers ClawHub over npm for npm-safe package names and only falls back to npm when ClawHub does not have the package or version.
!The legacy Chrome extension relay path, bundled extension assets, driver: "extension" config key, and browser.relayBindHost config key are removed; run openclaw doctor --fix to migrate host-local browser config to existing-session / user.
!The bundled nano-banana-pro skill wrapper is removed; use agents.defaults.imageGenerationModel.primary: "google/gemini-3-pro-image-preview" instead.
!The plugin SDK entrypoint openclaw/extension-api is removed with no compatibility shim; plugins must import from openclaw/plugin-sdk/* subpaths and use injected runtime (e.g. api.runtime.agent.runEmbeddedPiAgent) for host-side operations.
!The legacy ChannelMessageActionAdapter methods listActions, getCapabilities, and getToolSchema are removed; plugin authors must migrate message discovery to ChannelMessageActionAdapter.describeMessageTool(...).
!All legacy CLAWDBOT_* and MOLTBOT_* environment variable names are removed; use the matching OPENCLAW_* env names instead.
!The legacy .moltbot state directory and moltbot.json auto-detection/migration fallback are removed; move state from ~/.moltbot to ~/.openclaw or set OPENCLAW_STATE_DIR / OPENCLAW_CONFIG_PATH explicitly.
!The exec environment sandbox now blocks MAVEN_OPTS, SBT_OPTS, GRADLE_OPTS, ANT_OPTS, GLIBC_TUNABLES, and DOTNET_ADDITIONAL_DEPS from host injection, and restricts GRADLE_USER_HOME to override-only propagation.
!Discord native command deployment now defaults to Carbon reconcile, stopping slash commands from being churned through OpenClaw's local deploy path on Discord restarts.
!Voice-call/webhook pre-auth body budget is reduced to 64 KB / 5s (from 1 MB / 30s) and requests with missing provider signature headers are now rejected before body reads; concurrent pre-auth requests per source IP are also capped.
!The Matrix plugin is rebuilt on matrix-js-sdk; users upgrading from the previous public Matrix plugin must follow the migration guide at https://docs.openclaw.ai/install/migrating-matrix.

v2026.3.13-1 Mar 14, 2026 · release notes

OpenClaw v2026.3.13-1 adds Slack interactive reply directives, Docker timezone support, iOS onboarding pager, and Android chat settings redesign.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.13-1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.13-1

└──▷ TRY IT

Set the container timezone so scheduled tasks and log timestamps reflect your local time zone.

$ docker run -e OPENCLAW_TZ=America/New_York openclaw/openclaw

Adds opt-in interactive reply directives for Slack channels.
Adds OPENCLAW_TZ timezone support for Docker deployments.
Adds an onboarding welcome pager for iOS.
Redesigns the chat settings UI on Android.
Plugins now fail fast on channel and binding collisions, surfacing conflicts at startup.

+1 more show less

macOS gateway prompter now respects exec-approvals.json settings.

6 details in Everything

v2026.3.12 Mar 13, 2026 · release notes

OpenClaw v2026.3.12 adds a revamped gateway dashboard, GPT-5.4/Claude fast-mode toggles, Slack Block Kit support, and a new sessions_yield orchestration primitive.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.12 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.12

New modular gateway dashboard (dashboard-v2) with overview, chat, config, agent, and session views; command palette; mobile bottom tabs; and chat tools including slash commands, search, export, and pinned messages.
Adds configurable session-level fast-mode toggle (/fast) across TUI, Control UI, and ACP for OpenAI/GPT-5.4, with per-model config defaults and Codex request shaping.
Maps /fast toggle and params.fastMode to Anthropic API service_tier requests for Claude fast mode, with live tier verification for both Anthropic and OpenAI.
Moves Ollama, vLLM, and SGLang onto a provider-plugin architecture with provider-owned onboarding, discovery, model-picker setup, and post-selection hooks.
Adds a Kubernetes install path with raw manifests, Kind setup, and deployment docs.

+2 more show less

Adds sessions_yield so orchestrators can end the current turn immediately, skip queued tool work, and carry a hidden follow-up payload into the next session turn.
Supports channelData.slack.blocks in the shared reply delivery path, enabling agents to send Slack Block Kit messages through standard outbound delivery.

7 details in Everything

v2026.3.11 Mar 12, 2026 · release notes

OpenClaw v2026.3.11 adds multimodal memory indexing, ACP session resumption, Ollama onboarding, and new CLI/gateway primitives.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.11 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.11

└──▷ TRY IT

Run the doctor tool to automatically migrate legacy cron storage and notify/webhook metadata after upgrading past the cron delivery breaking change.

$ openclaw doctor --fix

Get clean, machine-readable JSON from skills commands in CI pipelines — control characters are now stripped so output is valid JSON.

$ openclaw skills list --json | jq '.[] | .name'

Adds opt-in multimodal image and audio indexing for memorySearch.extraPaths using Gemini gemini-embedding-2-preview, with strict fallback gating and scope-based reindexing.
Adds gemini-embedding-2-preview memory-search support with configurable output dimensions and automatic reindexing when configured dimensions change.
Adds optional resumeSessionId for runtime: "acp" in sessions_spawn so spawned ACP sessions can resume an existing ACPX/Codex conversation.
Adds narrow in-memory pending-work queue primitives (node.pending.enqueue / node.pending.drain) and wake-helper reuse for dormant-node work delivery.
Adds first-class Ollama setup in onboarding with Local or Cloud + Local modes, browser-based cloud sign-in, curated model suggestions, and smart local-pull skipping.

+8 more show less

Adds new OpenCode Go provider in onboarding, with a shared OpenCode key for both Zen and Go profiles.
Adds autoArchiveDuration channel config for Discord auto-created threads, supporting 1 hour, 1 day, 3 days, or 1 week archive windows.
Marks child command environments with OPENCLAW_CLI so subprocesses can detect when they were launched from the OpenClaw CLI.
Adds openclaw doctor --fix migration command for legacy cron storage and legacy notify/webhook delivery metadata.
Adds macOS chat model picker with persistent thinking-level selections across relaunch and provider-aware session model sync.
Adds macOS onboarding detection for remote gateways requiring a shared auth token, with guidance on locating it on the gateway host.
Adds iOS bundled welcome screen with live agent overview that refreshes on connect, reconnect, and foreground return.
Adds Fastlane-based local beta release flow for iOS/TestFlight with prepare/archive/upload support and canonical beta bundle IDs.

13 details in Everything

└──▷ BREAKING ON UPGRADE

!Cron jobs can no longer notify through ad hoc agent sends or fallback main-session summaries; run openclaw doctor --fix to migrate legacy cron storage and legacy notify/webhook delivery metadata.

v2026.3.8 Mar 9, 2026 · release notes

OpenClaw v2026.3.8 adds local backup commands, ACP provenance tracking, Brave LLM Context search, and configurable Talk silence timeout.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.8 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.8

└──▷ TRY IT

Create a config-only backup before a destructive operation such as a major upgrade or workspace reset.

$ openclaw backup create --only-config

Verify the integrity of an existing local state archive to confirm the manifest and payload are intact.

$ openclaw backup verify

Enable Brave LLM Context mode so web_search returns grounding snippets with source metadata instead of raw results.

yaml

tools.web.search.brave.mode: "llm-context"

Adds openclaw backup create and openclaw backup verify commands for local state archives, with --only-config and --no-include-workspace flags, manifest/payload validation, and backup guidance in destructive flows.
Adds openclaw acp --provenance off|meta|meta+receipt flag so agents can retain and report ACP-origin context with session trace IDs.
Adds opt-in tools.web.search.brave.mode: "llm-context" config to call Brave's LLM Context endpoint and return extracted grounding snippets with source metadata.
Adds top-level talk.silenceTimeoutMs config so Talk mode waits a configurable amount of silence before auto-sending the current transcript.
Includes the short git commit hash in openclaw --version output when metadata is available.

+3 more show less

Adds a remote gateway token field for macOS onboarding remote mode, preserving existing non-plaintext gateway.remote.token config values until explicitly replaced.
TUI now infers the active agent from the current workspace when launched inside a configured agent workspace, while preserving explicit agent: session targets.
Adds browser.relayBindHost config so the Chrome relay can bind to an explicit non-loopback address for WSL2 and other cross-namespace setups.

8 details in Everything

v2026.3.7 Mar 8, 2026 · release notes

OpenClaw v2026.3.7 adds a plugin context engine, durable ACP channel bindings, Gemini 3.1 Flash-Lite, Spanish UI, and 15+ new integrations and capabilities.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.7 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.7

└──▷ TRY IT

Bind a Telegram topic thread to an ACP session so follow-up messages in that topic always route to the same agent.

$ /acp spawn --thread here

Show reaction-based typing feedback in Slack Socket Mode DMs where native assistant typing indicators are unavailable.

yaml

channels:
  slack:
    typingReaction: "eyes"

Adds ContextEngine plugin slot with full lifecycle hooks (bootstrap, ingest, assemble, compact, afterTurn, prepareSubagentSpawn, onSubagentEnded) and a sessions.get gateway method, enabling alternative context management strategies without modifying core compaction logic.
Adds durable Discord channel and Telegram topic binding storage and routing so ACP thread targets survive restarts and can be managed consistently via CLI.
Supports Telegram topic thread binding (--thread here|auto) in /acp spawn, per-topic agentId overrides in forum groups, actionable Telegram approval buttons, and in-topic confirmation pinning.
Adds Spanish (es) locale support in the Control UI with locale detection, lazy loading, and a language picker.
Adds provider selection step and full provider list in the configure onboarding wizard, with SecretRef ref-mode support during onboarding.

+15 more show less

Switches Perplexity web search provider to the Search API with structured results and new language, region, and time filters.
Adds SecretRef support for gateway.auth.token with auth-mode guardrails.
Adds OPENCLAW_EXTENSIONS build arg so container builds can preinstall bundled extension npm dependencies for faster, more reproducible startup.
Adds prependSystemContext and appendSystemContext plugin hooks so static guidance can be placed in system prompt space, reducing repeated prompt token cost via provider caching.
Adds plugins.entries.<id>.hooks.allowPromptInjection hook policy and validates unknown typed hook names at runtime.
Emits session:compact:before and session:compact:after events with session/count metadata so automations can react to compaction runs.
Adds agents.defaults.compaction.postCompactionSections so deployments can choose which AGENTS.md sections are re-injected after compaction.
Adds messages.tts.openai.baseUrl config support with config-over-env precedence for routing OpenAI TTS requests to a resolved base URL.
Adds channels.slack.typingReaction so Socket Mode DMs can show reaction-based processing status when Slack native assistant typing is unavailable.
Adds allowBots: "mentions" Discord option to accept only bot-authored messages that explicitly mention the bot.
Uses head+tail truncation for oversized tool results to preserve important tail diagnostics.
Adds agents.defaults.compaction.recentTurnsPreserve and quality-guard retry knobs through the validated config surface.
Adds interactive provider/model browsing for Mattermost /oc_model and /oc_models commands.
Restructures Docker build as multi-stage to produce a minimal runtime image; adds OPENCLAW_VARIANT=slim build arg for a bookworm-slim variant.
Adds first-class support for google/gemini-3.1-flash-lite-preview across model-id normalization, default aliases, media-understanding image lookups, and Google Gemini CLI forward-compat fallback.

20 details in Everything

└──▷ BREAKING ON UPGRADE

!Gateway auth now requires an explicit gateway.auth.mode value (token or password) when both gateway.auth.token and gateway.auth.password are configured (including SecretRefs); omitting gateway.auth.mode before upgrade will cause startup, pairing, and TUI failures.

v2026.3.2 Mar 3, 2026 · release notes

OpenClaw v2026.3.2 adds PDF analysis, Ollama memory embeddings, config validation CLI, 64-target SecretRef coverage, and 10+ new plugin runtime APIs.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.2

└──▷ TRY IT

Validate your OpenClaw config file and get machine-readable errors before restarting the gateway — useful in CI or pre-deploy hooks.

$ openclaw config validate --json

Use a locally-running Ollama model for memory embeddings instead of a cloud provider, keeping all data on-premise.

$ openclaw config set memorySearch.provider ollama && openclaw config set memorySearch.fallback ollama

Adds first-class pdf tool with native Anthropic and Google PDF provider support, extraction fallback for non-native models, and configurable defaults (agents.defaults.pdfModel, pdfMaxBytesMb, pdfMaxPages).
Adds openclaw config validate (with --json flag) to validate config files before gateway startup, with detailed invalid-key paths in startup errors.
Adds memorySearch.provider = "ollama" and memorySearch.fallback = "ollama" support for local Ollama-powered memory embeddings.
Expands SecretRef support across 64 credential targets, including runtime collectors and openclaw secrets planning/apply/audit flows; unresolved refs now fail fast on active surfaces.
Adds inline file attachment support for sessions_spawn (subagent runtime only) with base64/utf8 encoding, transcript redaction, and configurable limits via tools.sessions_spawn.attachments.

+15 more show less

Adds api.runtime.stt.transcribeAudioFile(...) so plugins can transcribe local audio files through OpenClaw's configured audio providers.
Exposes channelRuntime on ChannelGatewayContext so external channel plugins access shared runtime helpers without internal imports.
Adds runtime.events.onAgentEvent and runtime.events.onSessionTranscriptUpdate for extension-side event subscriptions, with isolated listener failure handling.
Exposes runtime.system.requestHeartbeatNow(...) so plugins can wake targeted sessions immediately after enqueueing system events.
Adds internal hook events message:transcribed and message:preprocessed, plus isGroup/groupId context on outbound message:sent for group-conversation correlation.
Includes sessionKey in session_start/session_end hook events so plugins can correlate lifecycle callbacks with routing identity.
Adds optional tools.media.audio.echoTranscript and echoFormat to send a pre-agent transcript confirmation message back to the originating chat.
Adds optional disableAudioPreflight on Telegram group/topic config to skip mention-detection preflight transcription for inbound voice notes.
Adds sendPayload support across direct-text-media, Discord, Slack, WhatsApp, Zalo, and Zalouser adapters with multi-media iteration and chunk-aware text fallback.
Defaults channels.telegram.streaming to partial (from off) so new Telegram setups get live preview streaming out of the box.
Adds cli.banner.taglineMode (random | default | off) to control startup tagline behavior.
Adds first-class MiniMax-M2.5-highspeed model support across provider catalogs and onboarding flows, with legacy MiniMax-M2.5-Lightning compatibility.
Adds PDF file output and rendering quality controls (fileQuality, fileScale, fileMaxWidth) for generated diff artifacts.
Rebuilds Zalo Personal plugin (@openclaw/zalouser) to use native zca-js in-process, removing dependency on external CLI binaries.
Adds sendMessageDraft for Telegram private DM preview streaming with separated reasoning/answer preview lanes.

20 details in Everything

└──▷ BREAKING ON UPGRADE

!Onboarding now defaults tools.profile to messaging for new local installs; new setups no longer start with broad coding/system tools unless explicitly configured.
!ACP dispatch now defaults to enabled; set acp.dispatch.enabled=false to disable if you need to pause ACP turn routing while keeping /acp controls.
!Plugin SDK removed api.registerHttpHandler(...); plugins must use api.registerHttpRoute({ path, auth, match, handler }) and registerPluginHttpRoute(...) for dynamic webhook lifecycles.
!Zalo Personal plugin (@openclaw/zalouser) no longer depends on external zca-compatible CLI binaries (openzca, zca-cli); run openclaw channels login --channel zalouser after upgrade to refresh sessions.

v2026.3.1 Mar 2, 2026 · release notes

OpenClaw v2026.3.1 adds Android node commands, Discord/Telegram session controls, OpenAI WebSocket-first streaming, Feishu tooling, and a new diff-rendering plugin.

└──▷ GET THIS VERSION

$ git clone --branch v2026.3.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.3.1

└──▷ TRY IT

Find exactly which config file OpenClaw is reading — useful when debugging unexpected settings across multiple environments.

$ openclaw config file

Enable the Feishu chat tooling so agents can query chat info and membership within a Feishu channel.

yaml

channels:
  feishu:
    tools:
      chat: true

Adds openclaw config file subcommand to print the active config file path resolved from OPENCLAW_CONFIG_PATH or the default location.
Adds built-in HTTP liveness/readiness endpoints (/health, /healthz, /ready, /readyz) for Docker/Kubernetes container health checks with fallback routing.
Adds Android node commands: camera.list, device.permissions, device.health, notifications.actions (open/dismiss/reply), system.notify, photos.latest, contacts.search/contacts.add, calendar.events/calendar.add, and motion.activity/motion.pedometer.
Replaces Discord thread fixed-TTL lifecycle with inactivity (idleHours, default 24 h) and optional hard maxAgeHours controls; adds /session idle and /session max-age commands.
Adds per-DM Telegram topic config (direct + topic allowlists, dmPolicy, skills, systemPrompt, requireTopic) with topic-aware authorization and debounce.

+14 more show less

Makes OpenAI Responses transport WebSocket-first by default (transport: "auto" with SSE fallback) and adds optional WS warm-up via params.openaiWsWarmup.
Adds new optional diffs plugin tool for read-only diff rendering from before/after text or unified patches, with gateway viewer URLs for canvas and PNG output.
Adds Feishu Docx table actions (create_table, write_table_cells, create_table_with_values) and file/image upload actions (upload_image, upload_file).
Adds Feishu inbound reaction handling (im.message.reaction.created_v1) with verified routing through synthetic inbound turns.
Adds feishu_chat tool actions for chat info and member queries, configurable under channels.feishu.tools.chat.
Supports optional owner permission grant fields on feishu_doc create.
Adds German (de) locale support and auto-renders language options from supported locale constants in the Web UI Overview settings.
Supports custom OpenAI baseUrl and embedding dimensions for LanceDB memory.
Adds opt-in lightweight bootstrap mode for cron/heartbeat automation runs via --light-context flag and agents.*.heartbeat.lightContext config key.
Sets OPENCLAW_SHELL environment variable across shell-like runtimes (exec, acp, acp-client, tui-local) so shell startup rules can target OpenClaw contexts.
Replaces ad-hoc subagent completion handoff with typed internal task_completion events rendered consistently across direct and queued announce paths.
Sets adaptive as the default thinking level for Anthropic Claude 4.6 models (including Bedrock Claude 4.6 refs).
Localizes cron page labels, filters, form help text, and validation/error messaging in English and zh-CN.
Adds ACP final_only stream delivery default and configurable ACPX command/version probing, pinned to plugin version 0.1.15.

19 details in Everything

v2026.2.26 Feb 27, 2026 · release notes

OpenClaw v2026.2.26 adds External Secrets Management, ACP thread-bound agents, agent route binding CLI, Android device/notification nodes, and more.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.26 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.26

└──▷ TRY IT

Audit your current secrets configuration before migrating to External Secrets Management.

$ openclaw secrets audit

Apply a secrets configuration to a specific target path and activate it at runtime.

$ openclaw secrets apply <target-path> && openclaw secrets reload

Bind an agent to an account-scoped route for centralized routing management.

$ openclaw agents bind <agent> <channel>

New openclaw secrets workflow with audit, configure, apply, and reload subcommands for External Secrets Management, including runtime snapshot activation and ref-only auth-profile support.
ACP agents are now first-class runtimes for thread sessions with acp spawn/send dispatch integration, acpx backend bridging, lifecycle controls, and coalesced thread replies.
New openclaw agents bindings, openclaw agents bind, and openclaw agents unbind commands for account-scoped route management, including channel-to-account binding upgrades and role-aware binding identity handling.
Adds openai-codex WebSocket-first transport by default (transport: "auto" with SSE fallback), with explicit per-model/runtime transport overrides retained.
Channel plugins can now own interactive onboarding flows via optional configureInteractive and configureWhenConfigured hooks.

+3 more show less

Adds an explicit account-risk warning and confirmation gate before starting Gemini CLI OAuth.
New Android device capability with device.status and device.info node commands, including protocol and registry coverage for device status/info payloads.
Adds notifications.list support on Android nodes and exposes nodes notifications_list in agent tooling for listing active device notifications.

8 details in Everything

└──▷ BREAKING ON UPGRADE

!openclaw onboard --reset now defaults to config+creds+sessions scope; workspace deletion requires --reset-scope full.

v2026.2.25 Feb 26, 2026 · release notes

OpenClaw v2026.2.25 adds granular heartbeat delivery policy config and startup performance benchmarking scripts.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.25 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.25

└──▷ USE IT

Block heartbeat DMs globally while allowing specific agents to still deliver direct messages.

yaml

# In your OpenClaw config file:
agents:
  defaults:
    heartbeat:
      directPolicy: "block"
  list:
    - id: my-agent
      heartbeat:
        directPolicy: "allow"

New agents.defaults.heartbeat.directPolicy config key (allow | block) replaces the old heartbeat DM toggle, with per-agent override via agents.list[].heartbeat.directPolicy.
Adds startup macrobenchmark and low-noise perf CLI scripts for deterministic cold-start tracking on Android.
Adds mobile stacked layout for compose action buttons on small screens in the chat UI.

3 details in Everything

└──▷ BREAKING ON UPGRADE

!The heartbeat DM toggle is replaced by agents.defaults.heartbeat.directPolicy; the default is now allow. To preserve the DM-blocked behavior from v2026.2.24, set agents.defaults.heartbeat.directPolicy: "block" (or use a per-agent override via agents.list[].heartbeat.directPolicy).

v2026.2.24 Feb 25, 2026 · release notes

OpenClaw v2026.2.24 adds multilingual stop keywords, native Android onboarding, ElevenLabs gateway config, and a multi-user security heuristic.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.24 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.24

Adds multilingual auto-reply stop keywords (ES/FR/ZH/HI/AR/JP/DE/PT/RU) plus trailing-punctuation tolerance and exact do not do that as a stop trigger.
Ships a native four-step Android onboarding flow and a five-tab shell (Connect, Chat, Voice, Screen, Settings) with a full Connect setup/manual mode screen.
Adds provider-agnostic Talk configuration with legacy compatibility and exposes ElevenLabs gateway Talk config metadata for setup/status surfaces.
Introduces security.trust_model.multi_user_heuristic to flag likely shared-user ingress, with hardening guidance for multi-user deployments (sandbox.mode="all", workspace-scoped FS, reduced tool surface).

4 details in Everything

└──▷ BREAKING ON UPGRADE

!Heartbeat delivery now blocks direct/DM targets (e.g. user:<id>, Telegram user chat IDs, WhatsApp direct numbers/JIDs); heartbeat runs still execute but direct-message delivery is skipped — only channel/group targets receive outbound heartbeat messages.
!Docker network: "container:<id>" namespace-join mode is blocked by default for sandbox and sandbox-browser containers; to re-enable it, set agents.defaults.sandbox.docker.dangerouslyAllowContainerNamespaceJoin: true.

v2026.2.23 Feb 24, 2026 · release notes

OpenClaw v2026.2.23 adds Kilo Gateway and Kimi/Moonshot providers, HSTS header support, and hardened session-maintenance CLI commands.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.23 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.23

└──▷ USE IT

Enable HSTS headers on a self-hosted OpenClaw gateway serving HTTPS directly.

yaml

gateway:
  http:
    securityHeaders:
      strictTransportSecurity: "max-age=63072000; includeSubDomains; preload"

Adds first-class kilocode provider with auth, onboarding, implicit detection, model defaults, and transcript/cache-ttl handling; default model is kilocode/anthropic/claude-opus-4.6.
Adds provider: "kimi" (Moonshot) support in the web_search tool, with key/config schema wiring and a two-step $web_search flow that includes citation extraction.
Adds native Moonshot video provider and includes Moonshot in auto video key detection.
Accepts Claude shorthand model refs (vercel-ai-gateway/claude-*) for the Vercel AI Gateway by normalizing to canonical Anthropic-routed model IDs.
Adds optional gateway.http.securityHeaders.strictTransportSecurity config to emit Strict-Transport-Security headers for direct HTTPS deployments.

+3 more show less

Adds openclaw sessions cleanup command with per-agent store targeting, disk-budget controls (session.maintenance.maxDiskBytes / highWaterBytes), and safer transcript/archive cleanup.
Supports per-agent params overrides merged on top of model defaults (including cacheRetention) for independent cache-behavior tuning per agent.
Caches bootstrap file snapshots (AGENTS.md/MEMORY.md) per session key and clears them on session reset/delete, reducing prompt-cache invalidations.

8 details in Everything

└──▷ BREAKING ON UPGRADE

!The browser SSRF policy now defaults to trusted-network mode: browser.ssrfPolicy.dangerouslyAllowPrivateNetwork defaults to true when unset, and the canonical config key is browser.ssrfPolicy.dangerouslyAllowPrivateNetwork instead of the former browser.ssrfPolicy.allowPrivateNetwork. Run openclaw doctor --fix to migrate the legacy key automatically.

v2026.2.22 Feb 23, 2026 · release notes

OpenClaw v2026.2.22 adds Mistral provider support, Synology Chat channel, multilingual FTS memory, and a new --dry-run updater CLI.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.22 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.22

└──▷ TRY IT

Preview what an update would do — channel selected, plugins synced, restart planned — without actually changing anything.

$ openclaw update --dry-run

Adds Mistral provider integration with memory embeddings and voice support.
Adds native Synology Chat channel plugin with webhook ingress, DM routing, outbound send/media, per-account config, and DM policy controls.
Adds optional built-in auto-updater (update.auto.*) with stable rollout delay/jitter and beta hourly cadence, default-off.
Adds openclaw update --dry-run to preview channel/tag/target/restart actions without mutating config or installing.
Adds Spanish and Portuguese stop-word filtering for FTS-only memory query expansion.

+5 more show less

Adds Japanese-aware query expansion tokenization and stop-word filtering (including mixed ASCII + katakana) for FTS-only memory search.
Adds Korean stop-word filtering and particle-aware keyword extraction (including mixed Korean/English stems) for FTS-only memory search.
Adds Arabic stop-word filtering for FTS-only memory query expansion.
Adds tag-aware settings filtering and improved config labels/help copy in the dashboard config screen.
Adds explicit auth.deviceToken support in gateway connect frames.

10 details in Everything

└──▷ BREAKING ON UPGRADE

!The bundled food-order skill is removed from this repo; it must now be managed and installed from ClawHub instead.

v2026.2.21 Feb 21, 2026 · release notes

OpenClaw v2026.2.21 adds Gemini 3.1, Volcano Engine/BytePlus providers, Discord voice channels, subagent threading, and per-channel model overrides.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.21 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.21

└──▷ TRY IT

Join a Discord voice channel for realtime voice conversations using the new /vc command.

$ /vc join

Enable Telegram streaming with the simplified boolean config and set a per-channel model override.

yaml

channels:
  telegram:
    streaming: true
  modelByChannel:
    telegram: google/gemini-3.1-pro-preview

Adds Gemini 3.1 support via google/gemini-3.1-pro-preview model identifier.
Adds Volcano Engine (Doubao) and BytePlus as providers/models (including coding variants) with interactive and non-interactive onboarding auth flows keyed to volcengine-api-key.
Adds per-account/channel defaultTo outbound routing fallback so openclaw agent --deliver can send without requiring an explicit --reply-to when a default target is configured.
Adds per-channel model overrides via channels.modelByChannel, surfaced in /status output.
Simplifies Telegram preview streaming config to a single boolean channels.telegram.streaming with auto-mapping of legacy streamMode values.

+12 more show less

Adds Discord stream preview mode for live draft replies with partial/block options and configurable chunking.
Adds configurable lifecycle status reactions for Discord and Telegram covering queued/thinking/tool/done/error phases with a shared controller and emoji/timing overrides.
Adds Discord voice channel join, leave, and status via the /vc command, plus auto-join configuration for realtime voice conversations.
Adds configurable ephemeral defaults for Discord slash-command responses.
Supports updating Discord forum available_tags via channel edit actions for forum tag management.
Includes channel topics in trusted inbound metadata on new Discord sessions.
Adds thread-bound subagent sessions on Discord with per-thread focus/list controls and thread-bound continuation routing for spawned helper agents.
Defaults subagent spawn depth to maxSpawnDepth=2, enabling depth-1 orchestrator spawning by default.
Adds owner-ID obfuscation using a dedicated HMAC secret configured via ownerDisplaySecret, decoupled from gateway token handling.
Switches gateway lock and tool-call synthetic IDs from SHA-1 to SHA-256 for a stronger hash basis while keeping deterministic behavior and lock key format.
Adds model fallback lifecycle visibility in verbose logs, /status active-model context with fallback reason, and WebUI fallback indicators.
Adds non-blocking dead-code scans in CI via Knip/ts-prune/ts-unused-exports to surface unused dependencies and exports earlier.

17 details in Everything

v2026.2.19 Feb 19, 2026 · release notes

OpenClaw v2026.2.19 adds Apple Watch support, APNs push delivery, paired-device hygiene CLI commands, and gateway HTTP no-auth audit findings.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.19 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.19

└──▷ TRY IT

Remove a specific paired device from the gateway to revoke its access.

$ openclaw devices remove <device-id>

Clear all pending paired-device requests in one shot — useful during a security sweep or device reset.

$ openclaw devices clear --yes --pending

Adds Apple Watch companion MVP with watch inbox UI, notification relay, and gateway command surfaces for watch status and send flows.
Adds openclaw devices remove and openclaw devices clear --yes [--pending] CLI commands plus device.pair.remove gateway flow for paired-device hygiene.
Adds APNs push registration and notification-signing configuration for iOS node delivery.
Adds a push-test pipeline (push.test) for APNs delivery validation in gateway flows.
Adds gateway.http.no_auth security audit findings when gateway.auth.mode="none" exposes Gateway HTTP APIs, with loopback-warning and remote-exposure-critical severities.

+1 more show less

Enables wake of disconnected iOS nodes via APNs before nodes.invoke and auto-reconnects gateway sessions on silent push wake to reduce backgrounded-app invoke failures.

6 details in Everything

v2026.2.17 Feb 18, 2026 · release notes

OpenClaw v2026.2.17 adds 1M-context Anthropic support, Slack streaming, Discord slash commands, cron webhooks, and dozens of new platform capabilities.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.17 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.17

└──▷ TRY IT

Add a top-of-hour cron job with a deterministic stagger to avoid thundering-herd spikes, delivering results to a webhook.

$ openclaw cron add --schedule "0 * * * *" --stagger 90s --delivery.mode webhook --webhook https://example.com/hook "Summarize overnight alerts"

Adds opt-in 1M context beta header for Anthropic Opus/Sonnet via params.context1m: true (maps to anthropic-beta: context-1m-2025-08-07).
Supports Anthropic Claude Sonnet 4.6 (anthropic/claude-sonnet-4-6) with forward-compat fallback to Sonnet 4.5.
Adds /subagents spawn chat command for deterministic subagent activation.
Adds iOS share extension forwarding shared URL/text/image content directly to gateway agent.request with delivery-route fallback and optional receipt acknowledgements.
Adds iOS Talk Mode Background Listening toggle to keep Talk Mode active while the app is backgrounded.

+25 more show less

Adds iOS Talk Mode Voice Directive Hint toggle to disable ElevenLabs voice-switching instructions and save tokens.
Adds native Slack single-message text streaming via chat.startStream/appendStream/stopStream with replyToMode threading and automatic fallback.
Adds configurable Slack streaming modes for draft previews.
Adds inline button style support (primary|success|danger) for Telegram interactive messages.
Surfaces Telegram user message reactions as system events with configurable channels.telegram.reactionNotifications scope.
Supports replyToId on outbound iMessage text/media sends.
Adds intent-first tool detail views and exec summaries in the Web UI.
Exposes native Discord /exec command options (host/security/ask/node) with autocomplete and structured inputs.
Allows reusable Discord interactive components (buttons, selects, forms) with components.reusable=true.
Adds per-button allowedUsers allowlist for Discord interactive components.
Adds separate per-job cron webhook delivery (delivery.mode = "webhook") with valid HTTP(S) URL enforcement.
Adds openclaw cron add/edit --stagger <duration> and --exact flags for per-job timing control, with auto-migration of existing jobs to persisted schedule.staggerMs.
Logs per-run model/provider usage telemetry in cron run logs/webhooks and adds a local usage report script for aggregating token usage by job.
Adds URL allowlists for web_search and web_fetch tools.
Adds extraArgs config for custom Chrome launch arguments in the browser integration.
Pre-caches inbound greeting TTS for faster first playback in voice calls.
Enables tool_stream by default for Z.AI real-time tool call streaming, with opt-out via params.tool_stream: false.
Adds before_agent_start plugin hook for model/provider overrides before resolution.
Adds Mattermost emoji reaction actions and reaction event notifications with an explicit boolean remove flag.
Adds full-text search fallback plus query expansion for memory search.
Supports per-model thinkingDefault overrides in model config.
Enables llms.txt discovery in default agent behavior.
Adds OpenAI Codex CLI auth provider integration.
Adds Feishu Bitable create-app and create-field tools for automation workflows.
Adds optional OPENCLAW_INSTALL_BROWSER Docker build arg to preinstall Chromium + Xvfb, avoiding runtime Playwright installs.

30 details in Everything

v2026.2.15 Feb 16, 2026 · release notes

OpenClaw v2026.2.15 adds nested sub-agents, Discord Components v2, plugin LLM hooks, per-channel ack reactions, and cron webhook auth.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.15 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.15

└──▷ USE IT

Allow sub-agents to spawn their own child agents up to two levels deep, capped at 5 children each — useful for parallelizing multi-stage research or remediation pipelines.

yaml

agents:
  defaults:
    subagents:
      maxSpawnDepth: 2
      maxChildrenPerAgent: 5

Secure outbound cron webhooks so only authorized receivers can accept finished-run notifications.

yaml

cron:
  webhookToken: "<your-secret-token>"
  notify: true

Adds nested sub-agent spawning with configurable depth via agents.defaults.subagents.maxSpawnDepth and maxChildrenPerAgent limit.
Enables Discord rich interactive agent prompts with Components v2 (buttons, selects, modals, and attachment-backed file blocks).
Exposes llm_input and llm_output hook payloads so plugins can observe prompt context and model output usage details.
Adds per-channel acknowledgment reaction overrides at account/channel level for Slack, Discord, and Telegram to support platform-specific emoji formats.
Adds finished-run webhook delivery toggle (notify) and dedicated webhook auth token support (cron.webhookToken) for outbound cron webhook posts.

5 details in Everything

v2026.2.14 Feb 15, 2026 · release notes

OpenClaw v2026.2.14 adds Telegram poll sending, DM access-control config aliases, Discord exec-approval channel targeting, and browser-container bind mounts.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.14 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.14

└──▷ USE IT

Route Discord exec approval prompts to a dedicated #approvals channel instead of DM, so the whole team can review.

yaml

# in your openclaw config
channels:
  discord:
    execApprovals:
      target: channel

Migrate legacy DM policy keys to the new aliases automatically during an upgrade.

$ openclaw doctor --fix

Adds openclaw message poll subcommand for Telegram with duration, silent delivery, and anonymity controls.
Adds dmPolicy and allowFrom config aliases for Slack/Discord DM access control; legacy dm.policy/dm.allowFrom keys remain supported and openclaw doctor --fix can migrate them.
Adds channels.discord.execApprovals.target to route Discord exec approval prompts to a channel, or both DM and channel simultaneously.
Adds sandbox.browser.binds to configure browser-container bind mounts independently from exec containers.
Adds debug logging for Discord message routing decisions, improving --debug tracing output.

5 details in Everything

v2026.2.13 Feb 14, 2026 · release notes

OpenClaw v2026.2.13 adds Discord voice messages, Hugging Face provider support, configurable presence status, and Slack thread-ownership gating.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.13 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.13

Adds Discord voice message sending with waveform previews from local audio files, including silent delivery.
Adds configurable Discord presence status, activity, type, and URL (custom status defaults to activity text).
Adds Slack/plugin thread-ownership outbound gating via message_sending hooks, with @-mention bypass tracking and cancel/modify behavior.
Adds first-class Hugging Face Inference provider support with onboarding auth flow, API key configuration, and default-model selection.
Adds pre-prompt context diagnostics for agent embedded runner calls (messages, systemPromptChars, promptChars, provider/model, session file) to aid overflow debugging.

+4 more show less

Adds synthetic catalog support for the hf:zai-org/GLM-5 agent model.
Adds security audit misconfiguration checks for sandbox Docker config, ineffective gateway.nodes.denyCommands entries, minimal tool-profile overrides, and permissive extension-plugin tool reachability.
Blocks high-risk tools (sessions_spawn, sessions_send, gateway, whatsapp_login) from HTTP /tools/invoke by default, with gateway.tools.{allow,deny} overrides.
Adds security audit distinction between external webhooks (hooks.enabled) and internal hooks (hooks.internal.enabled) in attack-surface summaries.

9 details in Everything

└──▷ BREAKING ON UPGRADE

!Canvas IP-based auth fallback now only accepts machine-scoped addresses (RFC1918, link-local, ULA IPv6, CGNAT); public-source IP matches now require bearer token auth.

v2026.2.12 Feb 13, 2026 · release notes

OpenClaw v2026.2.12 adds local-time log display, Telegram blockquote rendering, and Z.AI/MiniMax provider expansions.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.12 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.12

└──▷ TRY IT

Tail agent logs with timestamps converted to your local timezone so you can correlate events without mental UTC math.

$ openclaw logs --local-time

Adds openclaw logs --local-time flag to display log timestamps in the local timezone with ±HH:MM offsets.
Telegram: renders blockquotes as native <blockquote> tags instead of stripping them.
Onboarding: adds Z.AI endpoint-specific auth choices (zai-coding-global, zai-coding-cn, zai-global, zai-cn) and expands default Z.AI model wiring.
Onboarding: adds MiniMax M2.5 and M2.5-Lightning model entries, updates default/recommended models from M2.1 to M2.5, and includes minimax-m2.5 in modern model filtering.
Discord: allows channel-edit to archive/lock threads and set auto-archive duration.

5 details in Everything

└──▷ BREAKING ON UPGRADE

!POST /hooks/agent now rejects payload sessionKey overrides by default; set hooks.defaultSessionKey (recommended with hooks.allowedSessionKeyPrefixes: ["hook:"]) to keep fixed hook context, or explicitly set hooks.allowRequestSessionKey: true to restore legacy behavior.

v2026.2.9 Feb 9, 2026 · release notes

OpenClaw v2026.2.9 adds iOS alpha node app, BlueBubbles channels, Grok web search, agent management RPCs, and OPENCLAW_HOME path override.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.9 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.9

└──▷ TRY IT

Override OpenClaw's home directory at runtime — useful in containerized or multi-tenant deployments where the default home path is not appropriate.

$ OPENCLAW_HOME=/opt/openclaw-data openclaw start

Adds iOS alpha node app with setup-code onboarding flow.
Adds comprehensive BlueBubbles channel support with channel cleanup.
Adds device pairing and phone control plugins, including Telegram /pair command and iOS/Android node controls.
Adds Grok (xAI) as a web_search provider.
Adds agent management RPC methods for the web UI: agents.create, agents.update, and agents.delete.

+3 more show less

Adds Compaction divider display in web UI chat history.
Includes runtime shell in agent envelopes.
Adds OPENCLAW_HOME environment variable for overriding the home directory used by internal path resolution.

8 details in Everything

v2026.2.6 Feb 7, 2026 · release notes

OpenClaw v2026.2.6 adds xAI/Grok provider, Anthropic Opus 4.6 & GPT-5.3-Codex support, Voyage AI memory, and a token usage dashboard.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.6 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.6

Adds xAI (Grok) as a supported provider.
Supports Anthropic Opus 4.6 and OpenAI Codex gpt-5.3-codex models with forward-compat fallbacks.
Adds native Voyage AI support for memory.
New token usage dashboard in the Web UI.
CLI help output now sorts commands alphabetically.

5 details in Everything

v2026.2.3 Feb 5, 2026 · release notes

OpenClaw v2026.2.3 adds Cron announce delivery mode, per-channel response prefixes, and new AI provider onboarding for Cloudflare and Moonshot.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.3 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.3

└──▷ TRY IT

Run a one-shot Cron job and retain it after it completes successfully, useful for auditing or debugging.

$ openclaw cron run --at 2026-03-01T09:00:00Z --keep-after-run

Adds announce delivery mode for isolated Cron jobs, configurable via CLI and Control UI.
Defaults isolated Cron jobs to announce delivery mode.
Accepts ISO 8601 schedule.at in Cron tool inputs for scheduling.
Deletes one-shot Cron jobs after successful execution by default; new --keep-after-run flag preserves them.
Suppresses messaging tools during announce delivery so summaries post consistently.

+3 more show less

Adds per-channel and per-account responsePrefix overrides across channels.
Adds Cloudflare AI Gateway as a provider option in onboarding setup.
Adds Moonshot (.cn) as an auth choice in onboarding, preserving the China base URL when keeping defaults.

8 details in Everything

└──▷ BREAKING ON UPGRADE

!Isolated Cron jobs are hard-migrated to announce/none delivery; legacy post-to-main and payload delivery fields and atMs inputs are dropped.

v2026.2.2 Feb 4, 2026 · release notes

OpenClaw v2026.2.2 adds Feishu/Lark integration, an Agents dashboard, QMD memory backend, and configurable subagent thinking levels.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.2

└──▷ USE IT

Set a default thinking level for all subagents, overriding per-agent as needed — useful for tuning reasoning depth across a fleet.

yaml

# In your OpenClaw config file:
agents:
  defaults:
    subagents:
      thinking: high
  list:
    - name: fast-agent
      subagents:
        thinking: low

Adds Feishu/Lark plugin support, enabling OpenClaw agents to operate in Feishu workspaces.
New Agents dashboard in the Web UI for managing agent files, tools, skills, models, channels, and cron jobs.
Introduces opt-in QMD backend for workspace memory storage.
Adds a healthcheck skill and bootstrap audit guidance for security posture validation.
Supports setting a default subagent thinking level via agents.defaults.subagents.thinking (and per-agent agents.list[].subagents.thinking).

5 details in Everything

v2026.2.1 Feb 2, 2026 · release notes

OpenClaw v2026.2.1 adds agent system prompt guardrails, TLS 1.3 enforcement, Discord thread routing, and gateway timestamp injection.

└──▷ GET THIS VERSION

$ git clone --branch v2026.2.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.1

Adds system prompt safety guardrails for Agents.
Extends CreateAgentSessionOptions with systemPrompt, skills, and contextFiles parameters.
Enforces TLS 1.3 minimum for all TLS listeners on the Gateway.
Injects timestamps into agent and chat.send messages at the Gateway layer.
Adds OpenRouter app attribution headers for Agents.

+2 more show less

Enables Discord channels to inherit thread parent bindings for message routing.
Adds shared pairing store support for Telegram.

7 details in Everything

└──▷ BREAKING ON UPGRADE

!The cacheControlTtl field is renamed to cacheRetention (back-compat mapping is included, but configurations referencing cacheControlTtl should be migrated).

v2026.1.30 Jan 31, 2026 · release notes

OpenClaw v2026.1.30 adds shell completion, per-agent model status filtering, Kimi K2.5, and MiniMax OAuth.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.30 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.30

└──▷ TRY IT

Set up shell completions for Zsh so OpenClaw subcommands and flags autocomplete in your terminal.

$ openclaw completion zsh

Check model availability scoped to a specific agent instead of seeing the full catalog.

$ openclaw models status --agent <agent-name>

Adds completion command with support for Zsh, Bash, PowerShell, and Fish, plus auto-setup during postinstall/onboarding.
Adds per-agent filtering to models status via new --agent flag.
Adds Kimi K2.5 to the synthetic model catalog.
Adds MiniMax OAuth plugin with onboarding option.
Switches Kimi Coding to a built-in provider with normalized OAuth profile email handling.

5 details in Everything

v2026.1.29 Jan 30, 2026 · release notes

OpenClaw v2026.1.29 adds Venice API key onboarding, Telegram sticker/edit/quote support, Discord gateway intents, per-sender tool policies, and more.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.29 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.29

Adds Venice API key support to the non-interactive onboarding flow.
Adds a dangerous Control UI device auth bypass flag with audit warnings to the Gateway.
Adds per-sender group tool policies with precedence control.
Adds extra paths support for memory indexing (symlinks ignored).
Adds per-account DM session scope with documented multi-account isolation.

+21 more show less

Adds Node module compile cache for faster CLI startup.
Adds Telegram sticker receive/send with vision caching and pixel forwarding to vision models.
Adds Telegram support for editing sent messages via message(action="edit").
Adds Telegram support for quote replies in the message tool and inbound context.
Adds optional silent send flag to Telegram (disables notifications).
Adds caption param support for Telegram media sends.
Adds Telegram plugin sendPayload channelData support (media/buttons) with plugin command validation.
Adds configurable privileged gateway intents for Discord presences and members.
Adds multi-image input support to the Nano Banana Pro skill.
Adds Google auth URL display as a copyable link after ASCII prompt.
Adds agent message summarization during compaction safeguard pruning.
Routes browser control via gateway/node and derives browser ports from gateway.port.
Routes browser.request via node proxies when available, honoring proxy timeouts.
Warns when gateway is exposed without authentication.
Warns when hook tokens are passed via query params and documents header auth preference.
Groups /help and /commands output with Telegram paging.
Supports tools.exec.safeBins in exec allowlist checks.
Renames npm package and CLI to openclaw with a compatibility shim; moves extensions to @openclaw/* scope.
Switches Matrix plugin SDK to @vector-im/matrix-bot-sdk.
Applies config.env before ${VAR} substitution in config processing.
Limits project-local node_modules/.bin PATH preference to debug builds to reduce PATH hijacking risk on macOS.

26 details in Everything

└──▷ BREAKING ON UPGRADE

!Gateway auth mode none is removed; gateway now requires token/password (Tailscale Serve identity still allowed). Any setup using auth: none or the gateway auth off choice will stop working on upgrade.
!The standalone browser control command and control URL config are removed; browser control is now routed via gateway/node.

v2026.1.24 Jan 25, 2026 · release notes

OpenClaw v2026.1.24 adds LINE channel support, Edge TTS fallback, in-chat exec approvals via /approve, Brave freshness filtering, and gateway config.patch.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.24 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.24

└──▷ TRY IT

Approve a pending exec command directly in chat instead of switching to another interface.

$ /approve

Set TTS to activate only for inbound messages in a session, then override per-session.

$ /tts inbound

Adds LINE channel plugin (Messaging API) with rich replies, quick replies, and plugin HTTP registry.
Adds Edge TTS provider as a keyless fallback with MP3 retry on format failures.
Adds TTS auto mode enum (off/always/inbound/tagged) with per-session /tts override.
Adds in-chat exec approval via /approve slash command across all channels including plugins.
Adds channels.telegram.linkPreview config key to toggle outbound link previews on Telegram.

+4 more show less

Adds Telegram DM topics as separate sessions with stable history limits via thread suffixes.
Adds Brave freshness filter parameter for time-scoped web search results.
Adds diagnostic flags for targeted debug logging, configurable via config and env override.
Refreshes Control UI dashboard design system (typography, colors, spacing).

9 details in Everything

v2026.1.23 Jan 24, 2026 · release notes

OpenClaw v2026.1.23 adds a /tools/invoke HTTP endpoint, Tlon/Urbit channel support, Fly.io deploy, and new CLI system controls.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.23 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.23

└──▷ TRY IT

Check live auth status for all configured profiles to catch expired credentials before they cause silent failures.

$ clawdbot models status

Manage system events and heartbeat controls from the CLI after migrating away from the removed wake command.

$ clawdbot system

New /tools/invoke HTTP endpoint on the Gateway for direct tool calls with auth and tool-policy enforcement.
New Tlon/Urbit channel plugin supporting DMs, group mentions, and thread replies.
Moves Telegram TTS into core and enables model-driven TTS tags by default for expressive audio replies.
Adds per-channel heartbeat visibility controls (OK / alerts / indicator).
Adds Fly.io deployment support with a dedicated guide.

+8 more show less

New clawdbot system CLI subcommand for system events and heartbeat controls; standalone wake command removed.
Adds live auth probes to clawdbot models status for per-profile credential verification.
Gateway now restarts by default after clawdbot update; new --no-restart flag skips it.
New optional llm-task JSON-only tool plugin for LLM-driven workflows.
Per-group tool allow/deny policies now work across built-in and plugin channels.
Adds Bedrock auto-discovery defaults with config overrides.
Browser node-host proxy auto-routing for remote gateways, configurable per gateway/node.
Per-channel Markdown table conversion: bullets for Signal/WhatsApp, code blocks elsewhere.

13 details in Everything

└──▷ BREAKING ON UPGRADE

!The standalone wake command is removed; its functionality moves to clawdbot system.

v2026.1.22 Jan 23, 2026 · release notes

OpenClaw v2026.1.22 adds Antigravity usage tracking, Slack reply threading overrides, BlueBubbles voice memo support, and a richer onboarding TUI.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.22 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.22

Adds Antigravity usage tracking to the status output.
Adds replyToModeByChatType config for per-chat-type reply threading overrides in Slack.
Adds asVoice support for MP3/CAF voice memos in BlueBubbles sendAttachment.
Adds new onboarding flow with hatch choice (TUI/Web/Later), token explainer, background dashboard seed on macOS, and showcase link.
Compaction safeguard now uses adaptive chunking, progressive fallback, UI status display, and retries.

5 details in Everything

v2026.1.21 Jan 22, 2026 · release notes

OpenClaw v2026.1.21 adds Lobster typed-workflow plugin, exec approval modes, Signal read receipts, MSTeams file uploads, and new CLI gateway/node commands.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.21 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.21

└──▷ TRY IT

Check reachability of a gateway node after reorganizing service commands under the new clawdbot gateway namespace.

$ clawdbot gateway probe

Run the interactive update wizard to select channels, run preflight checks, and restart cleanly after rebasing.

$ clawdbot update wizard

Set per-channel idle timeouts so busy channels don't evict sessions prematurely.

yaml

sessions:
  channelIdleMinutes:
    signal: 60
    discord: 30

Adds Lobster optional plugin tool for typed workflows and approval gates.
Adds custom assistant identity and avatars configurable via the Control UI and agent config.
Adds clawdbot update wizard with interactive channel selection, restart prompts, and preflight checks.
Adds /models command and expands clawdbot models paging for improved model listing UX.
Moves gateway service commands under clawdbot gateway, flattens node service commands under clawdbot node, and adds gateway probe for reachability checks.

+12 more show less

Adds elevated exec approval modes (ask/full) with allowlist gating and approval tables rendered on write.
Adds gateway/node targeting, wildcard agent allowlists, and target details to exec approvals.
Adds per-channel idle duration configuration via sessions.channelIdleMinutes.
Adds cache.ttlPrune mode with auth-aware defaults to reduce token spend on cold requests.
Adds per-channel debounce overrides for auto-reply queue behavior.
Adds wildcard channel config support for Discord.
Adds typing indicators and DM read receipts to the Signal channel via signal-cli.
Adds file uploads, adaptive cards, and attachment handling to the MSTeams channel.
Adds explicit session keys and active hours support for Heartbeat.
Adds cache trace config for debugging diagnostics.
Adds macOS Settings refresh: location access in Permissions, connection mode in menu.
Enables nodes to run exec-style and exposes PATH in node status/describe and bootstrap.

17 details in Everything

└──▷ BREAKING ON UPGRADE

!The Control UI now rejects insecure HTTP without device identity by default; use HTTPS (Tailscale Serve) or set gateway.controlUi.allowInsecureAuth: true to allow token-only auth.
!Envelope and system event timestamps now default to host-local time instead of UTC.

v2026.1.20 Jan 21, 2026 · release notes

OpenClaw v2026.1.20 adds ACP IDE integration, hybrid memory search, Nostr/BlueBubbles channels, OpenResponses API, and headless node hosting.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.20 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.20

└──▷ TRY IT

Wire up an IDE integration using the new ACP subcommand — useful for connecting editors like VS Code or JetBrains to a running clawdbot instance.

$ clawdbot acp

Debug ACP protocol messages interactively before shipping an IDE integration.

$ clawdbot acp client

Start a headless node host so remote agents can invoke system commands via system.run/system.which.

$ clawdbot node start

Adds clawdbot acp subcommand for IDE integrations via the Agent Communication Protocol.
Adds clawdbot acp client interactive harness for debugging ACP connections.
Adds headless node host (clawdbot node start) supporting system.run/system.which for remote execution.
Adds node daemon service management with install, status, start, stop, and restart lifecycle commands.
Adds hybrid BM25 + vector (FTS5) memory search with weighted merging and fallback.

+34 more show less

Adds SQLite embedding cache to accelerate memory reindexing and frequent updates.
Adds OpenAI batch indexing for embeddings with parallel jobs (default concurrency: 2) and 2-second polling.
Adds native Gemini embeddings provider for memory search.
Adds --verbose flag for detailed memory status and batch indexing logs.
Adds /v1/responses (OpenResponses) API endpoint with item-based input, semantic streaming events, file/image inputs, tool_choice, usage, and output limits.
Adds /usage cost summaries and macOS menu cost charts.
Adds the Nostr channel plugin with profile management and onboarding defaults.
Ships the bundled BlueBubbles channel plugin (disabled by default).
Adds Zalouser channel with dock metadata, config schema, and status reporting.
Migrates Matrix integration to matrix-bot-sdk with E2EE support, location handling, and group allowlist upgrades.
Adds HTTP webhook mode for Slack via Bolt HTTP receiver.
Enriches Telegram forwarded-message context with normalized origin details and legacy fallback.
Exposes Discord /skill command globally with fallback when native command limits are exceeded.
Adds Qwen Portal OAuth provider support.
Adds plugin slots with a dedicated memory slot selector.
Adds optional agent tools with explicit allowlists and a plugin tool authoring guide.
Requires manifest-embedded config schemas with preflight validation warnings for plugins.
Auto-enables bundled channel/provider plugins when configuration is present.
Adds daily session reset policy with per-type overrides and idle windows (default 4am local).
Allows sessions_spawn to override thinking level for sub-agent runs.
Adds security warning when models ≤300B run without sandboxing while web tools are enabled.
Adds host/security/ask routing for gateway and node exec via Exec tool.
Adds /exec directive for per-session exec defaults (host/security/ask/node).
Migrates exec approvals to ~/.clawdbot/exec-approvals.json with per-agent allowlists, skill auto-allow toggle, approvals UI, and node exec lifecycle events.
Adds TUI syntax highlighting for code blocks.
Adds TUI session picker with derived titles, fuzzy search, relative timestamps, and last-message preview.
Adds searchable model picker in the TUI for faster model selection.
Adds input history (up/down navigation) for submitted messages in the TUI.
Adds copy-as-markdown with error feedback to the Control UI.
Adds skill downloads with OS-filtered options.
Adds the local sherpa-onnx-tts skill.
Adds config timestamp stamping and warns when the config file is newer than the running build.
Migrates Android node transport to the Gateway WebSocket protocol with TLS pinning and gateway discovery naming.
Syncs plugin sources on channel switches and updates npm-installed plugins during clawdbot update.

39 details in Everything

└──▷ BREAKING ON UPGRADE

!Invalid or unknown config entries are now rejected and will prevent the gateway from starting; run clawdbot doctor --fix to repair, then clawdbot plugins update if you use plugins.

v2026.1.16-2 Jan 17, 2026 · release notes

OpenClaw v2026.1.16-2 adds a hooks system, inbound media understanding, PTY exec sessions, web-search locale params, and cross-platform session linking.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.16-2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.16-2

└──▷ TRY IT

Install a hook pack from npm to automate event-driven workflows in your OpenClaw deployment.

$ clawdbot hooks install @myorg/my-hookpack

Adds a hooks system with bundled hooks, CLI tooling (clawdbot hooks install/update), and hook pack installs from npm/path/zip/tar via clawdbot.hooks manifests.
Adds inbound media understanding (image/audio/video) with provider and CLI fallbacks.
Adds Zalo Personal plugin (@clawdbot/zalouser) and unifies the channel directory for plugins.
Adds Vercel AI Gateway auth choice with onboarding updates.
Adds session.identityLinks for cross-platform DM session linking.

+16 more show less

Adds country and language parameters to web search (schema + Brave API).
Adds exec PTY support for interactive terminal sessions.
Adds tmux-style process send-keys and bracketed paste helpers, plus process submit for sending CR in PTY sessions.
Responds to PTY cursor position queries to unblock interactive TUIs.
Adds Firecrawl fallback for web_fetch when configured, using bot-circumvention and cache by default.
Sends Chrome-like headers by default for web_fetch to improve extraction on bot-sensitive sites.
Adds bundled Antigravity, Gemini CLI OAuth, and Copilot Proxy provider plugins (disabled by default, overridable by installed versions).
Adds zip installs and --link flag for plugins to avoid copying local paths.
Adds user-invocable skill commands and expanded skill command registration.
Adds remote attachment support for iMessage on VM/SSH deployments.
Supports env var substitution in config values.
Adds per-agent session summaries and account-level health details with selective probes.
Allows deleting sessions from the Control UI.
Mirrors delivered outbound text/media into session transcripts.
Enables exec exit notifications by default and auto-migrates legacy tools.bash to tools.exec.
Includes tool outputs in verbose mode with expanded verbose tool feedback.

21 details in Everything

└──▷ BREAKING ON UPGRADE

!clawdbot message and the message tool now require target; the to and channelId destination parameters are dropped.
!Channel auth now prefers config over env for Discord/Telegram/Matrix; env is fallback only.
!Legacy chatType: "room" is dropped; use chatType: "channel".
!Legacy provider-specific target resolution fallbacks are removed; target resolution is centralized with plugin hints and directory lookups.
!clawdbot hooks is now clawdbot webhooks; hooks live under clawdbot hooks.
!clawdbot plugins install <path> now copies into ~/.clawdbot/extensions; use --link to keep path-based loading.

v2026.1.15 Jan 16, 2026 · release notes

OpenClaw v2026.1.15 adds plugin OAuth flows, per-agent heartbeats, session DM isolation, Telegram reactions, and browser aria-ref snapshots.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.15 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.15

└──▷ TRY IT

Authenticate a plugin-provided model provider (OAuth or API key) without leaving the CLI.

$ clawdbot models auth login

Check your current model tier selections for security weaknesses flagged by the new audit warnings.

$ clawdbot security audit

Get structured JSON output from daemon lifecycle commands to integrate with scripts or CI pipelines.

$ clawdbot daemon status --json

Adds clawdbot models auth login command and a provider auth registry for plugin-driven OAuth and API key flows.
Adds session.dmScope configuration for multi-user DM isolation with security audit warnings.
Adds per-agent heartbeat configuration with 24-hour duplicate alert suppression.
Adds clawdbot security audit warnings for weak model tiers (Haiku, below GPT-5, below Claude 4.5).
Stores app node auth tokens encrypted via Keychain (macOS) and SecurePrefs (other platforms).

+18 more show less

Adds --json output flag for clawdbot daemon lifecycle and install commands.
Adds snapshot refs=aria (Playwright aria-ref IDs) enabling self-resolving refs across snapshot → act browser workflows.
Adds remoteCdpTimeoutMs and remoteCdpHandshakeTimeoutMs settings to tune remote CDP reachability timeouts.
Preserves auth and query tokens for remote CDP endpoints and passes Basic auth for CDP HTTP/WS connections.
Adds bidirectional Telegram reaction support with configurable notifications and agent guidance.
Allows custom commands in the Telegram bot menu, merged with native commands.
Adds system.which tool on macOS for prompt-free remote skill discovery with gateway fallback to system.run.
Normalizes Slack/Discord message timestamps with timestampMs and timestampUtc fields while retaining raw provider fields.
Adds a Current Date & Time system prompt section with configurable time format (auto/12/24) for agents.
Debounces rapid inbound messages across channels with per-connector override support.
Allows media-only sends via CLI/tool and shows Telegram voice recording status for voice notes.
Surfaces provider usage headers in /status endpoint and clawdbot models status command.
Microsoft Teams is now a plugin; must be installed via clawdbot plugins install @clawdbot/msteams.
Supports CLAWDBOT_STATE_DIR environment variable for Windows task scripts.
TUI now shows provider/model labels for the active session and default model.
Allows Discord emoji and sticker uploads and channel actions in config defaults.
Allows allowlisted Discord guilds without channel lists to receive messages when groupPolicy="allowlist".
Auto-infers SSH targets in gateway status using ssh-config awareness on macOS.

23 details in Everything

└──▷ BREAKING ON UPGRADE

!iOS minimum version is now 18.0 (was lower); setups targeting older iOS versions will break.
!Microsoft Teams integration is now a plugin — existing setups will break until @clawdbot/msteams is installed via clawdbot plugins install @clawdbot/msteams.

v2026.1.14-1 Jan 15, 2026 · release notes

OpenClaw v2026.1.14-1 adds web search/fetch via Brave API, Chrome extension browser control, Matrix/Plivo/Zalo channel plugins, and expanded security auditing.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.14-1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.14-1

└──▷ TRY IT

Enable web search in a session — useful when you need the agent to pull live threat intel or CVE details from the web.

$ clawdbot configure --section web

Start a remote browser control session so the agent can drive your local Chrome instance for recon or authenticated app testing.

$ clawdbot browser serve

Audit your clawdbot configuration for security issues and automatically tighten sensitive state paths in one pass.

$ clawdbot security audit --fix

Adds web_search and web_fetch tools backed by the Brave API, with first-time setup guidance in onboarding and clawdbot configure --section web.
Enables web_fetch by default (unless explicitly disabled in config).
Adds Chrome extension relay takeover mode (toolbar button) and clawdbot browser serve for remote browser control, gated by browser.controlToken.
Adds clawdbot browser extension install/path to install the extension and copy its path to the clipboard.
Ships a built-in chrome profile for extension relay that starts automatically when running locally; defaults browser.defaultProfile to chrome.

+15 more show less

Adds channel plugin support via gateway HTTP hooks, including a new onboarding plugin install flow.
Adds Matrix channel plugin (external) with docs and onboarding hooks.
Adds Plivo voice call provider (no SDK dependency).
Adds Zalo plugin.
Expands clawdbot security audit with additional checks and a SECURITY.md reporting policy.
Adds detect-secrets CI scan and baseline guidance.
Adds a security checkpoint prompt during onboarding (docs link + sandboxing hint); requires --accept-risk for --non-interactive mode.
Adds MiniMax coding plan usage tracking.
Adds channels.<provider>.configWrites gating to control whether channel-initiated config writes are permitted.
Adds channels.whatsapp.sendReadReceipts config option to disable automatic read receipts.
Adds message delete action for Telegram via the message tool.
Supports profile-aware service names for multi-gateway daemon setups.
Adds dynamic template variables to messages.responsePrefix.
Adds optional auth-profile copy prompt on agents add with improved auth error messaging.
Adds per-command CLI doc pages linked from clawdbot <command> --help.

20 details in Everything

└──▷ BREAKING ON UPGRADE

!Onboarding now requires --accept-risk when using --non-interactive mode (new security checkpoint prompt will block non-interactive runs without it).

v2026.1.12 Jan 13, 2026 · release notes

OpenClaw v2026.1.12 adds vector memory search, voice-call plugin parity, ISO-timestamp cron, new AI models, and Tailscale gateway support.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.12 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.12

└──▷ TRY IT

Schedule a one-shot cron job for a specific agent to run at an exact UTC time and delete itself afterward.

$ clawdbot cron add --agent <agentId> --at 2026-02-01T09:00:00Z --delete-after-run "summarize overnight alerts"

Enable Docker bind mounts for sandboxed tool execution so agents can read host paths without a full volume.

yaml

# In your OpenClaw config:
tools:
  sandbox:
    tools:
      - group: default
    docker:
      binds:
        - /host/data:/workspace/data:ro

Adds vector search for agent memories (Markdown-only) backed by a SQLite index, with chunking, lazy sync, file watch, and per-agent enablement/fallback.
New clawdbot memory CLI with memory_search and memory_get tools, returning snippets and line ranges; index stored at ~/.clawdbot/memory/{agentId}.sqlite with watch enabled by default.
Supports custom OpenAI-compatible embedding endpoints and local node-llama-cpp embeddings, with per-agent overrides and provider metadata surfaced in tools and CLI.
Adds Synthetic provider and Moonshot Kimi K2 0905 (plus turbo/thinking variants) to the model catalog.
Cron one-shot schedules now accept ISO timestamps (UTC) with optional delete-after-run; cron jobs can target a specific agent via CLI and macOS Control UI.

+9 more show less

Adds agent compaction mode config with optional safeguard summarization and per-agent model fallbacks.
Adds tool profiles and group shorthands; supports tool-policy groups in tools.sandbox.tools; allows Docker bind mounts via docker.binds.
New browser scrollintoview action in the tools layer; adds xhigh thinking support for GPT-5.2/Codex with safe downgrades.
Adds Tailscale binary discovery, custom bind mode, and probe auth retry to the Gateway/CLI; adds clawdbot dashboard auto-open flow.
Adds Chutes OAuth (PKCE + refresh + onboarding choice) for auth/onboarding.
Adds discord.allowBots config option; routes MiniMax vision to the Coding Plan VLM endpoint with @/path/to/file.png input support.
Allows Tailscale Serve identity headers to satisfy gateway token auth.
Defaults ackMaxChars to 300 so short HEARTBEAT_OK replies stay internal.
Runs clawdbot doctor --non-interactive automatically after git installs and updates.

14 details in Everything

└──▷ BREAKING ON UPGRADE

!Chat providers (Slack/Telegram/WhatsApp/…) are renamed to channels across CLI, RPC, and config; legacy config keys are auto-migrated on load and written back as channels.*.
!The legacy memory tool shorthand is dropped from tool profiles/group shorthands.

v2026.1.11 Jan 12, 2026 · release notes

OpenClaw v2026.1.11 adds a first-class plugin system, voice-call plugin, apply_patch tool, $include config, and cron --model flag.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.11 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.11

└──▷ TRY IT

Install a third-party plugin from a local tarball and verify it loads correctly.

$ clawdbot plugins install ./my-plugin.tgz && clawdbot plugins doctor

Split a large config into separate files to keep provider and agent settings maintainable.

yaml

# clawdbot.config.yaml
$include: ./providers.yaml
$include: ./agents.yaml

Schedule a cron task with a specific model override so high-stakes jobs use a more capable model.

$ clawdbot cron add --model minimax/m2.1 "0 9 * * 1" "Summarise last week's alerts and post to #security"

New plugin extension loader supporting tools, RPC, CLI, and services — with discovery paths, config schema, and Control UI labels (uiHints).
New clawdbot plugins install command (path/tgz/npm) plus list, info, enable, disable, and doctor subcommands for full plugin lifecycle management.
New Voice Call plugin (Twilio/log backend) with start/status RPC, CLI, and tool interfaces.
New apply_patch tool for multi-file edits (experimental; gated by tools.exec.applyPatch; OpenAI-only).
Adds $include directive for modular, split config files.

+13 more show less

Adds --model flag to cron add and cron edit commands.
New pre-compaction memory flush config (agents.defaults.compaction.*) with soft threshold and system prompt to persist durable memories before auto-compaction.
Per-DM history limit overrides via dmHistoryLimit at the provider level.
Discord channel and category management actions now exposed in the message tool.
Gateway now requires client.id in WebSocket connect params; uses client.instanceId for presence de-duplication.
Control UI Config tab adds model presets (MiniMax M2.1, GLM 4.7, Kimi) for one-click provider setup.
Auto-reply compact /model picker now shows models alongside available providers and displays provider endpoints in /model status.
Bundles skill-creator skill to guide creating and packaging skills.
Installer supports CLAWDBOT_NO_ONBOARD=1 for non-interactive installs and --install-method git|npm flag with auto-detection of source checkouts.
Installer adds install.sh --help with flags, env vars, and git install hint.
macOS: prompts to install the global clawdbot CLI when missing in local mode, installing via clawd.bot/install-cli.sh.
Onboarding adds Moonshot AI (Kimi K2) auth choice and MiniMax M2.1 Lightning auth choice.
CLI/Onboarding prompts to reuse detected API keys for Moonshot, MiniMax, Z.AI, Gemini, Anthropic, and OpenCode.

18 details in Everything

└──▷ BREAKING ON UPGRADE

!The bash tool is renamed to exec (a config alias is maintained, but tooling referencing the old name bash should be verified).
!Gateway now requires client.id in WebSocket connect params; existing clients omitting this field will fail to connect.
!macOS local mode always manages launchd; the attach-only gateway setting has been removed.

v2026.1.10 Jan 11, 2026 · release notes

OpenClaw v2026.1.10 adds an OpenAI-compatible chat endpoint, clawdbot update, Z.AI/OpenRouter auth, browser target control, and richer status reporting.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.10 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.10

└──▷ TRY IT

Keep OpenClaw up to date on a git install without manually pulling and restarting.

$ clawdbot update

Expose the gateway as an OpenAI-compatible endpoint so existing OpenAI SDK clients can talk to your agents via SSE streaming.

yaml

gateway:
  http:
    endpoints:
      chatCompletions:
        enabled: true

Get a full diagnostic snapshot — log tails, Tailscale summary, and scan progress — when troubleshooting a misbehaving deployment.

$ clawdbot status --all

New clawdbot status command redesigned as a table-based view showing OS, updates, gateway, daemon, agents, and sessions; status --all adds a full read-only debug report with log tails, Tailscale summary, and scan progress.
New clawdbot update command (and --update shorthand) for safe git-checkout-based self-updates.
New OpenAI-compatible /v1/chat/completions HTTP endpoint on the gateway with auth, SSE streaming, and per-agent routing (disabled by default; enable via gateway.http.endpoints.chatCompletions.enabled=true).
Adds Z.AI (GLM) as a first-class auth choice (zai-api-key) with a corresponding --zai-api-key CLI flag.
Adds OpenRouter API key auth option in configure/onboard flow.

+12 more show less

New browser.target setting (sandbox/host/custom) for agents, with sandbox host-control gating via agents.defaults.sandbox.browser.allowHostControl and allowlists for custom URLs/hosts/ports.
New human-delay pacing between block replies for agents (modes: off/natural/custom, configurable per-agent).
Per-provider/per-account historyLimit overrides now supported (fallback to messages.groupChat.historyLimit; set 0 to disable).
Gateway heartbeat can now optionally include Reasoning: output via agents.defaults.heartbeat.includeReasoning.
Adds Codex CLI fallback with resume support, JSONL parsing for new runs, and a live CLI resume probe.
Catalog-backed default model picker added to onboarding and configure.
Telegram adds /whoami and /id commands to reveal sender IDs for allowlists, plus support for @username and prefixed IDs in allowFrom.
New clawdbot sandbox explain subcommand as an effective policy inspector with fix-it config key paths.
Telegram adds telegram.draftChunk setting to tune draft streaming chunking for streamMode: "block".
clawdbot sessions table now includes elev:* and usage:* flags.
Docker setup now supports optional home volume and extra bind mounts in docker-setup.sh.
Gateway now accepts image attachments on the agent endpoint (multimodal messages) with a live gateway image probe via CLAWDBOT_LIVE_GATEWAY_IMAGE_PROBE=1.

17 details in Everything

└──▷ BREAKING ON UPGRADE

!The OpenAI-compatible /v1/chat/completions gateway endpoint is disabled by default; existing integrations expecting it to be on will need to explicitly set gateway.http.endpoints.chatCompletions.enabled=true.
!The commands.config and commands.debug gates now disable /config and /debug by default; bots relying on these commands must enable them via commands.config/commands.debug.
!WhatsApp: messages.ackReaction is now ignored — the doctor copies it to whatsapp.ackReaction, so configs using the old key will no longer take effect without migration.

v2026.1.9 Jan 10, 2026 · release notes

OpenClaw v2026.1.9 adds Microsoft Teams, MiniMax/OpenCode Zen models, gateway discovery, message subcommands, and a major provider capability expansion.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.9 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.9

└──▷ TRY IT

Discover local and wide-area gateways and get structured JSON output for scripting or inventory.

$ clawdbot gateway discover --json --timeout 10

Inspect or reorder authentication profiles to control which credentials are tried first for model access.

$ clawdbot models auth order get
clawdbot models auth order set anthropic minimax opencode

Adds Microsoft Teams provider with polling, attachment support, outbound sends, requireMention, config reload, and DM policy.
Onboards OpenCode Zen and MiniMax (Anthropic-compatible API) models with hosted onboarding flows.
Introduces token auth profiles and clawdbot models auth order {get,set,clear} for managing authentication priority.
Adds OAuth expiry health checks in doctor/status output.
Introduces unified message subcommands (message send|poll|...) replacing the flat clawdbot message command.

+26 more show less

Adds gateway discover command with local and wide-area DNS-SD, JSON output, and configurable timeout.
Adds gateway status command with human-readable and JSON output, plus SSH loopback support.
Wide-area gateway records now include gatewayPort, sshPort, cliPath, and tailnet DNS fallback.
New /debug command for runtime overrides and effective config view.
New /config get subcommand and config --section flag for chat-based config inspection.
New /commands list, /models alias, and /usage alias commands.
Adds session_status tool for agents, including sandbox allow support.
Adds claude-cli runner for agent execution.
Introduces sandbox list and recreate commands.
Adds logs output modes (pretty/plain/JSONL) with colorized health and daemon output.
New global --no-color flag for CLI output.
Adds /status cost reporting and a /cost lines alias.
Adds Telegram inline keyboard buttons and callback payload routing.
Adds Telegram cron topic delivery targets.
Adds [[audio_as_voice]] tag support for Telegram audio messages.
Adds Signal reactions and notifications with allowlist support.
Adds WhatsApp broadcast groups for multi-agent replies.
Makes WhatsApp inbound media size cap configurable.
Adds identity-based message prefixes for WhatsApp.
Control UI: adds queued messages with Enter-to-send, session links, reasoning view, and mobile responsiveness improvements.
TUI: adds agent picker, agents list RPC, and a tui --message bootstrap prompt.
Adds per-agent auth candidates display in /model status.
QuickStart now auto-installs gateway (Node-only) with a provider picker and skip-systemd flags.
Inline env vars now supported in config.
Adaptive context pruning enabled by default.
Provider status probes added to doctor, with warnings for Discord intents and Telegram privacy settings.

31 details in Everything

└──▷ BREAKING ON UPGRADE

!clawdbot message is now subcommands (message send|poll|...) and requires --provider unless only one provider is configured.
!The /restart command and gateway restart tool are disabled by default; enable with commands.restart=true.

v2026.1.8 Jan 8, 2026 · release notes

OpenClaw v2026.1.8 locks down DMs by default, adds pairing-first auth, per-agent sandboxing, and a major CLI overhaul.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.8 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.8

└──▷ TRY IT

Approve a new user requesting DM access to your Telegram bot after the pairing-first lockdown.

$ clawdbot pairing list --provider telegram
clawdbot pairing approve --provider telegram <code>

Configure per-agent sandbox isolation so each agent gets its own container, or switch to per-session isolation for finer granularity.

yaml

agent.sandbox.scope="agent"   # default: one container per agent
# or for per-session isolation:
agent.sandbox.scope="session"

Tell the model the user's local timezone when UTC envelope timestamps are insufficient for time-sensitive workflows.

yaml

agent.userTimezone="America/New_York"

Enables DM pairing-first security model across Telegram, WhatsApp, Signal, iMessage, Discord, and Slack — bots are no longer open to anyone by default.
Adds clawdbot pairing list --provider <provider> and clawdbot pairing approve --provider <provider> <code> commands to manage inbound DM access requests.
Introduces per-agent sandbox scope (agent.sandbox.scope) with "agent", "session", and "shared" isolation modes for container/workspace separation.
Adds /compact slash command to manually compact session context in the agent loop.
Adds agent.userTimezone config field to inform the model of the user's local time zone via the system prompt.

+3 more show less

Gates all slash commands to authorized senders only.
Introduces whatsapp.groups, telegram.groups, and imessage.groups as allowlists for group access control.
Restructures CLI: new daemon subcommand for service control, send/agent/wake for RPC, nodes canvas for canvas operations, and providers login/logout for auth.

8 details in Everything

└──▷ BREAKING ON UPGRADE

!Inbound DMs are now locked down by default on Telegram/WhatsApp/Signal/iMessage/Discord/Slack (dmPolicy="pairing"); previously bots were open to anyone. Set dmPolicy="open" and "*" in allowFrom (or discord.dm.allowFrom / slack.dm.allowFrom) to restore old behavior.
!agent.sandbox.scope now defaults to "agent" (one container/workspace per agent) instead of shared isolation.
!Timestamps in agent envelopes are now UTC (YYYY-MM-DDTHH:mmZ); the messages.timestampPrefix field has been removed. Use agent.userTimezone to supply local time to the model.
!Model config schema has changed (auth profiles + model lists); doctor auto-migrates and the gateway rewrites legacy configs on startup.
!whatsapp.groups, telegram.groups, and imessage.groups now act as allowlists when set; add "*" to preserve allow-all behavior.
!autoReply has been removed from Discord/Slack/Telegram channel configs; use requireMention instead.
!CLI commands update, gateway-daemon, gateway {install|uninstall|start|stop|restart|daemon status|wake|send|agent}, and telegram have been removed. login/logout are moved to providers login/logout (top-level aliases hidden).

v2026.1.5 Jan 5, 2026 · release notes

OpenClaw v2026.1.5 adds image-model support with a dedicated image tool and named model shorthands for major providers.

└──▷ GET THIS VERSION

$ git clone --branch v2026.1.5 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.5

└──▷ USE IT

Configure a dedicated image model so the new image tool routes vision tasks to a capable model while text tasks use a lighter one.

yaml

agent:
  model: gpt-mini
  imageModel: gpt

Use a built-in model shorthand instead of a full model string to select Gemini Flash as your default agent model.

yaml

agent:
  model: gemini-flash

New agent.imageModel config key enables a dedicated image-specific model with fallback chain for image-aware scans.
New image agent tool routes image tasks to the configured image model.
Adds built-in model shorthands (opus, sonnet, gpt, gpt-mini, gemini, gemini-flash) for faster config authoring; user config takes precedence.

3 details in Everything

v2.0.0-beta5 Prerelease Jan 3, 2026 · release notes

OpenClaw v2.0.0-beta5 adds Signal/iMessage providers, Talk Mode, Discord polls/threads/slash commands, and a full CLI onboarding wizard.

└──▷ GET THIS VERSION

$ git clone --branch v2.0.0-beta5 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2.0.0-beta5

└──▷ TRY IT

Run the new onboarding wizard to configure your gateway, providers, and skills from scratch.

$ clawdis configure

Check your current setup for config issues and migrate deprecated keys (e.g. routing.allowFrom → whatsapp.allowFrom) after upgrading.

$ clawdis doctor

Connect to your gateway from a remote terminal using the new TUI client.

$ clawdis tui

Adds Signal provider via signal-cli JSON-RPC for send/receive messaging.
Adds iMessage provider via imsg JSON-RPC integration (stdio) with chat_id routing and group chat support.
Adds Talk Mode for continuous speech conversations (macOS/iOS/Android) with ElevenLabs TTS, reply directives, and optional interrupt-on-speech.
Expands Discord tool actions to include reactions, stickers, polls, threads, search, and moderation gates.
Adds Discord/Telegram reply tags ([[reply_to_current]], [[reply_to:<id>]]) with per-provider replyToMode (off|first|all) for native threaded replies.

+24 more show less

Adds Discord user-installed slash command handling with per-user sessions and auto-registration.
Adds Discord DM enable/allowlist plus guild channel/user/guild allowlists with id/name matching.
Adds Discord guild routing config with per-guild/channel rules, slugged display names, and optional group DM support.
Expands auto-reply queue modes (steer/followup/collect/steer-backlog) with debounce/cap/drop options and followup backlog handling.
Adds Google Antigravity OAuth auth option for Claude Opus 4.5/Gemini 3 via CLI.
Adds per-group mention gating defaults/overrides for Telegram/WhatsApp/iMessage via *.groups with "*" defaults; Discord supports discord.guilds."*" as a default.
Adds Trello skill for board/list/card management.
Adds things-mac skill (Things 3 CLI) for read/search plus add/update via URL scheme.
Adds Apple Notes and Reminders skills via memo CLI.
Adds tmux-first coding-agent skill with requires.anyBins gate for multi-CLI setup.
Adds full CLI onboarding wizard (clawdis configure, doctor, update) covering gateway, workspace, skills, and daemon installers.
Adds clawdis tui gateway-connected terminal UI (local or remote).
Adds remote gateway client config (gateway.remote.*) with Bonjour-assisted discovery.
Adds Signal CLI auto-install from GitHub releases in the onboarding wizard.
Adds Nix mode: opt-in declarative config and read-only settings UI when CLAWDIS_NIX_MODE=1.
Adds Docker containerized gateway/CLI setup via Dockerfile, compose, and setup script.
Adds optional ui.seamColor accent to tint the Talk Mode side bubble (macOS/iOS/Android).
Adds recent-session dropdown switcher in Chat UI (macOS/iOS/Android + Control UI).
Adds Discord/Signal/iMessage connection panels in macOS and Control UI.
Adds camera camera.list command and optional deviceId selection for snaps/clips.
Adds remote CDP URL support and Linux launcher options (executablePath, noSandbox) for browser tools.
Adds legacy Z_AI_API_KEY acceptance for Z.AI provider auth (maps to ZAI_API_KEY).
Allows bun as a node manager for skill installs.
Adds macOS debug log verbosity toggle and rolling file log toggle for swift-log-backed app logs.

29 details in Everything

└──▷ BREAKING ON UPGRADE

!Skills config schema reorganized: skillsLoad.extraDirs → skills.load.extraDirs, skillsInstall.* → skills.install.*, per-skill config map moved to skills.entries (e.g. skills.peekaboo.enabled → skills.entries.peekaboo.enabled), and new optional skills.allowBundled allowlist added.
!Session group keys now use surface:group:<id> / surface:channel:<id>; legacy group:* keys migrate on next message; groupdm keys are no longer recognized.
!Discord: discord.allowFrom, discord.guildAllowFrom, and discord.requireMention are removed; use discord.dm and discord.guilds instead.
!Discord/Telegram providers no longer auto-start from env tokens alone; discord: { enabled: true } / telegram: { enabled: true } must be added to config when using DISCORD_BOT_TOKEN / TELEGRAM_BOT_TOKEN.
!Config: routing.allowFrom is removed; use whatsapp.allowFrom instead (run clawdis doctor to migrate).
!Config: routing.groupChat.requireMention and telegram.requireMention are removed; use whatsapp.groups, imessage.groups, and telegram.groups defaults instead (run clawdis doctor to migrate).

v2.0.0-beta3 Prerelease Dec 27, 2025 · release notes

OpenClaw v2.0.0-beta3 adds Discord transport, gateway webhooks, Gmail Pub/Sub hooks, background bash tasks, and per-session model/queue controls.

└──▷ GET THIS VERSION

$ git clone --branch v2.0.0-beta3 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2.0.0-beta3

└──▷ TRY IT

Set up Gmail Pub/Sub push hooks so incoming emails wake the agent automatically.

$ clawdis hooks gmail setup && clawdis hooks gmail run

Override a paired node's display name in the menu bar without editing JSON directly.

$ clawdis nodes rename <node-id> "My Home Mac"

Adds Discord bot transport for DMs and guild text channels with allowlists and mention-gated replies.
Adds gateway webhooks: external wake and isolated agent hooks with dedicated token auth.
Adds Gmail Pub/Sub hook helper via clawdis hooks gmail setup/run with auto-renew and Tailscale Funnel support.
Adds background bash task support: bash auto-yields after 20 s (or on demand) with a process tool to list, poll, log, write, and kill sessions.
Adds per-session model selection and custom model providers via models.providers merging into ~/.clawdis/agent/models.json (merge/replace modes) supporting LiteLLM, local OpenAI-compatible servers, and Anthropic proxies.

+11 more show less

Adds group chat activation modes: per-group /activation mention|always command with status visibility.
Adds /queue <mode> for per-session queue/interrupt overrides and agent.maxConcurrent cap for safe parallelism across sessions.
Adds in-process gateway restart via clawdis_gateway tool action (SIGUSR1), eliminating the need for an external supervisor.
Adds nodes rename command to override paired node display names without editing JSON.
Adds canvas a2ui push with JSONL validation, v0.9 payload rejection, and --text quick-render support.
Adds new subsystem console formatter with color modes, shortened prefixes, and TTY detection for browser and gateway logs.
Adds Discord provider status and configuration UI to the macOS menu bar Connections section.
Adds Allow Camera toggle to the macOS menu bar alongside Canvas.
Adds remote SSH tunnel health checks with Debug → Ports highlighting unhealthy tunnels and a Reset SSH tunnel action.
Surfaces update-ready state in the macOS menu bar with regrouped session submenus and a dedicated Nodes section under Context.
Chat is now the dashboard landing view in the Web UI.

16 details in Everything

└──▷ BREAKING ON UPGRADE

!The inbound.* config namespace is removed; migrate to top-level routing (allowlists, group rules, transcription), messages (prefixes/timestamps), and session (scoping/store/mainKey). No legacy keys are read.
!Heartbeat config moves to agent.heartbeat (with every: "30m" duration string and optional model); agent.heartbeatMinutes is removed, and heartbeats are disabled unless agent.heartbeat.every is set.
!WhatsApp reply-heartbeat behavior is removed; use agent.heartbeat.target/to (or target: "none") to control delivery.
!Browser act no longer accepts a CSS selector; use snapshot refs (default ai) or evaluate as an escape hatch.

v2.0.0-beta2 Prerelease Dec 21, 2025 · release notes

OpenClaw v2.0.0-beta2 adds a bundled gateway daemon, a skills platform, WhatsApp QR login, and a browser-control MCP dispatch layer.

└──▷ GET THIS VERSION

$ git clone --branch v2.0.0-beta2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2.0.0-beta2

New gateway-daemon command packages and runs the gateway as a standalone bundled process with launchd and DMG/zip distribution support.
Introduces a managed Skills platform with install metadata, uv-based installers, skill search, and a skills website.
Adds models.list API to the Gateway for dynamic model enumeration from connected providers.
Adds provider status events and expanded RPC coverage to the Gateway for real-time provider health visibility.
Supports Tailscale auth and PAM authentication on the Gateway.

+15 more show less

Adds bind-mode configuration to the Gateway for flexible network binding.
New WhatsApp QR login flow including a dedicated WhatsApp QR login tool in the agent UI.
Adds self-chat mode handling for WhatsApp Web.
Normalizes Telegram chat IDs with clearer error reporting.
Canvas host is now served directly on the Gateway port, eliminating the separate canvasHost port.
Adds MCP tool dispatch and native actions to the browser control API.
Browser control server can now start without a Playwright dependency present.
New agent steering queue for directing in-flight agent behavior.
Tool summary streaming and a runtime toggle added to the web/agent UX.
Voice wake events now route to the main session.
Workspace bootstrap ritual added for new session initialization.
Connections settings panel in the macOS app shows provider status and supports QR login.
macOS Skills settings redesigned with configurable install targets.
Models list in the macOS app is now loaded dynamically from the Gateway.
Enriched agent WebSocket logs on the Gateway for improved observability.

20 details in Everything

└──▷ BREAKING ON UPGRADE

!The standalone canvasHost port config has been removed; the canvas host is now served on the Gateway port.

v1.3.0 Dec 2, 2025 · release notes

warelay v1.3.0 adds pluggable AI agents, safety stop words, same-phone mode, and IPC relay coordination.

└──▷ GET THIS VERSION

$ git clone --branch v1.3.0 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v1.3.0

└──▷ USE IT

Switch from Claude to Codex as the reply agent without changing prompt templates.

yaml

# In your warelay config:
inbound:
  reply:
    agent: codex

Customize the same-phone prefix so bot replies are visually distinct when chatting with yourself.

yaml

# In your warelay config:
inbound:
  samePhoneMarker: "[🦞 same-phone]"

Send a message through the running relay's IPC socket instead of opening a second WhatsApp connection.

$ warelay send --provider web

Adds pluggable agent support via a new inbound.reply.agent config block, enabling Claude, Pi, Codex, and Opencode as swappable CLI backends with per-agent argv builders and NDJSON stream parsing.
Adds safety stop words: sending stop, esc, abort, wait, or exit immediately kills the active agent run and marks the session with an aborted-run reminder.
Adds same-phone mode, allowing warelay to run on the same number it messages from; echo detection via a bounded Set prevents infinite reply loops.
Adds a new inbound.samePhoneMarker config option to customize the prefix on same-phone messages (default: [same-phone]).
Adds an IPC Unix socket server at ~/.warelay/relay.sock so warelay send and warelay heartbeat reuse the running relay's WhatsApp connection instead of opening a second socket.

+4 more show less

Adds batched inbound messaging: multiple queued WhatsApp messages are delivered to the agent in one timestamped batch to preserve ordering and context.
Adds a watchdog timer that auto-restarts the WhatsApp connection after 30 minutes of no message activity; heartbeat logs now include minutesSinceLastMessage.
Adds early allowFrom filtering in inbound.ts to block unauthorized senders before any encryption/decryption attempt, preventing Bad MAC errors from silently killing the event emitter.
Adds typing indicator after IPC-sent messages to signal that more replies may be coming.

9 details in Everything

v1.2.2 Nov 28, 2025 · release notes

OpenClaw v1.2.2 adds manual heartbeat sends with message body and dry-run preview via Twilio or web providers.

└──▷ GET THIS VERSION

$ git clone --branch v1.2.2 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v1.2.2

└──▷ TRY IT

Send a real outbound heartbeat alert through Twilio to verify an on-call channel is reachable.

$ warelay heartbeat --provider twilio --message "Heartbeat check: system nominal"

Preview the exact payload that would be sent before committing to a live web heartbeat, useful in CI or staging validation.

$ warelay heartbeat --provider web --body "Scheduled heartbeat ping" --dry-run

New --message/--body flags for warelay heartbeat let practitioners push real outbound heartbeat messages via --provider web or --provider twilio.
New --dry-run flag for warelay heartbeat previews outbound payloads without sending, enabling safe testing of heartbeat configurations.

2 details in Everything

v1.2.1 Nov 28, 2025 · release notes

OpenClaw v1.2.1 adds manual heartbeat messaging with dry-run preview and MIME-first media type detection.

└──▷ GET THIS VERSION

$ git clone --branch v1.2.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v1.2.1

└──▷ TRY IT

Preview a manual heartbeat payload to Twilio before actually sending it — useful for validating message content in CI or staging.

$ warelay heartbeat --message "System healthy" --dry-run

Send a manual heartbeat with a custom body to the web channel without relying on the default automated ping.

$ warelay heartbeat --body "All services nominal"

Adds --message/--body flags to warelay heartbeat for manual heartbeat sends via web or Twilio.
Adds --dry-run flag to warelay heartbeat to preview payloads before sending.
Enables MIME-first media detection (magic bytes → headers → extension) so files send with the correct type regardless of suffix.

3 details in Everything

v1.2.0 Nov 27, 2025 · release notes

OpenClaw v1.2.0 adds heartbeat tooling, session lifecycle controls, and prompt structure improvements.

└──▷ GET THIS VERSION

$ git clone --branch v1.2.0 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v1.2.0

└──▷ TRY IT

Use the tmux-aware heartbeat helper to send heartbeats from within a tmux pane during long-running relay sessions.

$ warelay relay:heartbeat:tmux

New warelay heartbeat --session-id command for managing session heartbeats from the CLI.
New --heartbeat-now relay flag to trigger an immediate heartbeat send.
New helper commands warelay relay:heartbeat and warelay relay:heartbeat:tmux for relay-based heartbeat workflows.
New HEARTBEAT_OK signal suppresses outgoing heartbeat sends when set.
New heartbeatIdleMinutes config key controls the heartbeat idle threshold (default 10 minutes).

+5 more show less

New one-time sessionIntro prompt structure fires once per session on first message.
New per-message ultrathink prefix applied automatically to outgoing prompts.
Sessions now idle-expire after 7 days (configurable); skipped heartbeats no longer refresh or start new sessions.
WebSocket error guards and global unhandled-rejection handlers improve connection robustness.
Webhook media hosting now uses a shared host module with test coverage.

10 details in Everything

└──▷ BREAKING ON UPGRADE

!Skipped heartbeats no longer refresh sessions — setups relying on skipped heartbeats to keep sessions alive will see sessions expire.
!Fallback heartbeats no longer start new sessions — any workflow that depended on fallback heartbeats to initiate a session will break.

v1.1.0 Nov 26, 2025 · release notes

OpenClaw v1.1.0 adds voice-note transcription, media recompression, session intro prompts, and structured command auto-reply payloads.

└──▷ GET THIS VERSION

$ git clone --branch v1.1.0 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v1.1.0

Adds voice-note transcription that feeds a Transcript block and media path into prompts before replying.
Web auto-replies now resize and recompress media, detect media kind, enforce provider caps, and honor the inbound.reply.mediaMaxMb limit.
Supports optional sessionIntro to send the system prompt only once per session, reducing token overhead.
Adds configurable interval for typing-indicator refresh during sessions.
Command auto-replies now return structured {payload, meta} responses, include the command cwd in timeout messages, respect mediaMaxMb for local media, and log Claude metadata.

5 details in Everything

v0.1.3 Nov 25, 2025 · release notes

OpenClaw v0.1.3 adds configurable working-directory for command replies and file-based logging with level control.

└──▷ GET THIS VERSION

$ git clone --branch v0.1.3 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v0.1.3

└──▷ USE IT

Tune log verbosity for long-running sessions without enabling full debug output.

json

# In ~/.warelay/warelay.json
{
  "logging": {
    "level": "info"
  }
}

Adds cwd option to command reply config so external reply commands run in the correct working directory.
Adds configurable file-based logging (default /tmp/warelay/warelay.log) with log level controlled via logging.level in ~/.warelay/warelay.json; --verbose still forces debug.

2 details in Everything

└──▷ BREAKING ON UPGRADE

!Custom runners or tests that stub runCommandWithTimeout must now accept an options object { timeoutMs, cwd } in addition to the legacy numeric timeout.

v0.1.1 Nov 25, 2025 · release notes

OpenClaw v0.1.1 adds --verbose flag to send and status commands for detailed output.

└──▷ GET THIS VERSION

$ git clone --branch v0.1.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v0.1.1

Adds --verbose flag to send and status commands for detailed, noisy output during execution.
Adds executable shim enabling direct CLI invocation via npx warelay@0.1.x without a local install.

2 details in Everything

OpenClaw

Summary

How OpenClaw helps

Languages

Features

What OpenClaw offers you

release

release

release

release

release 14 total

release 10 total

docs

example

release

release

example

release

example

release

example

release

release

release

command line

release

example

release

example

release

release

release

example

release

release

example

release

release

release

command line

release

command line

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

release

example

example

example

Command line

Release-note detail over time

Releases

Articles

Add the badge to your README