No entries match these filters. Clear filters
Adds conversation_link field, configurable New Relic timeout, GPU GPU A graphics processing unit, a processor that performs many calculations in parallel. AI workloads use GPUs to speed up model training and inference. diagnostics for k8s remediation, and namespace-scoped Helm install option.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.42.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.42.0
Adds conversation_link chat field rendered into the system prompt Not checked yet Surfaces MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. structuredContent and drops null optional params from the MCP toolset Not checked yet Adds configurable request timeout for the New Relic toolset Not checked yet Adds GPU node diagnostics support to kubernetes-remediation MCP Not checked yet Adds namespaceScopedRBAC Helm value for namespace-scoped Holmes installs Not checked yet
5 details in Everything
Adds skill_repos config for live-refresh of git-synced skills with caching
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.41.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.41.0
Adds first-class skill_repos configuration to enable live-refreshing git-synced skills Not checked yet
1 detail in Everything
HolmesGPT 0.39.0 adds Atlassian Rovo MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. integration and extends GitHub MCP to support multi-org GitHub App installs with credential-based skill pulling.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.39.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.39.0
Adds Atlassian Rovo MCP integration, enabling HolmesGPT to use Rovo as a data source via the MCP addon. Not checked yet Extends the GitHub MCP addon to support GitHub App installations spanning multiple organizations. Not checked yet Enables pulling skills using GitHub App credentials in the GitHub MCP integration. Not checked yet
3 details in Everything
HolmesGPT 0.38.2 adds RFC 8707 RFC 8707 An IETF standard that adds a resource indicator parameter to OAuth 2.0 token requests, letting authorization servers scope tokens to a specific API so one stolen token cannot be replayed against another service. resource indicator support to the MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. flow.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.38.2 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.38.2
HolmesGPT 0.38.0 adds remote tool call approval workflows and cuts prompt token usage by 50–60%.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.38.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.38.0
Implements remote tool call approval workflows, allowing human review and authorization of agent-initiated tool calls before execution. Not checked yet Reduces system prompt and tool description sizes by ~50–60%, significantly cutting prompt token consumption per investigation. Not checked yet Makes conversation-worker slot exhaustion visible and bounds reconnect sign-in, improving observability of capacity limits. Not checked yet
3 details in Everything
HolmesGPT 0.37.0 adds JSON log scraping, Langfuse/OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. tracing, and pre-acquired Azure AD token support.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.37.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.37.0
Adds JSON logging format support for log scrapers, enabling structured log ingestion pipelines. Not checked yet Adds Langfuse integration via OpenTelemetry tracing for LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. observability and trace export. Not checked yet Supports pre-acquired AZURE_AD_TOKEN for Entra ID Entra ID Microsoft's cloud-based identity and access management service, formerly Azure Active Directory, used by cyber tools to authenticate users and enforce access policies in Microsoft 365 and Azure environments. authentication, allowing token reuse without re-authentication. Not checked yet
3 details in Everything
HolmesGPT 0.36.0 adds a /api/info endpoint, in-app TLS, Helm secret sugar, and multi-MCP-server MCP-server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. tool-name isolation.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.36.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.36.0
└──▷ TRY IT
Check the running HolmesGPT instance's operational state — model, version, and configuration — without digging through logs.
copy
$ curl -s https://<holmesgpt-host>/api/info | jq .
Mount an existing Kubernetes secret containing API keys into the HolmesGPT pod via Helm without manually listing each env var.
yaml
copy
extraEnvVarsSecrets:
- my-llm-api-keys
Adds GET /api/info endpoint for operational visibility into the running HolmesGPT instance. Not checked yet Adds extraEnvVarsSecrets and envRef Helm values as shorthand for injecting secrets and configuring modelList without manual env var wiring. Not checked yet Enables in-app HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. /TLS support for the HolmesGPT API, allowing TLS termination without an external proxy. Not checked yet Supports multiple MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers simultaneously without tool-name collisions — identical tool names across servers are now disambiguated rather than overridden. Not checked yet Adds a standalone manifest for provisioning additional Azure MCP accounts alongside existing ones. Not checked yet
+5 more
show less
Marks multi-instance-capable data sources in the data source catalog so operators can distinguish sources that support parallel deployments. Not checked yet Consolidates Datadog and Elasticsearch/OpenSearch OpenSearch An open-source search and analytics engine, forked from Elasticsearch by AWS in 2021, that lets cyber tools store, query, and visualize large volumes of log or event data without licensing restrictions. entries into unified catalog cards in the data source catalog. Not checked yet Routes call_aws JSON-argument commands through the no-JSON path, cutting approximately 87 seconds of retries on AWS MCP calls. Not checked yet GitHub MCP personal-access-token (PAT PAT A personal access token, a credential used by scripts and integrations instead of a user's password. Its permissions and expiry depend on the service issuing it. ) path now uses native HTTP mode for more reliable authentication. Not checked yet Bounds conversation and tool-call claiming to worker capacity, preventing oversubscription under load. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! KRR resource recommendation features have been removed from HolmesGPT.
HolmesGPT 0.35.0 adds env var templating in MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. URLs and expands the datasource catalog.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.35.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.35.0
Supports environment variable templating inside MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. OAuth URLs, enabling dynamic credential injection without hardcoding secrets in config. Not checked yet Adds new data sources to the datasource catalog, broadening the range of backends HolmesGPT can query. Not checked yet
2 details in Everything
HolmesGPT 0.34.0 adds admin API endpoints for runtime config reload, event-driven operator triggers, and JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. -signed approval tickets for Kubernetes remediation.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.34.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.34.0
Adds admin API endpoints for runtime configuration reload, enabling live config changes without restarting the service. Not checked yet Introduces event-driven triggers in operator mode, allowing HolmesGPT to react to Kubernetes events automatically. Not checked yet Adds JWT-signed approval tickets to the Kubernetes Remediation MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. , with approval-based tool separation between safe and destructive actions. Not checked yet Updates AWS MCP Helm addon to native Streamable HTTP Streamable HTTP An MCP transport protocol that lets a client send JSON-RPC requests over HTTP POST while the server streams responses back using Server-Sent Events, replacing the older stdio and SSE transports for remote tool communication. (v2.1.0). Not checked yet Adds firewall detection and user-friendly error handling for Supabase sign-in failures. Not checked yet
+1 more
show less
OAuth MCP now deletes expired token rows on 401 responses so users can re-authenticate cleanly. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! The deprecated Tool._is_restricted() mechanism has been removed; any toolset code relying on it will break.
HolmesGPT 0.33.0 adds cross-cluster remote tool execution and per-request tracing with span token metrics.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.33.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.33.0
Adds cross-cluster remote tool execution via an executor worker, toolset publishing, and caller headers, enabling tools to run against remote clusters from a central Holmes instance. Not checked yet Adds per-request tracing experiment routing and span token metrics to the server for observability into LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. completion costs per request. Not checked yet
2 details in Everything
HolmesGPT 0.32.0 adds multi-instance toolsets, multi-cluster awareness, GitHub MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. auto-detection, and a unified firing boolean across all alert sources.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.32.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.32.0
Adds enable_todo flag to control the TodoWrite feature in evals. Not checked yet Exposes a uniform firing boolean field for all alert sources, normalising alert state across integrations. Not checked yet Adds multi-instance toolsets support ([ROB-3577]), allowing multiple instances of the same toolset to be configured simultaneously. Not checked yet MCP auth health check now auto-detects and enables GitHub context automatically. Not checked yet Adds a Denied commands column to eval reports for visibility into blocked tool calls. Not checked yet
+5 more
show less
Introduces multi-cluster scope-awareness in the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. prompt layer, enabling the AI to reason across clusters. Not checked yet Hardwires cluster and conversation context into platform-MCP headers for richer contextual routing. Not checked yet Supports overriding the config file at runtime. Not checked yet Allows omitting the temperature parameter for models that reject it (e.g. Claude Opus 4.7+). Not checked yet Marks the llm_summarize transformer as legacy / not recommended, steering users toward current alternatives. Not checked yet
10 details in Everything
HolmesGPT 0.31.0 adds Robusta Platform MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. toolset, multi-instance Elasticsearch/Grafana, per-conversation OAuth opt-out, and periodic MCP tool refresh.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.31.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.31.0
Adds the Robusta Platform MCP toolset with dynamic session token authentication for connecting Holmes to the Robusta platform. Not checked yet Adds per-conversation OAuth opt-out support, letting individual sessions bypass OAuth flows. Not checked yet Adds periodic MCP tools refresh so newly added tools are discovered without restarting the process. Not checked yet Adds multi-instance Elasticsearch support, enabling Holmes to query across multiple Elasticsearch backends. Not checked yet Adds multi-instance Grafana dashboard support, enabling Holmes to query across multiple Grafana instances. Not checked yet
+4 more
show less
Adds multi-region support for Robusta platform endpoints. Not checked yet Adds optional ClickHouse HTTP JSONEachRow format for DateTime64 query results. Not checked yet Adds evaluation harness for metrics analyses, expanding the benchmark coverage to metric-based investigations. Not checked yet Warns at startup when an OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. endpoint is configured but required OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. packages are missing. Not checked yet
9 details in Everything
HolmesGPT 0.30.1 adds GitLab MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. datasource, user_email on chat requests, and LITELLM_MODEL_COST_MAP_URL support for firewalled environments.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.30.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.30.1
Accepts user_email on chat requests and persists it to HolmesUsageEvents for usage tracking. Not checked yet Supports LITELLM_MODEL_COST_MAP_URL environment variable to configure model cost map fetching in firewalled environments. Not checked yet Adds GitLab MCP entry to datasource-catalog.json, making GitLab available as a selectable MCP datasource. Not checked yet Loki toolset now returns the raw response when parsing fails, surfacing unparseable data instead of silently dropping it. Not checked yet
4 details in Everything
HolmesGPT 0.30.0 adds GitLab MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server integration alongside existing Kubernetes MCP support.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.30.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.30.0
Adds GitLab MCP server integration, enabling Holmes to interact with GitLab repositories and resources via the Model Context Protocol Model Context Protocol Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. . Not checked yet
1 detail in Everything
HolmesGPT 0.29.0 adds SSL SSL A cryptographic protocol for encrypting network connections, now deprecated in favor of TLS but whose name persists colloquially. Cyber tools reference it when handling HTTPS or other encrypted-channel inspection and termination. /TLS custom CA support, AI usage tracking, Helm commonLabels, skills-from-Helm, and per-toolset prerequisite timeouts.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.29.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.29.0
└──▷ USE IT
Propagate custom labels (e.g. team, environment) to every resource the Holmes Helm chart creates.
yaml
copy
commonLabels:
team: security-ops
environment: production
Inject secrets or config from existing ConfigMaps/Secrets into the Holmes pod without hardcoding values.
yaml
copy
additional_env_froms:
- secretRef:
name: my-llm-api-keys
- configMapRef:
name: holmes-extra-config
Adds commonLabels support to the Helm chart to propagate custom labels across all chart resources. Not checked yet Adds additional_env_froms support to the Holmes Helm chart for injecting environment variables from ConfigMaps or Secrets. Not checked yet Adds skills provisioning directly from Helm chart values. Not checked yet Adds per-toolset prerequisite timeout to prevent startup hangs when toolset dependencies are unavailable. Not checked yet Adds SSL/TLS support for custom CA bundles in the Realtime WebSocket WebSocket A protocol that upgrades an HTTP connection into a persistent, full-duplex channel, letting a server push data to a client without repeated polling. Cyber tools use it for real-time event streaming and live command output. connection. Not checked yet
+1 more
show less
Adds AI usage tracking via HolmesUsageEvents to monitor LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. consumption. Not checked yet
6 details in Everything
HolmesGPT 0.28.0 adds DNS configuration support and authenticated private-channel realtime subscriptions.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.28.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.28.0
Adds the ability to configure dnsPolicy and dnsConfig for HolmesGPT deployments. Not checked yet Enables private channel support with authentication for realtime subscriptions. Not checked yet
2 details in Everything
HolmesGPT 0.27.0 adds GitHub Copilot AI provider, optional API key auth for HTTP endpoints, and a Kubernetes MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. addon.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.27.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.27.0
Adds optional API key authentication for all HTTP endpoints. Not checked yet Adds GitHub Copilot as a supported AI provider. Not checked yet Adds a Kubernetes MCP addon (ROB-3465 k8s mcp addon ). Not checked yet Adds support for additional environment variables in the Confluence MCP integration. Not checked yet Adds support for editing tool command arguments before execution. Not checked yet
+9 more
show less
Adds configurable deployment rollout strategy via Helm. Not checked yet Adds client secret support in the CLI OAuth flow, with an option to set the auth callback. Not checked yet Adds an M2 Conversation Worker for async conversation processing, now enabled by default. Not checked yet Adds health checks to detect silently-dead realtime WebSocket WebSocket A protocol that upgrades an HTTP connection into a persistent, full-duplex channel, letting a server push data to a client without repeated polling. Cyber tools use it for real-time event streaming and live command output. connections. Not checked yet Adds Supabase Realtime verification before starting the conversation worker. Not checked yet Adds retry logic to the conversation worker. Not checked yet Extracts text from MCP resource content blocks in tool results. Not checked yet Injects frontend tools into the worker conversation executor. Not checked yet Disables todowrite behavior controls in scheduled prompts. Not checked yet
14 details in Everything
HolmesGPT 0.26.0 introduces Skills extensibility, VictoriaLogs toolset, and new Grafana timeout controls
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.26.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.26.0
Adds extraVolumes, extraVolumeMounts, and extraInitContainers configuration keys to the AWS MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. toolset for flexible volume and init-container injection. Not checked yet Adds max retries and timeout configuration for Grafana integrations. Not checked yet Introduces Skills, a new extensibility model enabling custom tool integrations and workflows via configuration. Not checked yet Adds a VictoriaLogs toolset for log search and analysis. Not checked yet Adds support for logging aggregated investigation token usage. Not checked yet
+2 more
show less
Improves the data source configuration flow. Not checked yet Adds Atlassian admin setup steps to OAuth MCP documentation, expanding supported MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. configuration guidance. Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! The Skills functionality introduces a new extensibility model — existing custom tool integrations and workflows may need to be migrated to the new Skills configuration format.
HolmesGPT 0.25.0 adds a Crossplane toolset and OAuth support for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers in CLI and server mode.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.25.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.25.0
Adds OAuth support for MCP servers in both CLI and server mode. Not checked yet Adds a Crossplane toolset for investigating Crossplane resources. Not checked yet
2 details in Everything
HolmesGPT 0.24.4 adds OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. instrumentation, YAML anchors in config, new Kafka tools, and expanded DB data source support.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.24.4 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.24.4
└──▷ USE IT
Reuse shared config blocks (e.g., common LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. settings) across multiple toolsets without repetition.
yaml
copy
anchors:
common_llm: &common_llm
model: gpt-4o
max_tokens: 4096
toolsets:
- name: my-toolset
llm:
<<: *common_llm
Adds anchors top-level field to HolmesGPT config to support YAML anchors, enabling reuse of repeated config blocks. Not checked yet Adds OpenTelemetry tracing and metrics instrumentation for observing HolmesGPT's own runtime behavior. Not checked yet Adds missing Kafka tools to match the full capability set of the kafka-mcp-server integration. Not checked yet Expands datasource support with new database data sources and improved datasource descriptions. Not checked yet Adds Zabbix integration with supporting documentation. Not checked yet
+2 more
show less
Allows using the table API without specifying a version. Not checked yet Rebrands Azure OpenAI integration to Azure AI Foundry. Not checked yet
7 details in Everything
HolmesGPT 0.24.1 adds mTLS mTLS Mutual TLS, an encrypted connection where both client and server present certificates to prove their identity. It helps services verify who they are communicating with. /SSL SSL A cryptographic protocol for encrypting network connections, now deprecated in favor of TLS but whose name persists colloquially. Cyber tools reference it when handling HTTPS or other encrypted-channel inspection and termination. support to the Kafka/admin toolset.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.24.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.24.1
HolmesGPT 0.24.0 adds frontend tool execution, a startup sample-questions menu, and configurable Helm security contexts.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.24.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.24.0
└──▷ TRY IT
Ask Holmes a question without specifying a subcommand — useful for quick ad-hoc investigations from the shell.
copy
$ holmesgpt 'Why is my payment-service pod crash-looping?'
Adds configurable podSecurityContext and containerSecurityContext fields to the Holmes Helm chart, enabling custom pod and container security contexts at deploy time. Not checked yet Adds frontend tool execution support to Holmes, allowing UI-side tools to be invoked through the HTTP API (documented in the HTTP API frontend tools implementation guide). Not checked yet Defaults to the ask subcommand when no subcommand is provided on the CLI, so bare holmesgpt <question> invocations now work without specifying a subcommand. Not checked yet Adds a sample questions menu on startup to guide practitioners toward common investigations. Not checked yet
4 details in Everything
HolmesGPT 0.23.0 adds a revamped CLI experience, multi-account NewRelic support, image content in MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. results, and HTTP Basic Auth for ServiceNow.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.23.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.23.0
Adds HTTP Basic Auth support to the ServiceNow tables toolset. Not checked yet Adds support for image content in MCP tool results. Not checked yet Adds support for multiple NewRelic accounts in a single HolmesGPT instance. Not checked yet Adds a Docker Compose setup for simplified HolmesGPT deployment. Not checked yet Delivers a new and improved interactive CLI experience. Not checked yet
5 details in Everything
HolmesGPT 0.22.0 adds MongoDB toolset, mTLS mTLS Mutual TLS, an encrypted connection where both client and server present certificates to prove their identity. It helps services verify who they are communicating with. for HTTP/Elasticsearch, digest auth, Inspektor Gadget filtering, and GitHub App token management.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.22.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.22.0
└──▷ TRY IT
Use a separate classifier model by setting the CLASSIFIER_MODEL env var, e.g. when routing classification to a cheaper model via OpenRouter OpenRouter A unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. .
copy
$ export CLASSIFIER_MODEL=openrouter/anthropic/claude-3-haiku
holmes ask 'Why is my pod crashlooping?'
Adds initContainers and args support to the Helm chart for advanced pod configuration. Not checked yet Adds digest auth and mTLS support to the HTTP toolset, configurable via the HTTP connector config. Not checked yet Adds mTLS (mutual TLS mutual TLS Mutual TLS, an encrypted connection where both client and server present certificates to prove their identity. It helps services verify who they are communicating with. ) support to the Elasticsearch toolset. Not checked yet Adds CLASSIFIER_MODEL environment variable support for specifying a separate classifier model (documented alongside OpenRouter requirements). Not checked yet Adds behavior_controls API parameter for prompt customization in the investigation API. Not checked yet
+13 more
show less
Adds tool_results_dir parameter to ToolCallingLLM in the custom LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. interface. Not checked yet Adds a MongoDB toolset for querying and diagnostics. Not checked yet Adds filtering support to the Inspektor Gadget toolset, enabling scoped tool invocations. Not checked yet Adds GitHub App token manager for automatic installation token handling, including MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. config support for GitHub App credentials. Not checked yet Adds datasource-catalog.json for datasource cataloging. Not checked yet Adds keyless auth support for Azure AI Foundry. Not checked yet Adds cached tokens tracking and max_prompt_tokens_per_call tracking to LLM usage/cost reporting. Not checked yet Adds URL query parameter support to tab synchronization in the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. . Not checked yet Adds Enum field support and MCP config management to the TUI. Not checked yet Adds multi-round approval workflow support with iteration offset. Not checked yet Enables strict tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. universally with per-tool compatibility checks. Not checked yet Disables unconfigured toolsets by default in the CLI. Not checked yet Removes the automated investigation API, consolidating all investigation flows into the conversational interface. Not checked yet
18 details in Everything
└──▷ BREAKING ON UPGRADE
! The automated investigation API has been removed; all investigation flows must now use the conversational interface.! Unconfigured toolsets are now disabled by default in the CLI — toolsets that were previously active without explicit configuration will no longer run.! Message truncation logic has been removed; context overflow now causes a fast failure instead of silently truncating.
HolmesGPT 0.21.0 adds Coralogix archive support, Confluence integration, an interactive TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. for toolset config, and AWS Bedrock bearer-token auth.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.21.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.21.0
Adds AWS_BEARER_TOKEN_BEDROCK environment variable to authenticate with AWS Bedrock models. Not checked yet Adds an interactive TUI for toolset configuration, letting CLI users configure toolset prerequisites without manual file editing. Not checked yet Adds Coralogix archive support as a new data-source integration. Not checked yet Adds Confluence as a new toolset integration for knowledge-base lookups during investigations. Not checked yet Adds a direct Prometheus endpoint option for Grafana Cloud data sources. Not checked yet
+7 more
show less
Supports recursive parsing of nested schemas in MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool parameters, enabling richer MCP toolset interoperability. Not checked yet Adds HTTP header propagation to forward request headers through HolmesGPT's internal calls. Not checked yet Adds resourcequotas RBAC RBAC Role-based access control, where permissions are assigned to roles such as reader or administrator and users receive those roles. It makes access easier to manage than individual permission lists. role to the Holmes default service account, expanding Kubernetes resource visibility. Not checked yet Adds webhook configuration permissions to the HolmesGPT service account. Not checked yet Adds appProtocol field to the Holmes Helm service port configuration. Not checked yet Implements lazy initialization for toolset prerequisites in CLI mode, so missing prerequisites no longer block unrelated toolsets at startup. Not checked yet Adds Claude Opus 4.6 and Sonnet 4.6 to benchmark model defaults. Not checked yet
12 details in Everything
HolmesGPT 0.20.0 adds SQL database toolsets, five MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server integrations, Inspektor Gadget, KubeVela, and a generic HTTP connector toolset.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.20.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.20.0
Adds SQL Database toolsets covering PostgreSQL, ClickHouse, MariaDB, MySQL, SQLServer, and SQLite, enabling AI-driven investigation of database state. Not checked yet Adds a generic HTTP connector toolset for querying arbitrary HTTP endpoints as investigation sources. Not checked yet Adds Inspektor Gadget toolset for kernel-level eBPF eBPF A Linux technology for running verified programs inside the kernel without changing its source. Tools use it to observe processes, enforce rules and process network traffic. -based diagnostics within HolmesGPT investigations. Not checked yet Adds KubeVela built-in toolsets for investigating OAM OAM Operations, Administration, and Maintenance — a set of protocols and functions for monitoring, managing, and fault-isolating network connections, giving cyber tools visibility into link health without disrupting live traffic. application workloads. Not checked yet Adds Grafana MCP server integration, enabling HolmesGPT to query Grafana via the Model Context Protocol Model Context Protocol Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. . Not checked yet
+8 more
show less
Adds Sentry MCP server integration for pulling error and event context from Sentry during investigations. Not checked yet Adds Prefect MCP server integration for workflow observability via the Model Context Protocol. Not checked yet Adds Confluence MCP server integration for surfacing runbook and knowledge-base content during investigations. Not checked yet Adds Kubernetes Remediation MCP integration, allowing HolmesGPT to execute remediation actions against Kubernetes clusters. Not checked yet Adds filesystem storage for large tool results, removing in-memory size constraints on investigation outputs. Not checked yet Adds multi-cluster support and external change handling to Robusta tools. Not checked yet Adds GCP workload identity workload identity An identity assigned to software, such as a service or container, rather than a person. It lets the workload authenticate and receive permissions without sharing a user's credentials. support for the GCP MCP integration. Not checked yet Adds OpenRouter OpenRouter A unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. as a supported AI provider. Not checked yet
13 details in Everything
└──▷ BREAKING ON UPGRADE
! Additional instructions support has been removed; any configuration relying on that feature will no longer work after upgrading.! Unused Coralogix label settings have been removed and related functions have been flattened; configurations referencing those Coralogix label settings will break on upgrade.
HolmesGPT 0.19.0 adds GitHub, Confluence, and Splunk MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers, image input support, and scheduled prompt investigations.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.19.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.19.0
Adds Splunk MCP server support, replacing any prior ad-hoc Splunk integration with an explicit MCP-based server. Not checked yet Adds GitHub MCP server, replacing the legacy GitHub toolset with an MCP-based implementation. Not checked yet Adds Confluence MCP server for Confluence-based investigations and workflows. Not checked yet Supports passing an auth token to MCP servers via HTTP header. Not checked yet Adds support for image input to the chat API, including a new images field in the chat API. Not checked yet
+3 more
show less
Adds daily and weekly scheduled prompt investigations in SAS. Not checked yet Redesigns the Bash toolset with prefix-based approvals for command execution control. Not checked yet Improves OOMKill detection capability. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! The git toolset has been deprecated in favor of the Git MCP server; existing configurations relying on the git toolset will stop working and must be migrated to the MCP-based implementation.
HolmesGPT 0.18.5 adds structured output structured output Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. to /api/chat, periodic toolset refresh, and Claude tool-approval support
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.18.5 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.18.5
Adds structured output support to the POST /api/chat endpoint, enabling callers to receive machine-parseable responses. Not checked yet Adds periodic toolset status refresh in server mode, keeping tool availability current without restarting the process. Not checked yet Adds Claude tool-approval support, allowing all tools to be approved for Claude-backed workflows. Not checked yet Adds SSL SSL A cryptographic protocol for encrypting network connections, now deprecated in favor of TLS but whose name persists colloquially. Cyber tools reference it when handling HTTPS or other encrypted-channel inspection and termination. verification disable option for Claude integrations. Not checked yet Adds long file name support on Windows, removing path-length errors when processing deeply nested files. Not checked yet
+1 more
show less
Helm chart now uses a dynamic imagePullPolicy driven by values, replacing the previously hardcoded policy. Not checked yet
6 details in Everything
HolmesGPT 0.18.4 adds Azure managed Prometheus, New Relic multi-account, GitHub MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. , and AWS MCP improvements.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.18.4 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.18.4
Adds Azure managed Prometheus support to the Prometheus toolset. Not checked yet Adds New Relic multiple-account support, enabling queries across more than one New Relic account. Not checked yet Adds GitHub MCP addon for the Helm chart, extending MCP integrations alongside the existing Azure MCP toolset. Not checked yet Improves AWS MCP integration with several enhancements. Not checked yet Enables the connectivity_check toolset by default in the Helm chart. Not checked yet
+2 more
show less
Adds support for an additional system prompt URL in eval configurations. Not checked yet Improves SSL SSL A cryptographic protocol for encrypting network connections, now deprecated in favor of TLS but whose name persists colloquially. Cyber tools reference it when handling HTTPS or other encrypted-channel inspection and termination. error messaging for the Prometheus toolset to surface clearer diagnostics. Not checked yet
7 details in Everything
HolmesGPT 0.18.2 adds TCP TCP A network protocol that delivers a reliable, ordered stream of bytes between two endpoints. It detects lost data and retransmits it. connectivity checks, GCP & AKS AKS Azure Kubernetes Service, Microsoft's managed Kubernetes offering, which lets cyber tools offload cluster provisioning and scaling to Azure so engineers focus on workload logic instead of control-plane operations. MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. integrations, and an improved Elasticsearch/OpenSearch OpenSearch An open-source search and analytics engine, forked from Elasticsearch by AWS in 2021, that lets cyber tools store, query, and visualize large volumes of log or event data without licensing restrictions. toolset.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.18.2 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.18.2
Adds a connectivity check toolset supporting TCP checks for network reachability diagnostics. Not checked yet Adds GCP MCP integration for Google Cloud Platform context in investigations. Not checked yet Adds Azure (AKS) MCP integration for Azure Kubernetes Service context. Not checked yet Updates the Prometheus toolset configuration. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! The Elasticsearch/OpenSearch toolset has breaking configuration changes — consult the updated docs at https://holmesgpt.dev/data-sources/builtin-toolsets/elasticsearch/#elasticsearch-opensearch before upgrading.
HolmesGPT 0.18.1 adds memory usage limits for bash and yaml toolsets via ulimit.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.18.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.18.1
HolmesGPT 0.18.0 adds runbook support by alerts and symptoms, external links in tool results, and new health endpoints for pod probes.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.18.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.18.0
Adds healthz and readyz endpoints for pod probe health checks. Not checked yet Adds runbook alerts to the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. prompt, enabling runbook lookup by alerts and symptoms. Not checked yet Tool results now include external links for quick navigation to source resources. Not checked yet Reduces LLM context consumption by serializing multiple tool call outputs as minified JSON. Not checked yet Improves Coralogix toolset with expanded capabilities. Not checked yet
+4 more
show less
Adds health checks to TCP TCP A network protocol that delivers a reliable, ordered stream of bytes between two endpoints. It detects lost data and retransmits it. connections. Not checked yet Publishes Helm charts via OCI OCI Open Container Initiative standard, maintained by the Linux Foundation, defining the image format and runtime spec that container tools share so images built once run anywhere OCI-compliant. registry. Not checked yet Expands default CRD CRD A Kubernetes extension that adds a new object type to the cluster, so a tool's configuration is stored, validated and versioned by Kubernetes itself rather than in a file beside it. permissions for broader Kubernetes resource coverage. Not checked yet Adds timeout to Kafka prerequisites check. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! The datadog/rds plugin is removed; its functionality is now covered by the datadog/metrics plugin.
HolmesGPT 0.17.0 adds MariaDB MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. addon, user runbooks catalog, and total cost display with --log-costs.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.17.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.17.0
└──▷ TRY IT
Track the total LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. spend for a Holmes investigation to understand cost per incident.
copy
$ holmes ask 'Why is my payment-service pod crash-looping?' --log-costs
Adds --log-costs flag now displays total cost at the end of a run, in addition to per-call costs. Not checked yet Adds MariaDB MCP addon, extending the set of supported database integrations. Not checked yet Adds support for a user runbooks catalog, enabling practitioners to supply their own runbooks for Holmes to reference during investigations. Not checked yet
3 details in Everything
HolmesGPT 0.16.4 adds stdio MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. support and AWS MCP instructions.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.16.4 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.16.4
Adds stdio transport support for MCP (Model Context Protocol Model Context Protocol Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. ) servers, enabling local process-based tool integrations. Not checked yet Adds AWS MCP instructions, enabling Holmes to interact with AWS resources via the MCP toolchain. Not checked yet
2 details in Everything
HolmesGPT 0.16.3 adds ServiceNow and OpenShift OpenShift Red Hat's Kubernetes distribution that adds developer workflows, built-in CI/CD, and stricter security defaults on top of upstream Kubernetes, giving cyber tools a managed container platform with enterprise auth and RBAC already wired in. toolsets, streamable-HTTP MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. support, and Loki improvements.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.16.3 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.16.3
└──▷ TRY IT
Cap how many tokens a single tool can consume from the context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. , useful when running against models with tight context limits.
copy
$ export TOOL_MAX_ALLOCATED_CONTEXT_WINDOW_TOKENS=8000
holmes ask 'Why is my payment-service pod crash-looping?'
Adds TOOL_MAX_ALLOCATED_CONTEXT_WINDOW_TOKENS environment variable to control the maximum context window tokens allocated per tool. Not checked yet New ServiceNow toolset for querying and interacting with ServiceNow from within HolmesGPT investigations. Not checked yet New OpenShift toolset enabling use of oc commands during AI-driven investigations. Not checked yet Adds streamable-HTTP transport support for MCP (Model Context Protocol Model Context Protocol Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. ) integrations. Not checked yet Supports custom GitHub Enterprise URLs, allowing users on GitHub Enterprise to point HolmesGPT at their own instance. Not checked yet
+2 more
show less
Improved Loki toolset with expanded log querying capabilities. Not checked yet Improved KRR (Kubernetes Resource Recommender) tool integration. Not checked yet
7 details in Everything
HolmesGPT 0.16.1 adds Grafana dashboard tools, CRD CRD A Kubernetes extension that adds a new object type to the cluster, so a tool's configuration is stored, validated and versioned by Kubernetes itself rather than in a file beside it. reading, Robusta runbook support, and a resource-issues fetch tool.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.16.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.16.1
Adds four new built-in tools for retrieving Grafana dashboards, enabling Holmes to pull and reason over dashboard data during investigations. Not checked yet Enables Holmes to read Kubernetes Custom Resource Definitions Custom Resource Definitions A Kubernetes extension that adds a new object type to the cluster, so a tool's configuration is stored, validated and versioned by Kubernetes itself rather than in a file beside it. (CRDs CRDs A Kubernetes extension that adds a new object type to the cluster, so a tool's configuration is stored, validated and versioned by Kubernetes itself rather than in a file beside it. ), expanding its cluster-resource awareness beyond core API objects. Not checked yet Adds a fetch-resource-issues tool that retrieves workload issues directly, supporting richer automated triage workflows. Not checked yet Adds Robusta runbook support, allowing Holmes to reference and execute Robusta runbooks during incident response. Not checked yet Adds support for pulling external changes, keeping Holmes tooling in sync with upstream configurations. Not checked yet
+1 more
show less
Improves prompt caching to reduce latency and cost on repeated or similar queries. Not checked yet
6 details in Everything
HolmesGPT 0.16.0 adds AWS MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. integration for IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. /EC2 EC2 Amazon's cloud virtual-machine service, letting tools run on-demand servers without managing physical hardware. /cost queries and conversation history compaction for longer sessions.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.16.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.16.0
New AWS MCP addon enables querying IAM Roles, security groups, EC2 instances, and AWS costs directly from HolmesGPT conversations. Not checked yet Adds conversation history compaction to support longer, data-heavy conversations without hitting context limits. Not checked yet Adds AI reasoning logs for visibility into the model's decision process during investigations. Not checked yet
3 details in Everything
HolmesGPT 0.15.0 adds Cilium/Hubble toolsets, a feedback command, AG-UI chat endpoint, and a tool approval workflow.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.15.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.15.0
└──▷ TRY IT
Submit feedback directly from the CLI after an investigation session.
Adds feedback subcommand (with privacy notice) for submitting feedback from the CLI. Not checked yet Allows passing a custom system-prompt parameter in the Holmes chat endpoint via the custom_sys_prompt param (ROB-2197). Not checked yet Adds experimental AG-UI-supported chat endpoint and PPL query-assist feature. Not checked yet Adds Cilium and Hubble toolsets for network observability and policy inspection. Not checked yet Adds a tool approval workflow, enabling operator review of tool calls before execution (ROB-1933). Not checked yet
+7 more
show less
Adds Vertex AI Claude model support by including the google-cloud-aiplatform dependency. Not checked yet Adds OpenSearchQueryAssistToolset with prerequisites checking. Not checked yet Expands NewRelic toolset with freeform queries, transaction embed support, and improved trace handling. Not checked yet Limits max tool output to a hard-coded 25K tokens regardless of model context size, improving stability with large responses. Not checked yet Improves Gemini model support and compatibility. Not checked yet Removes experimental tag from three previously experimental toolsets. Not checked yet Improves CLI output to reduce noise during normal operation. Not checked yet
12 details in Everything
HolmesGPT 0.14.2 adds improved Tempo integration, Claude Sonnet 1M token model support, and context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. optimizations for metrics and trace data.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.14.2 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.14.2
Supports the Sonnet 1M token model for extended context analysis. Not checked yet Improves Tempo integration to enable latency increase and HTTP 500 error root-cause queries. Not checked yet Optimizes context window handling for metrics and trace data, increasing answer accuracy. Not checked yet Improves Datadog integration accuracy through multiple small changes. Not checked yet
4 details in Everything
HolmesGPT 0.14.1 adds a free-form Tempo toolset, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -based message summarization via a Transformer mechanism, and api_base/api_version Azure OpenAI config keys.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.14.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.14.1
Adds api_base and api_version config keys for Azure OpenAI support in the HolmesGPT configuration. Not checked yet Introduces LLM-based message summarization via a new Transformer mechanism to optimize context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. handling, improving accuracy with metrics and trace data. Not checked yet Adds a free-form Tempo toolset enabling natural-language trace queries such as 'Why was there an increase in latency?' and 'Find the cause of recent HTTP 500 errors.' Not checked yet Implements an LLM Model Registry allowing context size overrides per model. Not checked yet Adds max_tokens and max output tokens fields to Holmes responses. Not checked yet
+4 more
show less
Respects DEFAULT_LOG_LIMIT in the Loki integration for more controlled log retrieval. Not checked yet Improves Prometheus integration with better truncation and a reduced max query size cap. Not checked yet Improves DataDog integration with accuracy and error-handling enhancements. Not checked yet Improves Ollama support. Not checked yet
9 details in Everything
HolmesGPT 0.13.2 adds Datadog integration, cross-account IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. , Prometheus range queries, and CLI approval for bash tool execution.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.13.2 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.13.2
Adds a general-purpose Datadog tool, enabling HolmesGPT to query Datadog as part of AI-driven investigations. Not checked yet Adds cross-account IRSA support, allowing HolmesGPT to assume IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. roles across AWS accounts for multi-account Kubernetes environments. Not checked yet Adds Prometheus range-query support to the Prometheus toolset, enabling historical metric analysis over configurable time windows. Not checked yet Adds a CLI approval step for the bash tool, requiring explicit user confirmation before executing bash commands from the CLI. Not checked yet Adds manual and HPA-driven replica count control options. Not checked yet
5 details in Everything
HolmesGPT 0.13.1 adds AWS Bedrock single-token auth and AMP IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. support for IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. -based authentication.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.13.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.13.1
Adds single-token authentication support for AWS Bedrock as an LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. backend. Not checked yet Adds IRSA (IAM Roles for Service Accounts) support for Amazon Managed Prometheus (AMP) integration. Not checked yet Replaces CLI toolsets with a bash toolset. Not checked yet
3 details in Everything
HolmesGPT 0.13.0 adds a Datadog RDS analysis toolset, REASONING_EFFORT env var, streaming API chat, custom annotations, and subtask support.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.13.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.13.0
Adds support for the REASONING_EFFORT environment variable to control LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. reasoning effort at runtime. Not checked yet Adds call_stream support for the API chat endpoint, enabling streaming responses from the Holmes API. Not checked yet Adds an option for custom annotations on Holmes resources. Not checked yet Adds a new Datadog RDS analysis toolset for database-focused investigations via Datadog. Not checked yet Adds subtask support, allowing Holmes investigations to spawn and track sub-investigations. Not checked yet
+7 more
show less
Adds intermediate AI message and reasoning output via ai_message in investigation responses. Not checked yet Adds LLM support to the investigation workflow, broadening which models can drive investigations. Not checked yet Adds Prometheus AMP (Amazon Managed Prometheus) support alongside fixes to loading configs from environment variables. Not checked yet Adds icon_url field to tool call results in the API response. Not checked yet Adds revisionhistorylimit support for Kubernetes deployment configuration. Not checked yet Returns rate-limit errors to callers when the upstream LLM rate-limits Holmes. Not checked yet Adds an AI safety prompt to the system prompt for all Holmes interactions. Not checked yet
12 details in Everything
HolmesGPT 0.12.4 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server config file support, configurable config dir, OpenShift OpenShift Red Hat's Kubernetes distribution that adds developer workflows, built-in CI/CD, and stricter security defaults on top of upstream Kubernetes, giving cyber tools a managed container platform with enterprise auth and RBAC already wired in. Prometheus, YAML syntax highlighting, and faster startup.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.12.4 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.12.4
└──▷ USE IT
Configure an MCP server declaratively in the HolmesGPT config file instead of passing CLI flags each run.
yaml
copy
mcp_servers:
- name: my-mcp-server
url: http://localhost:8080
Point HolmesGPT at a non-default config directory, useful in multi-tenant or containerized environments.
copy
$ holmes ask --config-dir /etc/holmesgpt/prod 'Why is my pod crash-looping?'
Adds support for configuring MCP server in the config file, enabling declarative MCP server setup without CLI flags. Not checked yet Makes the config file directory configurable, allowing non-default config locations to be specified. Not checked yet Adds a toggle for the version check, letting users enable or disable the startup version check. Not checked yet Makes the agent name in the welcome banner configurable. Not checked yet Adds autocomplete for the /show command in interactive mode. Not checked yet
+9 more
show less
Adds YAML syntax highlighting for output in the /show command. Not checked yet Adds OpenShift Prometheus support as a metrics toolset. Not checked yet Enables HolmesGPT to unzip logs from findings, expanding log analysis coverage. Not checked yet Adds cluster name to the system prompt, giving the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. context about which cluster it is operating on. Not checked yet Adds line count to tool output for better readability of large results. Not checked yet Improves startup speed of holmes ask via lazy imports. Not checked yet Requests multiple tool calls for reasoning models to improve accuracy. Not checked yet Improves HolmesGPT accuracy on questions about itself, configuring tools, and using runbooks. Not checked yet Improves DataDog metrics toolset. Not checked yet
14 details in Everything
HolmesGPT 0.12.3 adds Datadog, Azure SQL, ServiceNow, Atlas MongoDB, and NSG NSG A Network Security Group is an Azure resource that filters inbound and outbound traffic to cloud resources using configurable allow/deny rules, giving cyber tools a policy layer to inspect or enforce network access control. toolsets plus interactive slash commands and a --refresh-toolsets flag.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.12.3 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.12.3
└──▷ TRY IT
Force a fresh toolset status check when a toolset may have become available since the last run.
copy
$ holmes ask --refresh-toolsets 'Why is my pod crash-looping?'
Pipe kubectl output directly into Holmes for inline investigation without a separate ask step.
copy
$ kubectl describe pod my-app-51 | holmes ask 'What is wrong with this pod?'
Adds --refresh-toolsets flag to the ask command to force a refresh of toolset status on demand. Not checked yet Introduces /run, /clear, /show, and /context slash commands in interactive mode. Not checked yet Adds Datadog logs toolset, Datadog metrics toolset, and Datadog traces toolset for querying logs, metrics, and traces from Datadog. Not checked yet Adds Azure SQL toolset for querying and troubleshooting Azure SQL databases. Not checked yet Adds Azure Network Security Groups (NSGs) toolset for inspecting network security group rules. Not checked yet
+14 more
show less
Adds Atlas MongoDB toolset for querying MongoDB Atlas clusters. Not checked yet Adds ServiceNow experimental toolset for integrating with ServiceNow. Not checked yet Introduces a runbook toolset (feat(runbook) ) to fetch and apply internal runbooks during investigations. Not checked yet Enriches AKS AKS Azure Kubernetes Service, Microsoft's managed Kubernetes offering, which lets cyber tools offload cluster provisioning and scaling to Azure so engineers focus on workload logic instead of control-plane operations. node health tools with additional diagnostic capabilities. Not checked yet Adds a toolset management tool command and caches toolset status to speed up repeated invocations. Not checked yet Enables Holmes to count Kubernetes resources during investigations. Not checked yet Makes interactive mode the default when running the CLI. Not checked yet Adds support for piped input to the Holmes CLI. Not checked yet Makes OpenSearch OpenSearch An open-source search and analytics engine, forked from Elasticsearch by AWS in 2021, that lets cyber tools store, query, and visualize large volumes of log or event data without licensing restrictions. environment variable and config description more generic for broader compatibility. Not checked yet Adds tracing support to the Holmes CLI. Not checked yet Injects global date context into prompts so the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. is aware of the current date. Not checked yet Checks Prometheus toolset health during auto-discovery, not only on explicit invocation. Not checked yet Checks toolset prerequisites in parallel, reducing CLI startup time. Not checked yet Adds an HTTP API with published documentation. Not checked yet
19 details in Everything
HolmesGPT 0.11.5 adds Remote MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server support for real-time access to external data sources and tools.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.11.5 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.11.5
└──▷ HOW TO FIND IT
Connect HolmesGPT to a remote MCP server to give it real-time access to an external tool or data source during investigations.
📍 See https://docs.robusta.dev/master/configuration/holmesgpt/remote_mcp_servers.html for the full configuration reference.
Adds Remote MCP server support, enabling HolmesGPT to connect to external data sources and tools in real time via configured remote endpoints. Not checked yet Loads the Robusta UI token from an environment variable when required, reducing manual credential configuration. Not checked yet Allows overriding the Grafana health-check URL via configuration, enabling custom Grafana deployment paths. Not checked yet Adds Azure OpenAI to the list of supported models. Not checked yet Removes the mandatory requirement for resource group, subscription, and cluster name in the AKS AKS Azure Kubernetes Service, Microsoft's managed Kubernetes offering, which lets cyber tools offload cluster provisioning and scaling to Azure so engineers focus on workload logic instead of control-plane operations. toolset, simplifying Azure configuration. Not checked yet
+1 more
show less
Restarts the Holmes pod automatically on config changes, ensuring configuration updates are applied without manual intervention. Not checked yet
6 details in Everything
HolmesGPT 0.11.2 adds direct connection support for Loki and Tempo datasources.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.11.2 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.11.2
Supports direct connections to Loki and Tempo, removing the requirement to route through a Grafana datasource. Not checked yet
1 detail in Everything
HolmesGPT 0.11.1 adds RabbitMQ, Elasticsearch, AKS AKS Azure Kubernetes Service, Microsoft's managed Kubernetes offering, which lets cyber tools offload cluster provisioning and scaling to Azure so engineers focus on workload logic instead of control-plane operations. , and Git toolsets plus Prometheus auto-discovery and multi-tenant Loki/Grafana support.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.11.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.11.1
└──▷ TRY IT
Supply a saved investigation prompt from a file instead of typing it inline — useful for repeatable runbook-style queries in CI or on-call workflows.
copy
$ holmes ask --prompt-file ./prompts/oom-investigation.txt
Use a named AWS profile when invoking Holmes with a Bedrock-backed model, avoiding the need to export credentials directly.
copy
$ AWS_PROFILE=prod-sre holmes ask 'Why is the payment service crashing?'
Adds --prompt-file argument to the holmes ask command to supply investigation prompts from a file. Not checked yet Adds AWS_PROFILE support in Bedrock model requirements for named AWS profile selection. Not checked yet New RabbitMQ toolset for querying RabbitMQ broker state during investigations. Not checked yet New Elasticsearch toolset for querying Elasticsearch during investigations. Not checked yet New Azure Kubernetes Service (AKS) toolset, including a dedicated AKS node health toolset and support for specifying the AKS environment. Not checked yet
+8 more
show less
New Git toolset enabling Holmes to inspect repository history as part of investigations. Not checked yet New workload KRR (Kubernetes Resource Recommender) tool for right-sizing analysis. Not checked yet Prometheus auto-discovery so Holmes can locate Prometheus instances without manual configuration. Not checked yet Multi-tenant Loki and Grafana support via additional headers configuration. Not checked yet Coralogix toolset gains archived log fetching and enhanced log query capabilities. Not checked yet Structured output Structured output Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. feature flag for controlling LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. response formatting. Not checked yet LLM selection support, allowing users to choose which model Holmes uses. Not checked yet Interactive clarifying questions and follow-up support after an investigation in the holmes ask command. Not checked yet
13 details in Everything
HolmesGPT 0.10.9 adds a by argument for investigating and enriching PagerDuty and JSM tickets.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.10.9 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.10.9
Adds by argument to the investigate and enrich commands for PagerDuty and JSM (Jira Service Management) tickets. Not checked yet
1 detail in Everything
HolmesGPT 0.10.8 adds custom Prometheus label support, streaming analysis, configurable Prometheus healthchecks, and improved ArgoCD ArgoCD A Kubernetes-native continuous delivery controller, maintained by the CNCF, that syncs live cluster state to declarative config stored in Git, giving cyber tools automated, auditable deployment pipelines. and Coralogix toolsets.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.10.8 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.10.8
Adds configurable Prometheus healthcheck support, allowing control over how Holmes validates Prometheus connectivity. Not checked yet Adds support for custom labels in Prometheus queries, enabling more targeted metric lookups. Not checked yet Adds streaming analysis output, delivering investigation results incrementally rather than waiting for full completion. Not checked yet Improves the ArgoCD toolset with enhanced integrations for application state analysis. Not checked yet Improves the Coralogix toolset to return source URLs alongside log results, making it easier to pivot directly to Coralogix. Not checked yet
+1 more
show less
Adds change history tools to support investigation workflows that incorporate recent change context. Not checked yet
6 details in Everything
HolmesGPT 0.10.5 adds Kafka, Coralogix, and Prometheus graph toolsets plus multi-cluster OpenSearch OpenSearch An open-source search and analytics engine, forked from Elasticsearch by AWS in 2021, that lets cyber tools store, query, and visualize large volumes of log or event data without licensing restrictions. /Kafka support and streaming responses.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.10.5 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.10.5
Adds Kafka toolset (kafka) for querying Kafka clusters, with support for multiple Kafka clusters in a single configuration. Not checked yet Adds initial Coralogix toolset (coralogix) for querying Coralogix logs, with prompt tuning for log retrieval. Not checked yet Adds Prometheus graph-generating capability to the prometheus toolset, enabling the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. to render metric graphs during investigations. Not checked yet Adds support for multiple OpenSearch clusters in the opensearch toolset configuration. Not checked yet Promotes Loki to a full-fledged log provider toolset (loki), replacing the previous limited integration. Not checked yet
+9 more
show less
Improves the Grafana Tempo toolset with enhanced trace querying capabilities. Not checked yet Adds OpenSearch logs and traces support, expanding OpenSearch toolset coverage beyond search. Not checked yet Adds streaming responses (ROB-717) so Holmes can stream answers to the CLI in real time. Not checked yet Adds auth improvements for internet, notion, and llm toolsets. Not checked yet Adds priorityClassName support to the Helm chart, allowing users to set the priority class name for Holmes pods. Not checked yet Adds node selector support to the Helm chart for pod scheduling control. Not checked yet Enables pod reloading when values.toolsets is updated via helm upgrade, so toolset config changes take effect without manual restarts. Not checked yet Improves fetch_url tool to work with GitHub Pages sources. Not checked yet Improves token counter performance via caching, reducing overhead on large investigations. Not checked yet
14 details in Everything
HolmesGPT 0.8.1 adds Gemini, ArgoCD ArgoCD A Kubernetes-native continuous delivery controller, maintained by the CNCF, that syncs live cluster state to declarative config stored in Git, giving cyber tools automated, auditable deployment pipelines. , OpenSearch OpenSearch An open-source search and analytics engine, forked from Elasticsearch by AWS in 2021, that lets cyber tools store, query, and visualize large volumes of log or event data without licensing restrictions. , and Grafana Loki toolsets plus AI output customization and global instructions.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.8.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.8.1
Adds ArgoCD toolset integration, bringing ArgoCD application state into Holmes investigations. Not checked yet Adds OpenSearch toolset integration for querying OpenSearch data during investigations. Not checked yet Adds Grafana Loki toolset integration for pulling logs from Loki during root-cause analysis. Not checked yet Adds Gemini LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. support as a backend model option. Not checked yet Adds global instructions capability, allowing operators to inject persistent context into all Holmes prompts. Not checked yet
+5 more
show less
Adds AI output customization (MAIN-2806), enabling custom sections and structured output structured output Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. shaping in RCA responses. Not checked yet Adds kubectl with jq as a built-in tool, enabling JSON-filtered Kubernetes queries inside Holmes investigations. Not checked yet Adds pod affinity configuration support to the Helm chart. Not checked yet Adds optional performance logging to improve observability of Holmes internals. Not checked yet Adds app diagnose chat capability for interactive application diagnosis sessions. Not checked yet
10 details in Everything
HolmesGPT 0.7.2 adds the ability to fetch deployment configuration data during investigations.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.7.2 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.7.2
Adds option to fetch deployment config, expanding the Kubernetes context available during investigations. Not checked yet
1 detail in Everything
HolmesGPT 0.7.1 adds WatsonX support, kubectl events, grep log search, and memory-request inspection tools.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.7.1 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.7.1
Adds kubectl_logs_grep tool, enabling Holmes to search pod logs using grep (upgraded to grep -E extended regex) to surface relevant log lines faster. Not checked yet Adds a tool to fetch top memory requests across the cluster, giving the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. visibility into resource consumption. Not checked yet Adds kubectl events capability so Holmes can retrieve and reason over Kubernetes events during investigations. Not checked yet Enables the LLM to fetch logs from all containers or a specific container within a pod, expanding container-level log coverage. Not checked yet Adds IBM WatsonX as a supported LLM backend, broadening model provider options. Not checked yet
+2 more
show less
Adds tag support to the ask holmes command, allowing queries to be scoped or annotated with tags. Not checked yet Adds LLM evaluations framework for testing and benchmarking Holmes response quality. Not checked yet
7 details in Everything
HolmesGPT 0.6.0 adds runbook URL support, custom LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. backends, kubectl top, and a new conversation API
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.6.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.6.0
Adds support for passing runbook URLs to the issue investigator, letting Holmes pull context from your own runbooks during investigations. Not checked yet Supports custom LLM implementations, enabling teams to plug in their own LLM backends beyond the built-in providers. Not checked yet Supports removing the Bedrock prefix from model name tokens for AWS Bedrock LLM configurations. Not checked yet Adds a kubectl top action to the toolset, giving the AI agent access to live resource-usage metrics during investigations. Not checked yet Adds a new conversation functionality, enabling multi-turn interactions with the investigator. Not checked yet
+1 more
show less
Adds an RDS single-instance lookup command to the AWS toolset for more targeted cloud investigations. Not checked yet
6 details in Everything
HolmesGPT 0.5.0 adds custom toolsets to the Helm chart and improved in-cluster authentication.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.5.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.5.0
Adds custom toolsets support to the Helm chart deployment. Not checked yet Adds improved in-cluster authentication handling. Not checked yet
2 details in Everything
HolmesGPT 0.4.0 adds tool_calls to the /api/conversation endpoint and lets you override the UI token via environment variable.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.4.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.4.0
The POST /api/conversation endpoint now returns tool_calls in its response, exposing which tools Holmes invoked during an investigation. Not checked yet Allows overriding the UI token with an environment variable instead of requiring it to be set in config. Not checked yet Improves CLI logging and expands the --verbose flag for more detailed diagnostic output. Not checked yet Improves prompt output to produce more detailed investigation results. Not checked yet
4 details in Everything
HolmesGPT 0.3.0 adds AWS/Confluence/Slab tools, a workload health endpoint, Robusta AI support, parallel tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. , and custom CA trust.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.3.0 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.3.0
└──▷ USE IT
Set the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. model once in config rather than passing it on every CLI invocation.
Adds model parameter support in the config file, allowing the LLM model to be set without a CLI flag. Not checked yet Adds AWS, Confluence, internet, and Slab tools, expanding the set of data sources Holmes can query during investigations. Not checked yet Adds a workload health API endpoint with JSON response, enabling programmatic health checks via the Holmes server. Not checked yet Adds a chat input box API for programmatic interaction with Holmes. Not checked yet Adds support for Robusta AI as an LLM backend for Holmes. Not checked yet
+5 more
show less
Adds support for trusting custom CA certificates, enabling use with private TLS infrastructure. Not checked yet Adds tolerations support for the Holmes pod, allowing scheduling on tainted Kubernetes nodes. Not checked yet Enables parallel tool calling, allowing Holmes to invoke multiple tools simultaneously for faster investigation. Not checked yet Adds K9s plugin integration, letting users invoke Holmes directly from the K9s terminal UI. Not checked yet Increases accuracy of holmes ask results through improved prompting. Not checked yet
10 details in Everything
HolmesGPT 0.2.6 adds Slack output for the ask command, streamlined Amazon Bedrock support, and LiteLLM env var support in Helm.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.2.6 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.2.6
Helm chart now supports LiteLLM environment variables for configuring LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. backends. Not checked yet Adds Slack as a destination for the ask command, enabling query results to be sent directly to Slack channels. Not checked yet Streamlines Amazon Bedrock integration alongside other LLM models for a more seamless setup experience. Not checked yet Adds a post-processing option for verbose (chatty ) AI responses. Not checked yet Updates PagerDuty integration with minor improvements. Not checked yet
+2 more
show less
Adds Prometheus Operator RBAC RBAC Role-based access control, where permissions are assigned to roles such as reader or administrator and users receive those roles. It makes access easier to manage than individual permission lists. rules for Holmes to the service account template in the Helm chart. Not checked yet Improves the Kubernetes toolset with minor enhancements. Not checked yet
7 details in Everything
HolmesGPT 0.2.5 adds a --file flag and ships as a pip-installable Python package.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.2.5 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.2.5
└──▷ TRY IT
Feed a pre-written investigation prompt from a file instead of typing it inline on the command line.
copy
$ holmes ask --file <path>
Adds --file flag to pass input from a file directly to the CLI. Not checked yet Makes HolmesGPT installable as a Python package via pip. Not checked yet
2 details in Everything
HolmesGPT 0.2.4 adds label-based filtering for Alertmanager alert ingestion.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.2.4 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.2.4
HolmesGPT 0.2.2 adds OpsGenie and PagerDuty investigation commands and JSON output flag.
└──▷ GET THIS VERSION
copy
$ git clone --branch 0.2.2 https://github.com/HolmesGPT/holmesgpt.git
$ git checkout 0.2.2
Adds holmes investigate opsgenie command to investigate OpsGenie alerts directly from the CLI. Not checked yet Adds holmes investigate pagerduty command to investigate PagerDuty incidents directly from the CLI. Not checked yet Adds a CLI flag to write investigation output to JSON for machine-readable results. Not checked yet
3 details in Everything