<div align="center">
<h1 align="center">HolmesGPT — The CNCF SRE Agent</h1>
<p align="center">
<a href="#installation"><strong>Installation</strong></a> |
<a href="https://holmesgpt.dev/"><strong>Docs</strong></a> |
<a href="https://deepwiki.com/HolmesGPT/holmesgpt"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
</p>
</div>
Open-source AI agent for investigating production incidents and finding root causes. Works with any stack — Kubernetes, VMs, cloud providers, databases, and SaaS platforms. We are a Cloud Native Computing Foundation sandbox project. Originally created by Robusta.Dev, with major contributions from Microsoft.
New: Operator Mode — Find Problems 24/7 in the Background
Most AI agents are great at troubleshooting problems, but still need a human to notice something is wrong and trigger an investigation. Operator mode fixes that — HolmesGPT runs in the background 24/7, spots problems before your customers notice, and messages you in Slack with the fix. Connect the GitHub integration and it can even open PRs to fix what it finds.
While the operator itself runs in Kubernetes, health checks can query any data source Holmes is connected to — VMs, cloud services, databases, SaaS platforms, and more.
Features
- Petabyte-scale data: Server-side filtering, JSON tree traversal, and tool output transformers keep large payloads out of context windows
- Memory-safe execution: Per-tool memory limits, streaming large results to disk, and automatic output budgeting prevent OOM kills when querying large observability datasets
- Deep integrations: Prometheus, Grafana, Datadog, Kubernetes, and many more—plus any REST API
- Bidirectional alert integrations: Fetch alerts from AlertManager, PagerDuty, OpsGenie, or Jira—and write findings back
- Any LLM provider: OpenAI, Anthropic, Azure, Bedrock, Gemini, and more
- No Kubernetes required: Works with any infrastructure — VMs, bare metal, cloud services, or containers
How it Works
HolmesGPT uses an agentic loop to query live observability data from multiple sources and identify root causes.
<img width="3114" alt="holmesgpt-architecture-diagram" src="https://github.com/user-attachments/assets/f659707e-1958-4add-9238-8565a5e3713a" />
🔗 Data Sources
HolmesGPT integrates with popular observability and cloud platforms. The following data sources ("toolsets") are built-in. Add your own.
| Data Source | Notes |
|---|
| <img src="images/integration_logos/aks-icon.png" alt="AKS" width="20" style="vertical-align: middle;"> AKS | Azure Kubernetes Service cluster and node health diagnostics |
| <img src="images/integration_logos/jira-icon.png" alt="Atlassian Rovo" width="20" style="vertical-align: middle;"> Atlassian Rovo | Jira issues and Confluence pages via Atlassian's hosted server (MCP) |
| <img src="images/integration_logos/argocd-icon.png" alt="ArgoCD" width="20" style="vertical-align: middle;"> ArgoCD | Get status, history and manifests and more of apps, projects and clusters |
| <img src="images/integration_logos/aws_logo.png" alt="AWS" width="20" style="vertical-align: middle;"> AWS | Any AWS API via the hosted AWS MCP Server: RDS, EC2, CloudWatch, CloudTrail, Cost Explorer and more (MCP) |
| <img src="images/integration_logos/azure.png" alt="Azure" width="20" style="vertical-align: middle;"> Azure | Azure resources and diagnostics (MCP) |
| <img src="images/integration_logos/confluence_logo.png" alt="Confluence" width="20" style="vertical-align: middle;"> Confluence | Private runbooks and documentation |
| <img src="images/integration_logos/confluence_logo.png" alt="Confluence MCP" width="20" style="vertical-align: middle;"> Confluence (MCP) | Private runbooks and documentation (MCP) |
| <img src="images/integration_logos/coralogix-icon.png" alt="Coralogix" width="20" style="vertical-align: middle;"> Coralogix | Retrieve logs for any resource |
| <img src="images/integration_logos/crossplane-icon.png" alt="Crossplane" width="20" style="vertical-align: middle;"> Crossplane | Troubleshoot Crossplane providers, compositions, claims, and managed resources |
| <img src="images/integration_logos/datadog_logo.png" alt="Datadog" width="20" style="vertical-align: middle;"> Datadog | Query logs, metrics, and traces |
| <img src="images/integration_logos/docker_logo.png" alt="Docker" width="20" style="vertical-align: middle;"> Docker | Get images, logs, events, history and more |
| <img src="images/integration_logos/opensearchserverless-icon.png" alt="Elasticsearch" width="20" style="vertical-align: middle;"> Elasticsearch / OpenSearch | Query logs, cluster health, shard and index diagnostics |
| <img src="images/integration_logos/gcpmonitoring-icon.png" alt="GCP" width="20" style="vertical-align: middle;"> GCP | Google Cloud Platform resources (MCP) |
| <img src="images/integration_logos/github_logo.png" alt="GitHub" width="20" style="vertical-align: middle;"> GitHub | Repositories, issues, and pull requests (MCP) |
| <img src="images/integration_logos/gitlab-icon.png" alt="GitLab" width="20" style="vertical-align: middle;"> GitLab | Projects, merge requests, issues, and CI/CD pipelines (MCP) |
| <img src="images/integration_logos/jenkins-icon.png" alt="Jenkins" width="20" style="vertical-align: middle;"> Jenkins (MCP) | Build status, pipeline logs, and job history (MCP) |
| <img src="images/integration_logos/grafana-icon.png" alt="Grafana" width="20" style="vertical-align: middle;"> Grafana | Query and analyze dashboard configurations and panels |
| <img src="images/integration_logos/helm_logo.png" alt="Helm" width="20" style="vertical-align: middle;"> Helm | Release status, chart metadata, and values |
| <img src="images/integration_logos/http-icon.png" alt="Internet" width="20" style="vertical-align: middle;"> Internet | Public runbooks, community docs, etc. |
| <img src="images/integration_logos/kafka_logo.png" alt="Kafka" width="20" style="vertical-align: middle;"> Kafka | Fetch metadata, list consumers and topics or find lagging consumer groups |
| <img src="images/integration_logos/kubernetes-icon.png" alt="Kubernetes" width="20" style="vertical-align: middle;"> Kubernetes | Pod logs, K8s events, and resource status (kubectl describe) |
| <img src="images/integration_logos/kubernetes-icon.png" alt="Kubernetes Remediation" width="20" style="vertical-align: middle;"> Kubernetes Remediation (MCP) | Apply fixes like scaling, rollbacks, and resource edits (MCP) |
| <img src="images/integration_logos/grafana_loki-icon.png" alt="Loki" width="20" style="vertical-align: middle;"> Loki | Query logs for Kubernetes resources or any query |
| <img src="images/integration_logos/postgres-icon.png" alt="MariaDB" width="20" style="vertical-align: middle;"> MariaDB | MariaDB database queries and diagnostics |
| <img src="images/integration_logos/postgres-icon.png" alt="MongoDB" width="20" style="vertical-align: middle;"> MongoDB | Query data, diagnose performance, inspect schemas, find slow operations |
| <img src="images/integration_logos/postgres-icon.png" alt="MongoDB Atlas" width="20" style="vertical-align: middle;"> MongoDB Atlas | Cluster health, slow queries, and performance diagnostics |
| <img src="images/integration_logos/newrelic_logo.png" alt="NewRelic" width="20" style="vertical-align: middle;"> NewRelic | Investigate alerts, query tracing data |
| <img src="images/integration_logos/openshift-icon.png" alt="OpenShift" width="20" style="vertical-align: middle;"> OpenShift | Projects, routes, builds, security context constraints, and deployment configs |
| <img src="images/integration_logos/prefect-icon.png" alt="Prefect" width="20" style="vertical-align: middle;"> Prefect (MCP) | Workflow orchestration monitoring, flow runs, and worker health (MCP) |
| <img src="images/integration_logos/prometheus-icon.png" alt="Prometheus" width="20" style="vertical-align: middle;"> Prometheus | Investigate alerts, query metrics and generate PromQL queries |
| <img src="images/integration_logos/rabbit_mq_logo.png" alt="RabbitMQ" width="20" style="vertical-align: middle;"> RabbitMQ | Partitions, memory/disk alerts, troubleshoot split-brain scenarios and more |
| <img src="images/integration_logos/robusta_logo.png" alt="Robusta" width="20" style="vertical-align: middle;"> Robusta | Multi-cluster monitoring, historical change data, runbooks, PromQL graphs and more |
| <img src="images/integration_logos/servicenow-icon.png" alt="ServiceNow" width="20" style="vertical-align: middle;"> ServiceNow | Query tables and incident records |
| <img src="images/integration_logos/sentry-icon.png" alt="Sentry" width="20" style="vertical-align: middle;"> Sentry | Error tracking, issues, and performance monitoring (MCP) |
| <img src="images/integration_logos/slab_logo.png" alt="Slab" width="20" style="vertical-align: middle;"> Slab | Team knowledge base and runbooks on demand |
| Splunk | Log search and analysis (MCP) |
| <img src="images/integration_logos/postgres-icon.png" alt="SQL Databases" width="20" style="vertical-align: middle;"> SQL Databases | PostgreSQL, MySQL, ClickHouse, MariaDB, SQL Server, Azure SQL, SQLite |
| <img src="images/integration_logos/tempo_logo.png" alt="Tempo" width="20" style="vertical-align: middle;"> Tempo | Fetch trace info, debug issues like high latency in application |
| <img src="images/integration_logos/victorialogs-icon.png" alt="VictoriaLogs" width="20" style="vertical-align: middle;"> VictoriaLogs | Query logs from VictoriaLogs using LogsQL |
| VictoriaMetrics | Query metrics from a Prometheus-compatible TSDB (vmsingle / vmcluster) |
| <img src="images/integration_logos/zabbix-icon.png" alt="Zabbix" width="20" style="vertical-align: middle;"> Zabbix | Monitor hosts, problems, events, triggers, and historical metrics |
See the full list of built-in toolsets for additional integrations including Cilium, KubeVela, Notion, and more.
🚀 End-to-End Automation
HolmesGPT can fetch alerts/tickets to investigate from external systems, then write the analysis back to the source or Slack.
| Integration | Status | Notes |
|---|
| Slack | ✅ | Demo. Available via Robusta |
| Microsoft Teams | ✅ | Available via Robusta |
| Prometheus/AlertManager | ✅ | Robusta or HolmesGPT CLI |
| PagerDuty | ✅ | HolmesGPT CLI only |
| OpsGenie | ✅ | HolmesGPT CLI only |
| Jira | ✅ | HolmesGPT CLI only |
| GitHub | ✅ | HolmesGPT CLI only |
Installation
<a href="https://holmesgpt.dev/installation/cli-installation/">
<img src="images/integration_logos/all-installation-methods.png" alt="All Installation Methods" style="max-width:100%; height:auto;">
</a>
Read the installation documentation to learn how to install HolmesGPT.
Supported LLM Providers
<a href="https://holmesgpt.dev/ai-providers/">
<img src="images/integration_logos/all-integration-providers.png" alt="All Integration Providers" style="max-width:100%; height:auto;">
</a>
Read the LLM Providers documentation to learn how to set up your LLM API key.
Using HolmesGPT
See the walkthrough documentation for usage guides, including:
🔐 Data Privacy
By design, HolmesGPT has read-only access and respects RBAC permissions. It is safe to run in production environments.
License
Distributed under the Apache 2.0 License. See LICENSE for more information.
<!-- Change License -->
Community
Join our community to discuss the HolmesGPT roadmap and share feedback:
Support
If you have any questions, feel free to message us on HolmesGPT Slack Channel
How to Contribute
Please read our CONTRIBUTING.md for guidelines and instructions.
For help, contact us on Slack or ask DeepWiki AI your questions.
Please make sure to follow the CNCF code of conduct - details here.
by HolmesGPT