# HolmesGPT review

> HolmesGPT is an open-source AI agent that investigates production incidents and finds root causes across Kubernetes, VMs, cloud services, databases and SaaS platforms.

Devtoolwatch Board, the week of Oct 25–31, 2026. Canonical page: https://index.devtoolwatch.com/tools/holmesgpt-holmesgpt/

## TL;DR

HolmesGPT is an open-source SRE agent and CNCF sandbox project for investigating production incidents. It is for SRE and DevOps teams who want an LLM to query live observability data and find root causes. It ships many built-in data source integrations, works with any LLM provider, and offers an operator mode that runs health checks in the background.

## HolmesGPT at a glance

- **Category:** [Coding agents](https://index.devtoolwatch.com/categories/coding-agents/)
- **Maintained by:** HolmesGPT (organization, [@HolmesGPT](https://github.com/HolmesGPT) on GitHub)
- **License:** Apache 2.0
- **Language:** Python, HTML, Jinja
- **Repository:** [github.com/HolmesGPT/holmesgpt](https://github.com/HolmesGPT/holmesgpt)
- **Website:** [holmesgpt.dev](https://holmesgpt.dev/)
- **PyPI package:** [holmesgpt](https://pypi.org/project/holmesgpt/) 0.45.0
- **Latest release:** [0.45.0](https://github.com/HolmesGPT/holmesgpt/releases/tag/0.45.0) on GitHub, Oct 15, 2026
- **First published:** May 30, 2024

## What HolmesGPT does

- HolmesGPT uses an agentic loop to query live observability data from multiple sources and identify root causes of incidents.
- HolmesGPT includes built-in toolsets for Prometheus, Grafana, Datadog, Kubernetes, Loki, Elasticsearch, SQL databases, AWS, GCP, Azure and more.
- HolmesGPT fetches alerts from AlertManager, PagerDuty, OpsGenie or Jira and writes its findings back to the source.
- HolmesGPT operator mode runs in Kubernetes 24/7, runs scheduled health checks and deployment verification, and messages findings in Slack.
- HolmesGPT can open pull requests to fix problems it finds when the GitHub integration is connected.
- HolmesGPT keeps large payloads out of context windows with server-side filtering, JSON tree traversal and tool output transformers.
- HolmesGPT supports custom toolsets and any REST API as a data source.

### How it works

HolmesGPT runs as a CLI or, in operator mode, inside Kubernetes. It connects to an LLM provider such as OpenAI, Anthropic, Azure, Bedrock or Gemini. It queries data sources called toolsets, including several over MCP. By design, its access is read-only and it respects RBAC permissions. Slack and Microsoft Teams output is available through Robusta.

## How to install HolmesGPT

**From PyPI**

```
pip install holmesgpt
```

### Requirements

- Python 3.10 or later, below 3.14, for the PyPI package
- An API key for a supported LLM provider
- A Kubernetes cluster for operator mode only

### First steps

1. Follow the HolmesGPT CLI installation documentation at holmesgpt.dev to install the tool.
2. Set up an LLM API key using the HolmesGPT LLM Providers documentation.
3. Use HolmesGPT interactive mode to ask questions about your systems and follow up on the answers.
4. Try investigating a Prometheus alert with HolmesGPT, following the walkthrough guide.

## Who HolmesGPT is for

- SRE and on-call teams investigating production incidents and alerts
- Teams with observability data spread across Prometheus, Datadog, Loki, Elasticsearch and similar tools
- Kubernetes operators who want continuous background health checks and deployment verification
- CI/CD troubleshooting across GitHub, GitLab or Jenkins pipelines

### Limitations

- HolmesGPT operator mode runs in Kubernetes, though its health checks can query other data sources.
- HolmesGPT Slack and Microsoft Teams integrations are available through Robusta, not the CLI alone.
- HolmesGPT PagerDuty, OpsGenie, Jira and GitHub alert integrations are available in the HolmesGPT CLI only.
- HolmesGPT requires an external LLM provider API key.

## Usage data (the week of Oct 25–31, 2026)

- Board rank: #187 overall, #67 in Coding agents, momentum score 46
- Downloads that week: 5.6k (+86% vs 4-week average)
- New GitHub stars per week (last 12 weeks): Aug 9: 52; Aug 16: 50; Aug 23: 50; Aug 30: 46; Sep 6: 69; Sep 13: 135; Sep 20: 48; Sep 27: 40; Oct 4: 67; Oct 11: 57; Oct 18: 63; Oct 25: 58

## HolmesGPT alternatives

| Rank | Tool | Stars | Downloads/wk |
|---|---|---|---|
| #1 | [Cindy](https://index.devtoolwatch.com/tools/makecindy-cindy/) | 8.8k | – |
| #2 | [OpenMausBot](https://index.devtoolwatch.com/tools/milind-soni-openmausbot/) | 9.6k | – |
| #3 | [Orca](https://index.devtoolwatch.com/tools/stablyai-orca/) | 111.7k | – |
| #4 | [OpenBot](https://index.devtoolwatch.com/tools/copilotkit-openbot/) | 9.1k | – |
| #5 | [Agent Reach](https://index.devtoolwatch.com/tools/panniantong-agent-reach/) | 107.2k | – |
| #6 | [Skill Recorder](https://index.devtoolwatch.com/tools/microsoft-skill-recorder/) | 5.6k | – |

## HolmesGPT FAQ

### Is HolmesGPT free and open source?

Yes. HolmesGPT's source code is on GitHub (HolmesGPT/holmesgpt) under the Apache 2.0 license, so you can use it for free.

### How do I install HolmesGPT?

Run `pip install holmesgpt`. The holmesgpt package needs Python 3.10 or newer, below 3.14.

### Is HolmesGPT still maintained?

Yes. The HolmesGPT/holmesgpt repository was last updated on Oct 21, 2026, and the latest release, 0.45.0 on GitHub, came out on Oct 15, 2026.

### How popular is HolmesGPT?

HolmesGPT has 3.7k GitHub stars as of Nov 1, 2026. It gained 58 new stars in the week of Oct 25–31, 2026, against a 12-week average of 61 a week. Its main package had 5.6k downloads that week, +86% against its own 4-week average. That made it #67 among AI coding agents on the Devtoolwatch Board.

### What are the best alternatives to HolmesGPT?

Other AI coding agents on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: Cindy (#1), OpenMausBot (#2), Orca (#3), OpenBot (#4), Agent Reach (#5). The alternatives table above has their numbers.

### Does HolmesGPT require Kubernetes?

No. HolmesGPT works with VMs, bare metal, cloud services and containers. Only operator mode runs inside Kubernetes, and its health checks can still query non-Kubernetes data sources.

### Which LLM providers does HolmesGPT support?

HolmesGPT supports OpenAI, Anthropic, Azure, Bedrock, Gemini and other providers. You configure the provider with an API key, as described in the LLM Providers documentation.

### Is HolmesGPT safe to run in production?

HolmesGPT is designed for production use. By design, it has read-only access and respects RBAC permissions, and the README states it is safe to run in production environments.

### Can HolmesGPT fix problems automatically?

HolmesGPT can propose fixes. In operator mode with the GitHub integration, it can open pull requests. A Kubernetes Remediation MCP toolset can apply scaling, rollbacks and resource edits.

### Who maintains HolmesGPT?

HolmesGPT is a Cloud Native Computing Foundation sandbox project. Robusta.Dev originally created it, and Microsoft made major contributions.

## Sources

1. [HolmesGPT/holmesgpt on GitHub](https://github.com/HolmesGPT/holmesgpt)
2. [HolmesGPT README](https://github.com/HolmesGPT/holmesgpt/blob/master/README.md)
3. [holmesgpt on PyPI](https://pypi.org/project/holmesgpt/)
4. [HolmesGPT website](https://holmesgpt.dev/)
5. [Release 0.45.0 (Oct 15, 2026)](https://github.com/HolmesGPT/holmesgpt/releases/tag/0.45.0)
6. [Release 0.45.0-alpha (Oct 15, 2026)](https://github.com/HolmesGPT/holmesgpt/releases/tag/0.45.0-alpha)
7. [Release 0.44.0 (Oct 14, 2026)](https://github.com/HolmesGPT/holmesgpt/releases/tag/0.44.0)
8. [Devtoolwatch Board, the week of Oct 25–31, 2026](https://index.devtoolwatch.com/)