| Name | holmesgpt JSON |
| Version |
0.12.3
JSON |
| download |
| home_page | None |
| Summary | None |
| upload_time | 2025-07-24 19:29:43 |
| maintainer | None |
| docs_url | None |
| author | Natan Yellin |
| requires_python | <4.0,>=3.10 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<div align="center">
<h1 align="center">Solve alerts faster with an AI Agent</h1>
<p align="center">
<a href="#how-it-works"><strong>How it Works</strong></a> |
<a href="#installation"><strong>Installation</strong></a> |
<a href="#supported-llm-providers"><strong>LLM Providers</strong></a> |
<a href="https://www.youtube.com/watch?v=TfQfx65LsDQ"><strong>YouTube Demo</strong></a> |
<a href="https://deepwiki.com/robusta-dev/holmesgpt"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
</p>
</div>
Respond to alerts faster, using AI to automatically:
- Fetch logs, traces, and metrics
- Determine if issues are application or infrastructure related
- Find upstream root-causes
Using HolmesGPT, you can transform your existing alerts from this 👇
To this 👇
<img width="600" alt="example-holmesgpt-analysis" src="https://github.com/user-attachments/assets/d03df693-9eff-4d61-8947-2b101f648c3e" />
### How it Works
HolmesGPT connects AI models with live observability data and organizational knowledge. It uses an **agentic loop** to analyze data from multiple sources and identify possible 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](#customizing-holmesgpt).
| Data Source | Status | Notes |
|-------------|--------|-------|
| [<img src="images/integration_logos/argocd-icon.png" alt="ArgoCD" width="20" style="vertical-align: middle;"> **ArgoCD**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/argocd.html) | ✅ | Get status, history and manifests and more of apps, projects and clusters |
| [<img src="images/integration_logos/aws_rds_logo.png" alt="AWS RDS" width="20" style="vertical-align: middle;"> **AWS RDS**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/aws.html) | ✅ | Fetch events, instances, slow query logs and more |
| [<img src="images/integration_logos/confluence_logo.png" alt="Confluence" width="20" style="vertical-align: middle;"> **Confluence**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/confluence.html) | ✅ | Private runbooks and documentation |
| [<img src="images/integration_logos/coralogix-icon.png" alt="Coralogix Logs" width="20" style="vertical-align: middle;"> **Coralogix Logs**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/coralogix_logs.html) | ✅ | Retrieve logs for any resource |
| [<img src="images/integration_logos/date_time_icon.png" alt="Datetime" width="20" style="vertical-align: middle;"> **Datetime**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/datetime.html) | ✅ | Date and time-related operations |
| [<img src="images/integration_logos/docker_logo.png" alt="Docker" width="20" style="vertical-align: middle;"> **Docker**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/docker.html) | ✅ | Get images, logs, events, history and more |
| <img src="images/integration_logos/github_logo.png" alt="GitHub" width="20" style="vertical-align: middle;"> **GitHub** | 🟡 Beta | Remediate alerts by opening pull requests with fixes |
| <img src="images/integration_logos/datadog_logo.png" alt="DataDog" width="20" style="vertical-align: middle;"> **DataDog** | 🟡 Beta | Fetches log data from datadog |
| [<img src="images/integration_logos/grafana_loki-icon.png" alt="Loki" width="20" style="vertical-align: middle;"> **Grafana Loki**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/grafanaloki.html) | ✅ | Query logs for Kubernetes resources or any query |
| [<img src="images/integration_logos/tempo_logo.png" alt="Tempo" width="20" style="vertical-align: middle;"> **Grafana Tempo**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/grafanatempo.html) | ✅ | Fetch trace info, debug issues like high latency in application. |
| [<img src="images/integration_logos/helm_logo.png" alt="Helm" width="20" style="vertical-align: middle;"> **Helm**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/helm.html) | ✅ | Release status, chart metadata, and values |
| [<img src="images/integration_logos/http-icon.png" alt="Internet" width="20" style="vertical-align: middle;"> **Internet**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/internet.html) | ✅ | Public runbooks, community docs etc |
| [<img src="images/integration_logos/kafka_logo.png" alt="Kafka" width="20" style="vertical-align: middle;"> **Kafka**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/kafka.html) | ✅ | 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**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/kubernetes.html) | ✅ | Pod logs, K8s events, and resource status (kubectl describe) |
| <img src="images/integration_logos/newrelic_logo.png" alt="NewRelic" width="20" style="vertical-align: middle;"> **NewRelic** | 🟡 Beta | Investigate alerts, query tracing data |
| [<img src="images/integration_logos/opensearchserverless-icon.png" alt="OpenSearch" width="20" style="vertical-align: middle;"> **OpenSearch**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/opensearch.html) | ✅ | Query health, shard, and settings related info of one or more clusters|
| [<img src="images/integration_logos/prometheus-icon.png" alt="Prometheus" width="20" style="vertical-align: middle;"> **Prometheus**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/prometheus.html) | ✅ | 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**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/rabbitmq.html) | ✅ | Info about partitions, memory/disk alerts to troubleshoot split-brain scenarios and more |
| [<img src="images/integration_logos/robusta_logo.png" alt="Robusta" width="20" style="vertical-align: middle;"> **Robusta**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/robusta.html) | ✅ | Multi-cluster monitoring, historical change data, user-configured runbooks, PromQL graphs and more |
| [<img src="images/integration_logos/slab_logo.png" alt="Slab" width="20" style="vertical-align: middle;"> **Slab**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/slab.html) | ✅ | Team knowledge base and runbooks on demand |
### 🔐 Data Privacy
By design, HolmesGPT has **read-only access** and respects RBAC permissions. It is safe to run in production environments.
We do **not** train HolmesGPT on your data. Data sent to Robusta SaaS is private to your account.
For extra privacy, [bring an API key](https://robusta-dev.github.io/holmesgpt/ai-providers/) for your own AI model.
### 🚀 Bi-Directional Integrations With Your Tools
Robusta can investigate alerts - or just answer questions - from the following sources:
| Integration | Status | Notes |
|-------------------------|-----------|-------|
| Slack | 🟡 Beta | [Demo.](https://www.loom.com/share/afcd81444b1a4adfaa0bbe01c37a4847) Tag HolmesGPT bot in any Slack message |
| Prometheus/AlertManager | ✅ | Robusta SaaS or HolmesGPT CLI |
| PagerDuty | ✅ | HolmesGPT CLI only |
| OpsGenie | ✅ | HolmesGPT CLI only |
| Jira | ✅ | HolmesGPT CLI only |
### See it in Action
<a href="https://www.loom.com/share/388d98aad1a04823b9ed50d0161a4819?sid=a2a669b4-f092-4067-adcb-c8527fbcaa90" target="_blank">
<img style="max-width:300px;" src="https://cdn.loom.com/sessions/thumbnails/388d98aad1a04823b9ed50d0161a4819-0ced91a0e8f80dcb-full-play.gif">
</a>
## Installation
You can install HolmesGPT in one of the follow three methods:
1. [Standalone](https://robusta-dev.github.io/holmesgpt/installation/cli-installation/): Run HolmesGPT from your terminal as a CLI tool. Typically installed with **Homebrew** or **Pip/Pipx**. Ideal for local use, **embedding into shell scripts, or CI/CD pipelines.** (E.g. to analyze why a pipeline deploying to Kubernetes failed.)
2. **Web UIs and TUIs**: HolmesGPT is embedded in several third-party tools, like [Robusta SaaS](https://platform.robusta.dev/signup/?utm_source=github&utm_medium=holmesgpt-readme&utm_content=ways_to_use_holmesgpt_section) and [K9s](https://robusta-dev.github.io/holmesgpt/installation/ui-installation/) (as a plugin).
3. **API**: Embed HolmesGPT in your own app to quickly add **root-cause-analysis functionality and data correlations across multiple sources like logs, metrics, and events**. HolmesGPT exposes an HTTP API and [Python SDK](https://robusta-dev.github.io/holmesgpt/installation/python-installation/), as well as [Helm chart](./helm/) to deploy the HTTP server on Kubernetes.
<table width="100%">
<tr valign="top">
<td colspan="2">
<h3>Standalone</h3>
<table width="100%">
<tr>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/installation/cli-installation/">
<img src="images/integration_logos/brew_logo.png" alt="Brew" width="50"><br>
<strong>Brew</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/installation/cli-installation/">
<img src="images/integration_logos/pipx_logo.png" alt="pipx" width="50"><br>
<strong>Pipx</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/installation/cli-installation/">
<img src="images/integration_logos/docker_logo.png" alt="Docker" width="50"><br>
<strong>Docker</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/installation/cli-installation/">
<img src="images/integration_logos/docker_logo.png" alt="Docker Build" width="50"><br>
<strong>Docker Build</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/installation/cli-installation/">
<img src="images/integration_logos/python_poetry_logo.png" alt="Python Poetry" width="50"><br>
<strong>Poetry</strong>
</a>
</td>
</tr>
</table>
</td>
</tr>
<tr valign="top">
<td width="30%">
<h3>Web UIs and TUIs</h3>
<table>
<tr>
<td align="center" width="120">
<a href="https://platform.robusta.dev/signup/?utm_source=github&utm_medium=holmesgpt-readme&utm_content=ways_to_use_holmesgpt_section">
<img src="images/integration_logos/robusta_logo.png" alt="Robusta SaaS" width="50"><br>
<strong>Robusta SaaS</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/installation/ui-installation/">
<img src="images/integration_logos/k9s_logo.png" alt="K9s Plugin" width="50"><br>
<strong>K9s Plugin</strong>
</a>
</td>
</tr>
</table>
</td>
<td width="30%">
<h3>API</h3>
<table>
<tr>
<td align="center" width="120">
<a href="helm">
<img src="images/integration_logos/helm_logo.png" alt="Helm Chart" width="50"><br>
<strong>Helm Chart</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/installation/python-installation/">
<img src="images/integration_logos/python_logo.png" alt="Python Package" width="50"><br>
<strong>Python API</strong>
</a>
</td>
</tr>
</table>
</td>
</tr>
</table>
## Supported LLM Providers
Select your LLM provider to see how to set up your API Key.
<table>
<tr>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/ai-providers/openai/">
<img src="images/integration_logos/openai_logo.png" alt="OpenAI" width="50"><br>
<strong>OpenAI</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/ai-providers/anthropic/">
<img src="images/integration_logos/anthropic_logo.png" alt="Anthropic" width="50"><br>
<strong>Anthropic</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/ai-providers/aws-bedrock/">
<img src="images/integration_logos/aws_bedrock_logo.png" alt="AWS Bedrock" width="50"><br>
<strong>AWS Bedrock</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/ai-providers/azure-openai/">
<img src="images/integration_logos/azure-openai.png" alt="Azure OpenAI" width="50"><br>
<strong>Azure OpenAI</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/ai-providers/google-vertex-ai/">
<img src="images/integration_logos/google_vertexai_logo.png" alt="Google Vertex AI" width="50"><br>
<strong>Google Vertex AI</strong>
</a>
</td>
</tr>
<tr>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/ai-providers/gemini/">
<img src="images/integration_logos/gemini_logo.png" alt="Gemini" width="50"><br>
<strong>Gemini</strong>
</a>
</td>
<td align="center" width="120">
<a href="https://robusta-dev.github.io/holmesgpt/ai-providers/ollama/">
<img src="images/integration_logos/ollama_logo.png" alt="Ollama" width="50"><br>
<strong>Ollama</strong>
</a>
</td>
</tr>
</table>
You can also use any OpenAI-compatible models, read [here](https://robusta-dev.github.io/holmesgpt/ai-providers/openai-compatible/) for instructions.
### Using HolmesGPT
- In the Robusta SaaS: Go to [platform.robusta.dev](https://platform.robusta.dev/signup/?utm_source=github&utm_medium=holmesgpt-readme&utm_content=ways_to_use_holmesgpt_section) and use Holmes from your browser
- With HolmesGPT CLI: [setup an LLM API key](https://robusta-dev.github.io/holmesgpt/ai-providers/) and ask Holmes a question 👇
```bash
holmes ask "what pods are unhealthy and why?"
```
You can also provide files as context:
```bash
holmes ask "summarize the key points in this document" -f ./mydocument.txt
```
You can also load the prompt from a file using the `--prompt-file` option:
```bash
holmes ask --prompt-file ~/long-prompt.txt
Enter interactive mode to ask follow-up questions:
```bash
holmes ask "what pods are unhealthy and why?" --interactive
# or
holmes ask "what pods are unhealthy and why?" -i
```
Also supported:
<details>
<summary>HolmesGPT CLI: investigate Prometheus alerts</summary>
Pull alerts from AlertManager and investigate them with HolmesGPT:
```bash
holmes investigate alertmanager --alertmanager-url http://localhost:9093
# if on Mac OS and using the Holmes Docker image👇
# holmes investigate alertmanager --alertmanager-url http://docker.for.mac.localhost:9093
```
<b>To investigate alerts in your browser, sign up for a free trial of [Robusta SaaS](https://platform.robusta.dev/signup/?utm_source=github&utm_medium=holmesgpt-readme&utm_content=ways_to_use_holmesgpt_section). </b>
<b>Optional:</b> port-forward to AlertManager before running the command mentioned above (if running Prometheus inside Kubernetes)
```bash
kubectl port-forward alertmanager-robusta-kube-prometheus-st-alertmanager-0 9093:9093 &
```
</details>
<details>
<summary>HolmesGPT CLI: investigate PagerDuty and OpsGenie alerts</summary>
```bash
holmes investigate opsgenie --opsgenie-api-key <OPSGENIE_API_KEY>
holmes investigate pagerduty --pagerduty-api-key <PAGERDUTY_API_KEY>
# to write the analysis back to the incident as a comment
holmes investigate pagerduty --pagerduty-api-key <PAGERDUTY_API_KEY> --update
```
For more details, run `holmes investigate <source> --help`
</details>
## Customizing HolmesGPT
HolmesGPT can investigate many issues out of the box, with no customization or training. Optionally, you can extend Holmes to improve results:
**Custom Data Sources**: Add data sources (toolsets) to improve investigations
- If using Robusta SaaS: See [Robusta's docs](https://docs.robusta.dev/master/configuration/holmesgpt/custom_toolsets.html)
- If using the CLI: Use `-t` flag with [custom toolset files](./examples/custom_toolset.yaml) or add to `~/.holmes/config.yaml`
**Custom Runbooks**: Give HolmesGPT instructions for known alerts:
- If using Robusta SaaS: Use the Robusta UI to add runbooks
- If using the CLI: Use `-r` flag with [custom runbook files](./examples/custom_runbooks.yaml) or add to `~/.holmes/config.yaml`
You can save common settings and API Keys in a config file to avoid passing them from the CLI each time:
<details>
<summary>Reading settings from a config file</summary>
You can save common settings and API keys in config file for re-use. Place the config file in <code>~/.holmes/config.yaml`</code> or pass it using the <code> --config</code>
You can view an example config file with all available settings [here](config.example.yaml).
</details>
## Evals
Because HolmesGPT relies on LLMs, it relies on [a suite of pytest based evaluations](https://robusta-dev.github.io/holmesgpt/development/evals/) to ensure the prompt and HolmesGPT's default set of tools work as expected with LLMs.
- [Introduction to HolmesGPT's evals](https://robusta-dev.github.io/holmesgpt/development/evals/).
- [Write your own evals](https://robusta-dev.github.io/holmesgpt/development/evals/writing/).
- [Use Braintrust to view analyze results (optional)](https://robusta-dev.github.io/holmesgpt/development/evals/reporting/).
## License
Distributed under the MIT License. See [LICENSE.txt](https://github.com/robusta-dev/holmesgpt/blob/master/LICENSE.txt) for more information.
<!-- Change License -->
## Support
If you have any questions, feel free to message us on [robustacommunity.slack.com](https://bit.ly/robusta-slack)
## How to Contribute
Please read our [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines and instructions.
For help, contact us on [Slack](https://bit.ly/robusta-slack) or ask [DeepWiki AI](https://deepwiki.com/robusta-dev/holmesgpt) your questions.
[](https://deepwiki.com/robusta-dev/holmesgpt)
Raw data
{
"_id": null,
"home_page": null,
"name": "holmesgpt",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Natan Yellin",
"author_email": "natan@robusta.dev",
"download_url": "https://files.pythonhosted.org/packages/6d/27/081260807811a8f171ce115c63dc32ceb3c997088f324b9373f67b81e1d8/holmesgpt-0.12.3.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <h1 align=\"center\">Solve alerts faster with an AI Agent</h1>\n <p align=\"center\">\n <a href=\"#how-it-works\"><strong>How it Works</strong></a> |\n <a href=\"#installation\"><strong>Installation</strong></a> |\n <a href=\"#supported-llm-providers\"><strong>LLM Providers</strong></a> |\n <a href=\"https://www.youtube.com/watch?v=TfQfx65LsDQ\"><strong>YouTube Demo</strong></a> |\n <a href=\"https://deepwiki.com/robusta-dev/holmesgpt\"><img src=\"https://deepwiki.com/badge.svg\" alt=\"Ask DeepWiki\"></a>\n </p>\n</div>\n\nRespond to alerts faster, using AI to automatically:\n\n- Fetch logs, traces, and metrics\n- Determine if issues are application or infrastructure related\n- Find upstream root-causes\n\nUsing HolmesGPT, you can transform your existing alerts from this \ud83d\udc47\n\n\n\nTo this \ud83d\udc47\n\n<img width=\"600\" alt=\"example-holmesgpt-analysis\" src=\"https://github.com/user-attachments/assets/d03df693-9eff-4d61-8947-2b101f648c3e\" />\n\n### How it Works\n\nHolmesGPT connects AI models with live observability data and organizational knowledge. It uses an **agentic loop** to analyze data from multiple sources and identify possible root causes.\n\n<img width=\"3114\" alt=\"holmesgpt-architecture-diagram\" src=\"https://github.com/user-attachments/assets/f659707e-1958-4add-9238-8565a5e3713a\" />\n\n### \ud83d\udd17 Data Sources\n\nHolmesGPT integrates with popular observability and cloud platforms. The following data sources (\"toolsets\") are built-in. [Add your own](#customizing-holmesgpt).\n\n| Data Source | Status | Notes |\n|-------------|--------|-------|\n| [<img src=\"images/integration_logos/argocd-icon.png\" alt=\"ArgoCD\" width=\"20\" style=\"vertical-align: middle;\"> **ArgoCD**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/argocd.html) | \u2705 | Get status, history and manifests and more of apps, projects and clusters |\n| [<img src=\"images/integration_logos/aws_rds_logo.png\" alt=\"AWS RDS\" width=\"20\" style=\"vertical-align: middle;\"> **AWS RDS**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/aws.html) | \u2705 | Fetch events, instances, slow query logs and more |\n| [<img src=\"images/integration_logos/confluence_logo.png\" alt=\"Confluence\" width=\"20\" style=\"vertical-align: middle;\"> **Confluence**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/confluence.html) | \u2705 | Private runbooks and documentation |\n| [<img src=\"images/integration_logos/coralogix-icon.png\" alt=\"Coralogix Logs\" width=\"20\" style=\"vertical-align: middle;\"> **Coralogix Logs**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/coralogix_logs.html) | \u2705 | Retrieve logs for any resource |\n| [<img src=\"images/integration_logos/date_time_icon.png\" alt=\"Datetime\" width=\"20\" style=\"vertical-align: middle;\"> **Datetime**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/datetime.html) | \u2705 | Date and time-related operations |\n| [<img src=\"images/integration_logos/docker_logo.png\" alt=\"Docker\" width=\"20\" style=\"vertical-align: middle;\"> **Docker**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/docker.html) | \u2705 | Get images, logs, events, history and more |\n| <img src=\"images/integration_logos/github_logo.png\" alt=\"GitHub\" width=\"20\" style=\"vertical-align: middle;\"> **GitHub** | \ud83d\udfe1 Beta | Remediate alerts by opening pull requests with fixes |\n| <img src=\"images/integration_logos/datadog_logo.png\" alt=\"DataDog\" width=\"20\" style=\"vertical-align: middle;\"> **DataDog** | \ud83d\udfe1 Beta | Fetches log data from datadog |\n| [<img src=\"images/integration_logos/grafana_loki-icon.png\" alt=\"Loki\" width=\"20\" style=\"vertical-align: middle;\"> **Grafana Loki**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/grafanaloki.html) | \u2705 | Query logs for Kubernetes resources or any query |\n| [<img src=\"images/integration_logos/tempo_logo.png\" alt=\"Tempo\" width=\"20\" style=\"vertical-align: middle;\"> **Grafana Tempo**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/grafanatempo.html) | \u2705 | Fetch trace info, debug issues like high latency in application. |\n| [<img src=\"images/integration_logos/helm_logo.png\" alt=\"Helm\" width=\"20\" style=\"vertical-align: middle;\"> **Helm**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/helm.html) | \u2705 | Release status, chart metadata, and values |\n| [<img src=\"images/integration_logos/http-icon.png\" alt=\"Internet\" width=\"20\" style=\"vertical-align: middle;\"> **Internet**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/internet.html) | \u2705 | Public runbooks, community docs etc |\n| [<img src=\"images/integration_logos/kafka_logo.png\" alt=\"Kafka\" width=\"20\" style=\"vertical-align: middle;\"> **Kafka**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/kafka.html) | \u2705 | Fetch metadata, list consumers and topics or find lagging consumer groups |\n| [<img src=\"images/integration_logos/kubernetes-icon.png\" alt=\"Kubernetes\" width=\"20\" style=\"vertical-align: middle;\"> **Kubernetes**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/kubernetes.html) | \u2705 | Pod logs, K8s events, and resource status (kubectl describe) |\n| <img src=\"images/integration_logos/newrelic_logo.png\" alt=\"NewRelic\" width=\"20\" style=\"vertical-align: middle;\"> **NewRelic** | \ud83d\udfe1 Beta | Investigate alerts, query tracing data |\n| [<img src=\"images/integration_logos/opensearchserverless-icon.png\" alt=\"OpenSearch\" width=\"20\" style=\"vertical-align: middle;\"> **OpenSearch**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/opensearch.html) | \u2705 | Query health, shard, and settings related info of one or more clusters|\n| [<img src=\"images/integration_logos/prometheus-icon.png\" alt=\"Prometheus\" width=\"20\" style=\"vertical-align: middle;\"> **Prometheus**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/prometheus.html) | \u2705 | Investigate alerts, query metrics and generate PromQL queries |\n| [<img src=\"images/integration_logos/rabbit_mq_logo.png\" alt=\"RabbitMQ\" width=\"20\" style=\"vertical-align: middle;\"> **RabbitMQ**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/rabbitmq.html) | \u2705 | Info about partitions, memory/disk alerts to troubleshoot split-brain scenarios and more |\n| [<img src=\"images/integration_logos/robusta_logo.png\" alt=\"Robusta\" width=\"20\" style=\"vertical-align: middle;\"> **Robusta**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/robusta.html) | \u2705 | Multi-cluster monitoring, historical change data, user-configured runbooks, PromQL graphs and more |\n| [<img src=\"images/integration_logos/slab_logo.png\" alt=\"Slab\" width=\"20\" style=\"vertical-align: middle;\"> **Slab**](https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/slab.html) | \u2705 | Team knowledge base and runbooks on demand |\n\n### \ud83d\udd10 Data Privacy\n\nBy design, HolmesGPT has **read-only access** and respects RBAC permissions. It is safe to run in production environments.\n\nWe do **not** train HolmesGPT on your data. Data sent to Robusta SaaS is private to your account.\n\nFor extra privacy, [bring an API key](https://robusta-dev.github.io/holmesgpt/ai-providers/) for your own AI model.\n\n### \ud83d\ude80 Bi-Directional Integrations With Your Tools\n\nRobusta can investigate alerts - or just answer questions - from the following sources:\n\n| Integration | Status | Notes |\n|-------------------------|-----------|-------|\n| Slack | \ud83d\udfe1 Beta | [Demo.](https://www.loom.com/share/afcd81444b1a4adfaa0bbe01c37a4847) Tag HolmesGPT bot in any Slack message |\n| Prometheus/AlertManager | \u2705 | Robusta SaaS or HolmesGPT CLI |\n| PagerDuty | \u2705 | HolmesGPT CLI only |\n| OpsGenie | \u2705 | HolmesGPT CLI only |\n| Jira | \u2705 | HolmesGPT CLI only |\n\n### See it in Action\n\n<a href=\"https://www.loom.com/share/388d98aad1a04823b9ed50d0161a4819?sid=a2a669b4-f092-4067-adcb-c8527fbcaa90\" target=\"_blank\">\n<img style=\"max-width:300px;\" src=\"https://cdn.loom.com/sessions/thumbnails/388d98aad1a04823b9ed50d0161a4819-0ced91a0e8f80dcb-full-play.gif\">\n</a>\n\n\n## Installation\n\nYou can install HolmesGPT in one of the follow three methods:\n\n1. [Standalone](https://robusta-dev.github.io/holmesgpt/installation/cli-installation/): Run HolmesGPT from your terminal as a CLI tool. Typically installed with **Homebrew** or **Pip/Pipx**. Ideal for local use, **embedding into shell scripts, or CI/CD pipelines.** (E.g. to analyze why a pipeline deploying to Kubernetes failed.)\n2. **Web UIs and TUIs**: HolmesGPT is embedded in several third-party tools, like [Robusta SaaS](https://platform.robusta.dev/signup/?utm_source=github&utm_medium=holmesgpt-readme&utm_content=ways_to_use_holmesgpt_section) and [K9s](https://robusta-dev.github.io/holmesgpt/installation/ui-installation/) (as a plugin).\n3. **API**: Embed HolmesGPT in your own app to quickly add **root-cause-analysis functionality and data correlations across multiple sources like logs, metrics, and events**. HolmesGPT exposes an HTTP API and [Python SDK](https://robusta-dev.github.io/holmesgpt/installation/python-installation/), as well as [Helm chart](./helm/) to deploy the HTTP server on Kubernetes.\n\n<table width=\"100%\">\n <tr valign=\"top\">\n <td colspan=\"2\">\n <h3>Standalone</h3>\n <table width=\"100%\">\n <tr>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/installation/cli-installation/\">\n <img src=\"images/integration_logos/brew_logo.png\" alt=\"Brew\" width=\"50\"><br>\n <strong>Brew</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/installation/cli-installation/\">\n <img src=\"images/integration_logos/pipx_logo.png\" alt=\"pipx\" width=\"50\"><br>\n <strong>Pipx</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/installation/cli-installation/\">\n <img src=\"images/integration_logos/docker_logo.png\" alt=\"Docker\" width=\"50\"><br>\n <strong>Docker</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/installation/cli-installation/\">\n <img src=\"images/integration_logos/docker_logo.png\" alt=\"Docker Build\" width=\"50\"><br>\n <strong>Docker Build</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/installation/cli-installation/\">\n <img src=\"images/integration_logos/python_poetry_logo.png\" alt=\"Python Poetry\" width=\"50\"><br>\n <strong>Poetry</strong>\n </a>\n </td>\n </tr>\n </table>\n </td>\n </tr>\n <tr valign=\"top\">\n <td width=\"30%\">\n <h3>Web UIs and TUIs</h3>\n <table>\n <tr>\n <td align=\"center\" width=\"120\">\n <a href=\"https://platform.robusta.dev/signup/?utm_source=github&utm_medium=holmesgpt-readme&utm_content=ways_to_use_holmesgpt_section\">\n <img src=\"images/integration_logos/robusta_logo.png\" alt=\"Robusta SaaS\" width=\"50\"><br>\n <strong>Robusta SaaS</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/installation/ui-installation/\">\n <img src=\"images/integration_logos/k9s_logo.png\" alt=\"K9s Plugin\" width=\"50\"><br>\n <strong>K9s Plugin</strong>\n </a>\n </td>\n </tr>\n </table>\n </td>\n <td width=\"30%\">\n <h3>API</h3>\n <table>\n <tr>\n <td align=\"center\" width=\"120\">\n <a href=\"helm\">\n <img src=\"images/integration_logos/helm_logo.png\" alt=\"Helm Chart\" width=\"50\"><br>\n <strong>Helm Chart</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/installation/python-installation/\">\n <img src=\"images/integration_logos/python_logo.png\" alt=\"Python Package\" width=\"50\"><br>\n <strong>Python API</strong>\n </a>\n </td>\n </tr>\n </table>\n </td>\n\n </tr>\n</table>\n\n\n## Supported LLM Providers\n\nSelect your LLM provider to see how to set up your API Key.\n\n<table>\n <tr>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/ai-providers/openai/\">\n <img src=\"images/integration_logos/openai_logo.png\" alt=\"OpenAI\" width=\"50\"><br>\n <strong>OpenAI</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/ai-providers/anthropic/\">\n <img src=\"images/integration_logos/anthropic_logo.png\" alt=\"Anthropic\" width=\"50\"><br>\n <strong>Anthropic</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/ai-providers/aws-bedrock/\">\n <img src=\"images/integration_logos/aws_bedrock_logo.png\" alt=\"AWS Bedrock\" width=\"50\"><br>\n <strong>AWS Bedrock</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/ai-providers/azure-openai/\">\n <img src=\"images/integration_logos/azure-openai.png\" alt=\"Azure OpenAI\" width=\"50\"><br>\n <strong>Azure OpenAI</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/ai-providers/google-vertex-ai/\">\n <img src=\"images/integration_logos/google_vertexai_logo.png\" alt=\"Google Vertex AI\" width=\"50\"><br>\n <strong>Google Vertex AI</strong>\n </a>\n </td>\n </tr>\n <tr>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/ai-providers/gemini/\">\n <img src=\"images/integration_logos/gemini_logo.png\" alt=\"Gemini\" width=\"50\"><br>\n <strong>Gemini</strong>\n </a>\n </td>\n <td align=\"center\" width=\"120\">\n <a href=\"https://robusta-dev.github.io/holmesgpt/ai-providers/ollama/\">\n <img src=\"images/integration_logos/ollama_logo.png\" alt=\"Ollama\" width=\"50\"><br>\n <strong>Ollama</strong>\n </a>\n </td>\n </tr>\n</table>\n\nYou can also use any OpenAI-compatible models, read [here](https://robusta-dev.github.io/holmesgpt/ai-providers/openai-compatible/) for instructions.\n\n### Using HolmesGPT\n\n- In the Robusta SaaS: Go to [platform.robusta.dev](https://platform.robusta.dev/signup/?utm_source=github&utm_medium=holmesgpt-readme&utm_content=ways_to_use_holmesgpt_section) and use Holmes from your browser\n- With HolmesGPT CLI: [setup an LLM API key](https://robusta-dev.github.io/holmesgpt/ai-providers/) and ask Holmes a question \ud83d\udc47\n\n```bash\nholmes ask \"what pods are unhealthy and why?\"\n```\n\nYou can also provide files as context:\n```bash\nholmes ask \"summarize the key points in this document\" -f ./mydocument.txt\n```\n\nYou can also load the prompt from a file using the `--prompt-file` option:\n```bash\nholmes ask --prompt-file ~/long-prompt.txt\n\nEnter interactive mode to ask follow-up questions:\n```bash\nholmes ask \"what pods are unhealthy and why?\" --interactive\n# or\nholmes ask \"what pods are unhealthy and why?\" -i\n```\n\nAlso supported:\n\n<details>\n<summary>HolmesGPT CLI: investigate Prometheus alerts</summary>\n\nPull alerts from AlertManager and investigate them with HolmesGPT:\n\n```bash\nholmes investigate alertmanager --alertmanager-url http://localhost:9093\n# if on Mac OS and using the Holmes Docker image\ud83d\udc47\n# holmes investigate alertmanager --alertmanager-url http://docker.for.mac.localhost:9093\n```\n\n<b>To investigate alerts in your browser, sign up for a free trial of [Robusta SaaS](https://platform.robusta.dev/signup/?utm_source=github&utm_medium=holmesgpt-readme&utm_content=ways_to_use_holmesgpt_section). </b>\n\n\n<b>Optional:</b> port-forward to AlertManager before running the command mentioned above (if running Prometheus inside Kubernetes)\n\n```bash\nkubectl port-forward alertmanager-robusta-kube-prometheus-st-alertmanager-0 9093:9093 &\n```\n</details>\n\n<details>\n<summary>HolmesGPT CLI: investigate PagerDuty and OpsGenie alerts</summary>\n\n```bash\nholmes investigate opsgenie --opsgenie-api-key <OPSGENIE_API_KEY>\nholmes investigate pagerduty --pagerduty-api-key <PAGERDUTY_API_KEY>\n# to write the analysis back to the incident as a comment\nholmes investigate pagerduty --pagerduty-api-key <PAGERDUTY_API_KEY> --update\n```\n\nFor more details, run `holmes investigate <source> --help`\n</details>\n\n## Customizing HolmesGPT\n\nHolmesGPT can investigate many issues out of the box, with no customization or training. Optionally, you can extend Holmes to improve results:\n\n**Custom Data Sources**: Add data sources (toolsets) to improve investigations\n - If using Robusta SaaS: See [Robusta's docs](https://docs.robusta.dev/master/configuration/holmesgpt/custom_toolsets.html)\n - If using the CLI: Use `-t` flag with [custom toolset files](./examples/custom_toolset.yaml) or add to `~/.holmes/config.yaml`\n\n**Custom Runbooks**: Give HolmesGPT instructions for known alerts:\n - If using Robusta SaaS: Use the Robusta UI to add runbooks\n - If using the CLI: Use `-r` flag with [custom runbook files](./examples/custom_runbooks.yaml) or add to `~/.holmes/config.yaml`\n\nYou can save common settings and API Keys in a config file to avoid passing them from the CLI each time:\n\n<details>\n<summary>Reading settings from a config file</summary>\n\nYou can save common settings and API keys in config file for re-use. Place the config file in <code>~/.holmes/config.yaml`</code> or pass it using the <code> --config</code>\n\nYou can view an example config file with all available settings [here](config.example.yaml).\n</details>\n\n## Evals\n\nBecause HolmesGPT relies on LLMs, it relies on [a suite of pytest based evaluations](https://robusta-dev.github.io/holmesgpt/development/evals/) to ensure the prompt and HolmesGPT's default set of tools work as expected with LLMs.\n\n- [Introduction to HolmesGPT's evals](https://robusta-dev.github.io/holmesgpt/development/evals/).\n- [Write your own evals](https://robusta-dev.github.io/holmesgpt/development/evals/writing/).\n- [Use Braintrust to view analyze results (optional)](https://robusta-dev.github.io/holmesgpt/development/evals/reporting/).\n\n\n## License\nDistributed under the MIT License. See [LICENSE.txt](https://github.com/robusta-dev/holmesgpt/blob/master/LICENSE.txt) for more information.\n<!-- Change License -->\n\n## Support\n\nIf you have any questions, feel free to message us on [robustacommunity.slack.com](https://bit.ly/robusta-slack)\n\n## How to Contribute\n\nPlease read our [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines and instructions.\n\nFor help, contact us on [Slack](https://bit.ly/robusta-slack) or ask [DeepWiki AI](https://deepwiki.com/robusta-dev/holmesgpt) your questions.\n\n[](https://deepwiki.com/robusta-dev/holmesgpt)\n",
"bugtrack_url": null,
"license": null,
"summary": null,
"version": "0.12.3",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "61502bc7f4b647fe2ddf73490a6d910fdeb958f654646fcab7c8e9b9d21de506",
"md5": "08f2ce27d6564b500d95d0e4eb14f707",
"sha256": "5abd78d1274e95f7fc0b686f83a2286ef2f834c92c965458afa9dd8ef1d8a699"
},
"downloads": -1,
"filename": "holmesgpt-0.12.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "08f2ce27d6564b500d95d0e4eb14f707",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 315929,
"upload_time": "2025-07-24T19:29:42",
"upload_time_iso_8601": "2025-07-24T19:29:42.321641Z",
"url": "https://files.pythonhosted.org/packages/61/50/2bc7f4b647fe2ddf73490a6d910fdeb958f654646fcab7c8e9b9d21de506/holmesgpt-0.12.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "6d27081260807811a8f171ce115c63dc32ceb3c997088f324b9373f67b81e1d8",
"md5": "b8bb1df3b67748ff98659b3d4e3b16d8",
"sha256": "97a1cd0d1fa8760bc54e082e6d637ce248cd6328fcaa56972bb079614326de7d"
},
"downloads": -1,
"filename": "holmesgpt-0.12.3.tar.gz",
"has_sig": false,
"md5_digest": "b8bb1df3b67748ff98659b3d4e3b16d8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 228971,
"upload_time": "2025-07-24T19:29:43",
"upload_time_iso_8601": "2025-07-24T19:29:43.676784Z",
"url": "https://files.pythonhosted.org/packages/6d/27/081260807811a8f171ce115c63dc32ceb3c997088f324b9373f67b81e1d8/holmesgpt-0.12.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-24 19:29:43",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "holmesgpt"
}
