AI Worker worker.md

holmesgpt

SRE Agent - CNCF Sandbox Project

Agent framework 1,906 stars Python Apache-2.0 Worker-compatible

Source#

Tags#

aiopschatbotchatopsdevopsdevops-toolsincident

Integration notes#

Framework-level abstraction; derive bounded worker contracts from concrete tasks and APIs in docs/examples.

worker.md example#

Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.

---
id: holmesgpt-repo-derived-worker
name: holmesgpt Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/holmesgpt/
source_repository: https://github.com/HolmesGPT/holmesgpt
repository_default_branch: master
repository_language: Python
repository_license: Apache-2.0
repository_updated_at: 2026-03-01
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.9
derived_on: 2026-03-01
tags:
  - aiops
  - chatbot
  - chatops
  - devops
  - devops-tools
  - incident
---

# holmesgpt Repo-Derived Worker

## Repo-derived summary
- Registry summary: SRE Agent - CNCF Sandbox Project
- Repository description: SRE Agent - CNCF Sandbox Project
- Stars (snapshot): 1,906
- Primary language: Python
- Worker mode classification: agent-orchestration-worker

## Extracted from
- https://github.com/HolmesGPT/holmesgpt
- https://github.com/HolmesGPT/holmesgpt/blob/master/README.md
- https://holmesgpt.dev/data-sources/builtin-toolsets/
- https://holmesgpt.dev/data-sources/api-toolsets/
- https://holmesgpt.dev/ai-providers/

## Evidence notes (from repository text)
- README summary paragraph: Open-source AI agent for investigating production incidents and finding root causes. A [CNCF Sandbox project](./ADOPTERS.md) by https://home.robusta.dev/.
- Open-source AI agent for investigating production incidents and finding root causes. A [CNCF Sandbox project](./ADOPTERS.md) by https://home.robusta.dev/.
- - **Petabyte-scale data**: Server-side filtering, JSON tree traversal, and tool output transformers keep large payloads out of context windows
- - **https://holmesgpt.dev/data-sources/builtin-toolsets/**: Prometheus, Grafana, Datadog, Kubernetes, and [many more](#-data-sources)—plus any https://holmesgpt.dev/data-sources/api-toolsets/
- HolmesGPT uses an **agentic loop** to query live observability data from multiple sources and identify root causes.
- HolmesGPT integrates with popular observability and cloud platforms. The following data sources ("toolsets") are built-in. https://holmesgpt.dev/data-sources/custom-toolsets/.

## Installation hints found in README
- No explicit package installation command detected in README text.

## worker.md contract (derived starter)
Purpose: Execute one orchestrated agent task as a bounded worker step.

### Input schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "task",
    "context"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "task": {
      "type": "string"
    },
    "context": {
      "type": "object"
    }
  }
}
```

### Output schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "status",
    "result"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "enum": [
        "ok",
        "retryable_error",
        "invalid_request",
        "invalid_output"
      ]
    },
    "result": {
      "type": "object"
    }
  }
}
```

### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use

## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.

How to use#

  • Save this as a worker spec file (for example: holmesgpt-my-task.worker.md).
  • Replace the input/output schemas and purpose with your real bounded task.
  • Enforce schema validation + timeout + retry policy in your runtime before production use.

Citation#

Reference URL: https://worker.md/registry/holmesgpt/

Source URL: https://github.com/HolmesGPT/holmesgpt