# andrewyng/openworker

Repository: https://github.com/andrewyng/openworker
Canonical: https://ross.abutalabs.com/products/openworker
Homepage: http://openworker.com
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-26T17:29:40+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 3
- inputs: {"age_days": 45, "days_push": 7, "days_rel": 8, "gap_med": 1, "n_releases_24m": 6}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16241, forks 2243 (observed 2026-08-28T04:11:14.832941+00:00)

## What it is
OpenWorker is an open-source desktop AI agent application that completes real work end-to-end — code security reviews with fix branches, cloud posture audits, incident triage, documents, and scheduled automations. It runs locally, supports any model via API keys or Ollama, and governs and logs every agent action with user approval gates.

## Use cases
- scan my codebase and dependencies for vulnerabilities and prepare fixes
- audit my cloud configuration for misconfigurations and draft remediation
- triage a security incident and draft the timeline and report
- prep a customer call from my CRM and inbox
- run a scheduled morning brief or weekly report
- review this repo's supply-chain posture and open a PR with fixes

## When to choose
- you want a governed, local-first AI agent that delivers finished artifacts rather than chat
- you want to use your own model provider or run fully local with Ollama
- you need AI-assisted security review, supply-chain pinning, or incident triage on your desktop

## When to avoid
- you need a headless server-side agent framework or API to embed in your own backend
- you require a fully stable, code-signed release on Windows (signing still in progress)
- you need mobile or Linux support

## Facets
- artifact type: application
- maturity: experimental
- function: agent-framework, security, vulnerability-scanning, llm-inference, workflow-automation, chat-interface
- domain: security, developer-tools, large-language-models
- platform: windows, python
- tags: ai-coworker, desktop-agent, local-first, bring-your-own-model, ollama, governed-agents, security-coworker, open-beta, ai-agents, automation, macos, desktop

## Member repositories
- andrewyng/openworker (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:14.832941+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:10.548085+00:00, confidence not recorded.
  - readme: https://github.com/andrewyng/openworker (fetched 2026-08-28T04:11:14.832941+00:00, sha 4e1c4733470e)
  - homepage: http://openworker.com (fetched 2026-08-29T08:02:41.622358+00:00, sha 341680cbb879)
- Data as of 2026-08-30T08:39:29.467469+00:00.