# patched-codes/patchwork

Agentic AI framework for enterprise workflow automation.

Repository: https://github.com/patched-codes/patchwork
Canonical: https://ross.abutalabs.com/products/patched-codes-patchwork
Homepage: https://patched.codes
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: codereview, devops, devtools, llms, workflows, automation, hacktoberfest
Last push: 2026-08-24T07:08:39+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 28, longevity 62
- inputs: {"age_days": 880, "days_push": 9, "days_rel": 504, "gap_med": 1, "n_releases_24m": 64}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1572, forks 105 (observed 2026-08-28T04:05:05.500602+00:00)

## What it is
Patchwork is an open-source agentic AI framework and CLI that automates development chores like PR reviews, bug fixing, security patching, and documentation using your preferred LLMs. It composes reusable steps, prompt templates, and 'patchflows' that can run locally, in an IDE, or in CI/CD pipelines.

## Use cases
- automate pull request reviews with an llm
- auto-fix security vulnerabilities in my codebase
- generate docstrings and readmes automatically
- upgrade dependencies automatically with ai
- resolve github issues using an llm agent
- run ai code fixes in my ci/cd pipeline
- build custom llm workflows for dev tasks

## When to choose
- you want a self-hosted, extensible CLI agent for automating code review and fixes
- you need LLM-assisted workflows that integrate into CI/CD pipelines
- you want to bring your own LLM keys and customize prompts and workflows

## When to avoid
- you need a fully managed SaaS with SLAs rather than a self-hosted tool
- you want a general-purpose agent framework outside software development tasks
- AGPL-3.0 licensing is incompatible with your usage

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, code-review, workflow-automation, cli, security
- domain: developer-tools, security, large-language-models
- platform: cli, python, cross-platform
- tags: llm-agent, patchflows, pr-review, autofix, vulnerability-remediation, self-hosted, agentic-ai, automation, devops

## Member repositories
- patched-codes/patchwork (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.500602+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 2026-08-30T03:58:11.641830+00:00, confidence not recorded.
  - readme: https://github.com/patched-codes/patchwork (fetched 2026-08-28T04:05:05.500602+00:00, sha 9fa4d1ea90b7)
  - homepage: https://patched.codes (fetched 2026-08-29T11:28:20.501174+00:00, sha 1e3ea39bd6ad)
  - site_page: https://patched.codes/changelog (fetched 2026-08-29T11:28:20.510375+00:00, sha 91213fde6a7d)
- Data as of 2026-08-30T08:39:29.467469+00:00.