Back to directory

Patchwork

A self-hosted CLI agent framework that automates development chores such as PR reviews, bug fixing and security patching by combining reusable steps, prompt templates and an LLM.

Patchwork

Patchwork automates development gruntwork, such as pull-request reviews, bug fixing, security patching, dependency upgrades, documentation and README generation, using a self-hosted CLI agent paired with a user's preferred LLM. It is built from three kinds of pieces: steps, reusable atomic actions such as creating a pull request, committing changes or calling an LLM; prompt templates, customizable prompts tuned for a specific chore; and patchflows, which combine steps and prompts into a complete automation such as an AutoFix or a PR review.

Patchflows can run locally from the CLI or an IDE, or as part of a CI/CD pipeline, and several are available out of the box alongside the ability to create custom ones. It installs from PyPI with optional dependency groups for security-scanning tools such as semgrep and depscan, for a RAG-based issue resolver, and for notification integrations such as Slack. It is written in Python and licensed under AGPL-3.0.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.