patched-codes/patchwork

Agentic AI framework for enterprise workflow automation.

What it solves

Patchwork is a self-hosted CLI agent designed to automate repetitive development tasks (gruntwork) such as PR reviews, bug fixing, security patching, and documentation generation. It reduces the manual effort required for maintenance chores like updating vulnerable dependencies or resolving issues via automated pull requests.

How it works

The tool operates through "Patchflows"—LLM-assisted automations built by combining reusable atomic actions called "Steps" (e.g., committing changes or calling an LLM) and customizable "Prompt Templates". These flows can be run locally via a CLI, integrated into IDEs, or embedded into CI/CD pipelines. It supports a wide range of LLMs, including OpenAI, Google Gemini, and any OpenAI-compatible endpoint (such as Groq, Together AI, or local models via Ollama and vLLM).

Who it’s for

It is intended for developers and DevOps engineers who want to automate their codebase maintenance and security remediation using AI agents.

Highlights

  • Predefined Patchflows: Includes out-of-the-box automations for PR reviews, vulnerability fixing (AutoFix), dependency upgrades, and README generation.
  • Flexible LLM Support: Compatible with managed services and local open-source models.
  • Extensible Architecture: Users can create their own custom steps and prompt templates to build new automations.
  • Integration Ready: Can be deployed as a CLI tool or as part of a CI/CD pipeline.

Related

  • Project
    The-PR-Agent/pr-agent

    An open-source AI code review agent that automates PR descriptions, reviews, and improvements across multiple git platforms.

  • Project
    greptileai/skills

    A collection of agent skills for automating PR review workflows across GitHub, GitLab, and Perforce using Greptile.

  • Project
    github/gh-aw

    GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension that lets you write AI‑powered automation as Markdown files with YAML front‑matter. The tool compiles these *agentic* workflows into standard GitHub Actions workflows, running LLMs (Copilot, Claude, OpenAI, Gemini, Pi) in a sandboxed, read‑only mode. Writes are gated through a separate safe‑outputs job with scoped permissions. It’s designed for tasks like issue triage, PR review, CI failure analysis, docs updates, and repo reporting, integrating securely with existing CI/CD pipelines.

  • Project
    githubnext/agentics

    A collection of reusable agentic workflows for GitHub that automate repository maintenance, code review, fault analysis, and documentation updates.

  • Project
    alibaba/open-code-review

    An AI-powered code review CLI tool that combines deterministic engineering with an agentic workflow to provide high-precision, token-efficient code analysis.