Patchwork is an open-source project on GitHub with about 1,579 stars, most recently updated in 2026. Patchwork is an agentic AI framework from Patched that automates development gruntwork such as PR reviews, bug fixing and security patching. It combines reusable steps, customizable prompt templates and ready-made patchflows into LLM-assisted automations that run from a self-hosted CLI, inside your IDE, or as part of CI/CD, using your preferred LLMs.
Published on GitHub under the AGPL-3.0 license, Patchwork has attracted a community of about 1,579 stars, which places it among the more visible open-source AI projects in its niche. Development was still active as of 2026, based on the repository’s latest updates. Because the full source code is public, teams can audit how it works, adapt it to their own stack, and self-host it rather than depending on a closed hosted product.
The repository is tagged with topics including automation, codereview, devops, devtools, hacktoberfest, which gives a quick picture of where it fits in the open-source AI ecosystem. New users can explore the examples and documentation in the repository to understand the main workflows before integrating it into their own projects, and the public issue tracker shows what the maintainers are actively working on and what the community is asking for.
Patchwork is AGPL-3.0 open source and free to self-host, and Patched also offers a hosted version for teams that prefer a managed service, making it freemium overall.
Patchwork is best suited for engineering teams that want AI to clear repetitive review, maintenance and patching work from their backlog. Anyone evaluating it should start with the GitHub repository, where the documentation, examples and issue tracker show exactly what the current version can do.