aifix-code implements a failure-driven agentic loop that takes in failing tests (pytest or Maven) and uses LLMs to generate candidate patches. The patches are automatically validated by re-running the tests until a passing solution is found. It is built on LangGraph and is designed for automated code repair in Python and Java projects.
aifix-code is a Coding AI & assistants project. Manually debugging and fixing failing tests in codebases. aifix-code is an open-source project aimed at developers. The project is open source (MIT). It ships for the command line.
It is developed by sumengnan, and it first shipped in 2026. Development happens publicly on GitHub with 274 commits in the last 90 days. Key capabilities include test-driven repair, agentic loop, and automated patching.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match