SWE-Agent and mini-SWE-agent harnesses for training and eval

An open source agentic framework and lightweight harness designed to run, train, and evaluate language models on real-world software engineering tasks.

SWE-agent turns language models into autonomous coding agents capable of resolving GitHub issues within secure, sandboxed environments. While the original system uses an Agent-Computer Interface (ACI) to let models browse files and execute tests, the newer mini-swe-agent streamlines this architecture into a radically simple 100-line Python implementation. Together, these harnesses serve as the standard infrastructure for running evaluations on SWE-bench and generating high-quality trajectory datasets for supervised fine-tuning (SFT) and reinforcement learning.

https://github.com/princeton-nlp/SWE-agent