Website & Demo | Documentation | Discord | Preprint
SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can fix bugs and issues in real GitHub repositories.
On SWE-bench, SWE-agent resolves 12.29% of issues, achieving the state-of-the-art performance on the full test set.
We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, view, edit and execute code files. We call this an 🤖 Agent-Computer Interface (ACI). Read more about it in our paper!
SWE-agent is built and maintained by researchers from Princeton University.
If you found this work helpful, please consider using the following citation:
@misc{yang2024sweagent,
title={SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering},
author={John Yang and Carlos E. Jimenez and Alexander Wettig and Kilian Lieret and Shunyu Yao and Karthik Narasimhan and Ofir Press},
year={2024},
}
I'm a dev who wants to use SWE-agent as a tool | I'm doing research on agents & benchmarks |
---|---|
✅ Easy installation, batteries included | |
✅ Fully documented | |
✅ Behavior can be modified by config files | |
✅ Graphical user interface in the browser | ✅ First-class integration with SWE-bench |
✅ Stable & tested |
All information is provided in our documentation:
and many more topics.
Contact person: John Yang and Carlos E. Jimenez (Email: {jy1682, carlosej}@princeton.edu).
MIT. Check LICENSE
.