Awesome
<p align="center"> <a href="https://www.swe-agent.com/"> <img src="assets/swe-agent-banner.png" alt="swe-agent.com" /> </a> </p> <p align="center"> <a href="https://swe-agent.com"><strong>Website & Demo</strong></a> | <a href="https://princeton-nlp.github.io/SWE-agent/"><strong>Documentation</strong></a> | <a href="https://discord.gg/AVEFbBn2rH"><strong>Discord</strong></a> | <a href="https://arxiv.org/abs/2405.15793"><strong>Preprint</strong></a> </p>SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can resolve issues in real GitHub repositories.
On SWE-bench, SWE-agent resolves 12.47% 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.
You can use SWE-agent either through a web interface (shown above) or through the command line.
🚀 Get started!
👉 Try SWE-agent in your browser: (more information)
Read our documentation to learn more:
- Installation
- Command line usage
- Using the web UI
- Benchmarking on SWE-bench
- Frequently Asked Questions
Our most recent lecture touches on the project's motivation, showcases our research findings and provides a hands-on tutorial on how to install, use, and configure SWE-agent:
<div align="center"> <a href="https://youtu.be/d9gcXpiiDao"><img src="assets/wb_stream_youtube.png" style="width: 600px"/></a> </div>💫 Contributions <a name="contributions"></a>
- If you'd like to ask questions, learn about upcoming features, and participate in future development, join our Discord community!
- If you'd like to contribute to the codebase, we welcome issues and pull requests!
Contact person: John Yang and Carlos E. Jimenez (Email: johnby@stanford.edu, carlosej@princeton.edu).
📝 Citation <a name="citation"></a>
If you found this work helpful, please consider citing it using the following:
@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},
eprint={2405.15793},
archivePrefix={arXiv},
primaryClass={cs.SE}
}
🪪 License <a name="license"></a>
MIT. Check LICENSE
.