Website & Demo |
Documentation |
Discord |
Preprint
**SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can resolve issues in real GitHub repositories.**
On [SWE-bench](https://github.com/princeton-nlp/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](https://arxiv.org/abs/2405.15793)!
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: [](https://codespaces.new/princeton-nlp/SWE-agent) ([more information](https://princeton-nlp.github.io/SWE-agent/installation/codespaces/))
Read our [documentation][docs] to learn more:
* [Installation](https://princeton-nlp.github.io/SWE-agent/installation/)
* [Command line usage](https://princeton-nlp.github.io/SWE-agent/usage/cl_tutorial/)
* [Using the web UI](https://princeton-nlp.github.io/SWE-agent/usage/web_ui/)
* [Benchmarking on SWE-bench](https://princeton-nlp.github.io/SWE-agent/usage/benchmarking/)
* [Frequently Asked Questions](https://princeton-nlp.github.io/SWE-agent/faq/)
[docs]: https://princeton-nlp.github.io/SWE-agent/
## 💫 Contributions
- If you'd like to ask questions, learn about upcoming features, and participate in future development, join our [Discord community](https://discord.gg/AVEFbBn2rH)!
- If you'd like to contribute to the codebase, we welcome [issues](https://github.com/princeton-nlp/SWE-agent/issues) and [pull requests](https://github.com/princeton-nlp/SWE-agent/pulls)!
Contact person: [John Yang](https://john-b-yang.github.io/) and [Carlos E. Jimenez](http://www.carlosejimenez.com/) (Email: {jy1682, carlosej}@princeton.edu).
## 📝 Citation
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
MIT. Check `LICENSE`.
[](https://github.com/princeton-nlp/SWE-agent/actions/workflows/pytest.yaml)
[](https://github.com/princeton-nlp/SWE-agent/actions/workflows/test_build_containers.yaml)
[](https://github.com/princeton-nlp/SWE-agent/actions/workflows/release-dockerhub-nightly.yaml)
[](https://github.com/princeton-nlp/SWE-agent/actions/workflows/release-dockerhub-release.yaml)
[](https://github.com/princeton-nlp/SWE-agent/actions/workflows/build-docs.yaml)
[](https://codecov.io/gh/princeton-nlp/SWE-agent)
[](https://results.pre-commit.ci/latest/github/princeton-nlp/SWE-agent/main)
[](https://github.com/princeton-nlp/SWE-agent/actions/workflows/check-links.yaml)