https://github.com/princeton-nlp/SWE-agent
[NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.
https://github.com/princeton-nlp/SWE-agent
agent agent-based-model ai cybersecurity developer-tools llm lms
Last synced: 14 days ago
JSON representation
[NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.
- Host: GitHub
- URL: https://github.com/princeton-nlp/SWE-agent
- Owner: SWE-agent
- License: mit
- Created: 2024-04-02T04:09:47.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-07T22:18:37.000Z (4 months ago)
- Last Synced: 2024-12-07T22:25:07.991Z (4 months ago)
- Topics: agent, agent-based-model, ai, cybersecurity, developer-tools, llm, lms
- Language: Python
- Homepage: https://swe-agent.com
- Size: 35.5 MB
- Stars: 13,821
- Watchers: 99
- Forks: 1,402
- Open Issues: 21
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
- Security: SECURITY.md
Awesome Lists containing this project
- awesome-ai-agents - SWE-agent - nlp/SWE-agent) | AI agent for software engineering tasks. | (🚀 Specialized Agents / 💻 Coding Agents)
- awesome-devins - GitHub
- awesome_ai_agents - SWE-agent - This open source project introduces SWE-agent, a software engineering agent for LMs like GPT-4, enhancing bug and issue resolution in GitHub repositories with state-of-the-art performance, facilitated by a well-designed Agent-Computer Interface (ACI) and support for OpenAI and Anthropic Claude models [github](https://github.com/princeton-nlp/SWE-agent) | [website](https://swe-agent.com/) (Learning / Repositories)
- awesome-genai - SWE-agent - SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run. [](https://github.com/princeton-nlp/SWE-agent/network/members) [](https://github.com/princeton-nlp/SWE-agent/stargazers) (Tools & Frameworks / Agent)
- awesome-AI-driven-development - SWE-agent - GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. (Uncategorized / Uncategorized)
- AiTreasureBox - princeton-nlp/SWE-agent - 04-07_15307_10](https://img.shields.io/github/stars/princeton-nlp/SWE-agent.svg)|SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models| (Repos)
- ai-game-devtools - SWE-agent
- awesome-ai-api-projects - SWE-agent - commit/princeton-nlp/SWE-agent?label=%20) | (AI Agent / Task)
README
Documentation | Â
Discord | Â
Paper
SWE-agent lets your language model of choice (e.g. GPT-4o or Claude Sonnet 3.7) autonomously use tools to:
* [fix issues in real GitHub repositories](https://swe-agent.com/latest/usage/hello_world),
* perform tasks on the web,
* find cybersecurity vulnerabilities (by solving Capture The Flag challenges), or
* [any custom task](https://swe-agent.com/latest/usage/coding_challenges).
It does so by using configurable [agent-computer interfaces](https://arxiv.org/abs/2405.15793) (ACIs) to interact with isolated computer environments.
SWE-agent is built and maintained by researchers from Princeton University and Stanford University.
## 📣 News
* Feb 28: [SWE-agent 1.0 + Claude 3.7 is SoTA on SWE-Bench full](https://x.com/KLieret/status/1895487966409298067)
* Feb 25: [SWE-agent 1.0 + Claude 3.7 is SoTA on SWE-bench verified](https://x.com/KLieret/status/1894408819670733158)
* Feb 13: [Releasing SWE-agent 1.0: SoTA on SWE-bench light & tons of new features](https://x.com/KLieret/status/1890048205448220849)
* Dec 7: [An interview with the SWE-agent & SWE-bench team](https://www.youtube.com/watch?v=fcr8WzeEXyk)
## 🚀 Get started!
👉 Try SWE-agent in your browser: [](https://codespaces.new/SWE-agent/SWE-agent) ([more information](https://swe-agent.com/latest/installation/codespaces/))
Read our [documentation][docs] to learn more:
* [Installation](https://swe-agent.com/latest/installation/source/)
* [Hello world from the command line](https://swe-agent.com/latest/usage/hello_world/)
* [Benchmarking on SWE-bench](https://swe-agent.com/latest/usage/batch_mode/)
* [Frequently Asked Questions](https://swe-agent.com/latest/faq/)
[docs]: https://swe-agent.com
## SWE-agent for offensive cybersecurity (EnIGMA)
[SWE-agent: EnIGMA][enigma] is a mode for solving offensive cybersecurity (capture the flag) challenges.
EnIGMA achieves state-of-the-art results on multiple cybersecurity benchmarks (see [leaderboard](https://enigma-agent.com/#results)).
The EnIGMA project introduced multiple features that are available in all modes of SWE-agent, such as the [debugger and server connection tools](https://swe-agent.com/0.7/background/iat/) and a [summarizer](https://swe-agent.com/0.7/config/summarizers/) to handle long outputs. Please use [SWE-agent 0.7](https://github.com/SWE-agent/SWE-agent/tree/v0.7) while we update EnIGMA for 1.0.
[enigma]: https://enigma-agent.com
[SWE-bench]: https://github.com/SWE-bench/SWE-bench
[nyu-ctf]: https://arxiv.org/abs/2406.05590
## About
SWE-agent is an academic project started at Princeton University by John Yang*, Carlos E. Jimenez*, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press.
Contact person: [John Yang](https://john-b-yang.github.io/), [Carlos E. Jimenez](http://www.carlosejimenez.com/), and [Kilian Lieret](https://www.lieret.net/) (Email: [email protected], [email protected], [email protected]).
- 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/SWE-agent/SWE-agent/issues) and [pull requests](https://github.com/SWE-agent/SWE-agent/pulls)!
If you found this work helpful, please consider citing it using the following:
```bibtex
@inproceedings{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 R Narasimhan and Ofir Press},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://arxiv.org/abs/2405.15793}
}
```
If you used the summarizer, interactive commands or the offensive cybersecurity capabilities in SWE-agent, please also consider citing:
```bibtex
@misc{abramovich2024enigmaenhancedinteractivegenerative,
title={EnIGMA: Enhanced Interactive Generative Model Agent for CTF Challenges},
author={Talor Abramovich and Meet Udeshi and Minghao Shao and Kilian Lieret and Haoran Xi and Kimberly Milner and Sofija Jancheska and John Yang and Carlos E. Jimenez and Farshad Khorrami and Prashanth Krishnamurthy and Brendan Dolan-Gavitt and Muhammad Shafique and Karthik Narasimhan and Ramesh Karri and Ofir Press},
year={2024},
eprint={2409.16165},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2409.16165},
}
```
## 🪪 License
MIT. Check `LICENSE`.
[](https://github.com/SWE-agent/SWE-agent/actions/workflows/pytest.yaml)
[](https://github.com/SWE-agent/SWE-agent/actions/workflows/build-docs.yaml)
[](https://codecov.io/gh/SWE-agent/SWE-agent)
[](https://results.pre-commit.ci/latest/github/SWE-agent/SWE-agent/main)
[](https://github.com/SWE-agent/SWE-agent/actions/workflows/check-links.yaml)