SWE-agent /SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
★ 20,811⑂ 2,270👁 109⑃ 952● 662▤ 10
TA的项目
+7
日增长
+95
周增长
+233
月增长
20,811
stars
2,270
forks
109
watchers
952
prs
662
issues
10
releases
README
[!warning] Most of our current development effort is on mini-swe-agent, which has superseded SWE-agent. It matches the performance performance of SWE-agent, while being much simpler. See the FAQ for more details about the differences. Our general recommendation is to use mini-SWE-agent instead of SWE-agent going forward. SWE-agent enables your language model of choice (e.g. GPT-4o or Claude Sonnet 4) to autonomously use tools to fix issues in real GitHub repositories, find cybersecurity vulnerabilities, or perform any custom task. ✅ State of the art on SWE-bench among open-source projects ✅ Free-flowing & generalizable: Leaves maximal agency to the LM ✅ Configurable & fully documented: Governed by a single yaml file ✅ Made for research: Simple & hackable by design SWE-agent is built and maintained by researchers from Princeton University and Stanford University. 📣 News July 24: Mini-SWE-Agent achieves 65% on SWE-bench verified in 100 lines of python! May 2: SWE-agent-LM-32b achieves open-weights SOTA on SWE-bench Feb 28: SWE-agent 1.0 + Claude 3.7 is SoTA on SWE-Bench full Feb 25: SWE-agent 1.0 + Claude 3.7 is SoTA on SWE-bench verified Feb 13: Releasing SWE-agent 1.0: SoTA on SWE-bench light & tons of new features Dec 7: An interview with the SWE-agent & SWE-bench team 🚀 Get started! 👉 Try SWE-agent in your browser: (more information) Read our [documentation][docs] to learn more: Installation Hello world from the command line Benchmarking on SWE-bench Frequently Asked Questions [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). Please use SWE-agent 0.7 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 In addition, you might be interested in our other projects: -- Contributions If you'd like to contribute to the codebase, we welcome issues and pull requests! For larger code changes, we always encourage discussion in issues first. Citation & contact 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, Carlos E. Jimenez, and Kilian Lieret (Email: [email protected], [email protected], [email protected]). If you found this work helpful, please consider citing it using the following: SWE-agent citation 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 Y
Top issues
#1240Buggy cost control with Gemini 2.5 Pro9 comments · 2025-07-10#702End-of-line-sequences: `\r\n` vs `\n`7 comments · 2024-07-30#1526RFC: deterministic execution boundaries for tool calls (task text is untrusted input)5 comments · 2026-08-30#1170"pip not found" for tools/edit_anthropic when running SweBench MultiModal6 comments · 2025-05-27#1333How to correctly capture DeepSeek reasoning_content in agent trajectory?5 comments · 2026-01-22#1302Local model (Ollama CodeLlama 13B) + `thought_action` keeps emitting multi-line Python; SWE-agent treats it as bash and loops with `BashIncorrectSyntaxError`5 comments · 2025-09-18#1051SWE-agent for coding challenge fails to write patch due to Syntax Error5 comments · 2025-03-23#1481Cache-hit accounting is invisible in SWE-agent's own token stats3 comments · 2026-07-28
Latest release
v1.1.0: 10s of thousands of training trajectories v1.1.0 2025-05-22v1.1.0: 10s of thousands of training trajectories We're very excited to announce our new project SWE-smith, generating 10s of thousands of training trajectories for SWE agents. Using this training data, our LM SWE-agent-LM-32b achieves open-weights SotA on SWE-bench verified with SWE-agent! !image Apart from that, v1.1.0 is mostly a fix release with minor improvements, in particular adding compatibility with SWE-bench multilingual/multimodal, and SWE-smith. However, please pay attention to the breaking changes below. Breaking changes Changes to trajectory data format. The mes