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]
SWE-agent from Princeton turns an LLM into an autonomous agent that fixes bugs in real GitHub repositories using a purpose-built agent-computer interface.

Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeSWE-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]
SWE-agent has 20.2k stars on GitHub. It has been forked 2.2k times. SWE-agent is written mainly in Python. It has been in active development since 2024. SWE-agent is available under the MIT license. Its main topics are agent, agent-based-model, ai, cybersecurity.
Read the full guideSWE-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]
SWE-agent is an open-source project. It is released under the MIT license.
Yes. SWE-agent is free and open source — you can use, modify and self-host it.
SWE-agent is available under the MIT license.
SWE-agent is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/swe-agent-swe-agent.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.