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.
We sped up SWE-agent by 2x (timed with GPT4o). This is mostly due to faster communication with the running processes inside of the Docker container and other container setup & installation related improvements. Here are a few relevant PRs:
Full Changelog: https://github.com/princeton-nlp/SWE-agent/compare/v0.5.0...v0.6.0
✨ The big news is our brand new documentation ✨
Secondly, @ollmer added a new flag --cache_task_images
that will significantly speed up SWE-agent when running on the same environment/repository multiple times (no more waiting for cloning and installation!)
pre-commit
hook to avoid merge-conflicts because of formatting. See our docs for more information.__init__.py
(you can no longer from sweagent import Agent
by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/436
Full Changelog: https://github.com/princeton-nlp/SWE-agent/compare/v0.4.0...v0.5.0
We’re excited to launch the SWE-agent web UI! Specify a bug, press start and watch SWE-agent do the magic :sparkles:
Full Changelog: https://github.com/princeton-nlp/SWE-agent/compare/v0.3.0...v0.4.0
Full Changelog: https://github.com/princeton-nlp/SWE-agent/compare/v0.2.0...v0.3.0
--repo_path
) by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/193
--environment_setup
) by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/153
keys.cfg
by @bvandorf in https://github.com/princeton-nlp/SWE-agent/pull/118
Full Changelog: https://github.com/princeton-nlp/SWE-agent/compare/v0.1.2...v0.2.0