
SWE-agent is an open-source AI agent from Princeton NLP that automatically solves GitHub issues by navigating codebases, editing files, and running tests — designed for software engineering benchmarks and automated program repair.
SWE-agent is an open-source AI system from Princeton NLP that automatically resolves software engineering tasks. You give it a GitHub issue and a repository, and it browses the codebase, edits files, runs tests, and produces a patch — end to end, without human intervention.