Type: url
Original: https://github.com/SWE-agent/SWE-agent
Status: generated
Summary
The GitHub repository for SWE-agent, an MIT-licensed academic project from Princeton University and Stanford University researchers that lets a language model of the user’s choice autonomously use tools to fix issues in real GitHub repositories, find cybersecurity vulnerabilities or perform custom tasks. The README highlights its configurability through a single YAML file and its research orientation, describes the EnIGMA mode for offensive cybersecurity challenges, and warns that development effort has moved to mini-swe-agent, which it says has superseded SWE-agent.