Getting Started

SWE-agent enables your language model of choice (e.g. GPT-4o or Claude Sonnet 3.7) 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.

• Installation

  ---

  Installing SWE-agent.

  Get started

• Hello world

  ---

  Solve a GitHub issue with SWE-agent.

  Hello world

• User guides

  ---

  Dive deeper into SWE-agent's features and goals.

  User guides

• Background & goals

  ---

  Learn more about the project goals and academic research.

  Learn more

📣 News

• 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

✍️ Doc updates

• Apr 8: Running SWE-agent competitively
• Mar 7: Updated SWE-agent architecture diagram of 1.0

Our projects

SWE-ReX SWE-smith SWE-bench sb-cli