Skip to content

Getting Started

SWE-agent banner SWE-agent banner

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

✍️ Doc updates