Skip to content
@SWE-agent

SWE-agent

Use language models to 🐛 fix issues in real GitHub repositories, ⛳️ solve coding challenges, and 🔥 crack offensive cybersecurity challenges
README.md

📣 News: mini, the 100 line AI agent that still gets 65% on SWE-bench verified!
📣 New benchmark: CodeClash (website, github) evaluates SWE agents on goals, not tasks


SWE-agent   mini-SWE-agent   SWE-ReX   SWE-Smith   SWE-bench   codeclash logo   sb-cli

Software engineering agents, benchmarks, and models.
Built and maintained by researchers from Princeton University and Stanford University.

Slack HuggingFace YouTube

More information about the projects

Main projects:

  • SWE-agent, a system that automatically solves GitHub issues using an LM agent.
  • mini-SWE-agent, a 100 line AI agent that still gets 65% on SWE-bench verified!
  • SWE-bench, a benchmark for evaluating AI systems on real world GitHub issues.
  • SWE-smith, a toolkit for generating SWE training data at scale.

Also check out the supporting infrastructure for working with SWE-* projects

  • SWE-ReX, infrastructure supporting sandboxed code execution for AI agents
  • sb-cli, a command line interface for running evaluations on the cloud.

Pinned Loading

  1. SWE-agent SWE-agent Public

    SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

    Python 18k 1.9k

  2. mini-swe-agent mini-swe-agent Public

    The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

    Python 2.2k 271

  3. SWE-ReX SWE-ReX Public

    Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

    Python 386 89

Repositories

Showing 8 of 8 repositories
  • SWE-agent Public

    SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

    SWE-agent/SWE-agent’s past year of commit activity
    Python 17,952 MIT 1,904 52 13 Updated Dec 5, 2025
  • mini-swe-agent Public

    The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

    SWE-agent/mini-swe-agent’s past year of commit activity
    Python 2,232 MIT 271 30 (1 issue needs help) 14 Updated Dec 2, 2025
  • SWE-ReX Public

    Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

    SWE-agent/SWE-ReX’s past year of commit activity
    Python 386 MIT 89 30 12 Updated Dec 1, 2025
  • swe-agent-media Public

    Hosting ground for readme media/videos of all projects

    SWE-agent/swe-agent-media’s past year of commit activity
    1 MIT 0 0 0 Updated Nov 14, 2025
  • .github Public
    SWE-agent/.github’s past year of commit activity
    0 MIT 2 0 3 Updated Nov 14, 2025
  • mini-traj-web-browser Public
    SWE-agent/mini-traj-web-browser’s past year of commit activity
    JavaScript 2 2 0 0 Updated Aug 5, 2025
  • test-repo Public

    Repo with very simple issues to test swe-agent

    SWE-agent/test-repo’s past year of commit activity
    Python 8 29 5 17 Updated Jul 1, 2025
  • empty_repo Public
    SWE-agent/empty_repo’s past year of commit activity
    Python 1 0 0 0 Updated Jul 12, 2024

Most used topics

agent ai