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

📣 New: Meet mini, the 100 line AI agent that still gets 65% on SWE-bench verified!


SWE-agent    mini-SWE-agent    SWE-ReX    SWE-Smith    SWE-bench    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 16.9k 1.7k

  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 crazy configs, no giant monorepo—but scores 65% on SWE-bench verified!

    Python 770 71

  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 271 65

Repositories

Showing 7 of 7 repositories
  • mini-swe-agent Public

    The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no crazy configs, no giant monorepo—but scores 65% on SWE-bench verified!

    SWE-agent/mini-swe-agent’s past year of commit activity
    Python 770 MIT 71 12 (1 issue needs help) 3 Updated Aug 2, 2025
  • 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 16,872 MIT 1,743 37 14 Updated Jul 31, 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 271 MIT 65 21 7 Updated Jul 29, 2025
  • swe-agent-media Public

    Hosting ground for readme media/videos

    SWE-agent/swe-agent-media’s past year of commit activity
    1 MIT 0 0 0 Updated Jul 25, 2025
  • .github Public
    SWE-agent/.github’s past year of commit activity
    0 MIT 1 0 1 Updated Jul 24, 2025
  • test-repo Public

    Repo with very simple issues to test swe-agent

    SWE-agent/test-repo’s past year of commit activity
    Python 6 25 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

Top languages

Python

Most used topics

Loading…