◐ Shell
clean mode source ↗

SWE-agent

📣 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 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 19.5k 2.1k

  2. 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 5.2k 715

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

    Python 530 110

Repositories

Showing 10 of 10 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

  • 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

  • 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

  • SWE-agent/.github’s past year of commit activity

    0 MIT

    1 0 2

    Updated Apr 6, 2026

  • minimal-agent-tutorial Public

    Tutorial on how to build a minimal software engineering agent that still scores high on SWE-bench verified

    SWE-agent/minimal-agent-tutorial’s past year of commit activity

    10 5 2 1

    Updated Feb 3, 2026

  • SWE-agent/mini-landing-page’s past year of commit activity

    HTML

    2 1 0 0

    Updated Dec 9, 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

    2

    MIT

    1 0 0

    Updated Nov 15, 2025

  • SWE-agent/mini-traj-web-browser’s past year of commit activity

    JavaScript

    3 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 28 5 17

    Updated Jul 1, 2025

  • SWE-agent/empty_repo’s past year of commit activity

    Python

    1

    0

    0 0

    Updated Jul 12, 2024