swe-agent--swe-agent/docs/index.md

title

title
Getting Started

<style> .md-typeset h1, .md-content__button { display: none; } </style>

!!! warning "We recommend mini-swe-agent instead of SWE-agent" Most of our current development effort is on mini-swe-agent, which has superseded SWE-agent. It matches the performance of SWE-agent, while being much simpler. See the FAQ for more details about the differences.

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

download Installation

Installing SWE-agent.

settings Hello world

Solve a GitHub issue with SWE-agent.

lightbulb User guides

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

book Background & goals

Learn more about the project goals and academic research.

## 📣 News

• July 24: Mini-SWE-Agent achieves 65% on SWE-bench verified in 100 lines of python!
• July 9: Multimodal support for SWE-agent - Process images from GitHub issues with vision-capable AI models
• 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

• June 26: Adding custom tools
• Apr 8: Running SWE-agent competitively
• Mar 7: Updated SWE-agent architecture diagram of 1.0