SWE-agent

Research agent from Princeton and Stanford that lets a language model fix GitHub issues and other tasks by using tools on its own

Agent by Princeton & Stanford

IndexedMIT★ 20,630

Write a review

Get started

Setup steps are in the repository. Website · Docs · Repository

About

SWE-agent lets a language model of your choice use tools autonomously to fix issues in real GitHub repositories, find cybersecurity vulnerabilities or do custom tasks. It is configured through a single yaml file and is designed for research. The maintainers say development has moved to mini-swe-agent, which has superseded SWE-agent and matches its performance with a simpler design.

Use cases: coding, security, debugging, security-scanning

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: coding, securityREADME
Autonomy: Autonomous: runs tasks end to end and reports backREADME
Where you use it: TerminalREADME
Hosting: You run itREADME
Models: openai, anthropicswe-agent.com
Open source: YesREADME

Facts extracted by Claude Sonnet 5.5 from the linked sources on Oct 24, 2026; reviewed Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 20,630
Forks: 2,263
Open issues: 58
Last commit: Jul 16, 2026 (3 months ago)
Last release: May 22, 2025 (1 year ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/SWE-agent/SWE-agent
Website: swe-agent.com
Docs: swe-agent.com/latest/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README Website Docs github-graphql