SWE-agent
Open SourceAbout SWE-agent
SWE-agent enables a language model to autonomously use tools to fix issues in real GitHub repositories, find cybersecurity vulnerabilities, or perform custom tasks. The project is governed by a single yaml file. It is described as made for research, simple and hackable by design. SWE-agent is built and maintained by researchers from Princeton University and Stanford University. SWE-agent is now in maintenance-only mode.
Products
- SWE-agent: Enables a language model to autonomously use tools to fix GitHub issues, find vulnerabilities, or perform custom tasks.
Used for
- Fixing issues in real GitHub repositories
- Finding cybersecurity vulnerabilities
- Performing custom tasks
- Processing images from GitHub issues with vision-capable AI models
- Solving a GitHub issue with SWE-agent
Who it is for
- Built for researchers.
- Built and maintained by researchers from Princeton University and Stanford University.
From SWE-agent's own website, read 2026-10-24. How we build listings.
Other Enterprise AI Applications Vendors
View allCIOPages put this listing together from public sources. It’s information, not an endorsement. How we build listings. Work here? Claim this listing or .
Quick Facts
swe-agent.comWe publish a detail only when we can point at the page it came from. Know when SWE-agent was founded or where it is based? Send it to us, free.