SWE-Agent
Autonomous agent by Princeton that resolves real GitHub issues.
About
SWE-agent, from researchers at Princeton and Stanford, turns a language model into an autonomous software engineering agent that resolves real GitHub issues, finds security vulnerabilities, or performs custom tasks. Its agent-computer interface is designed so the model can navigate and edit code efficiently. A separate EnIGMA mode targets offensive cybersecurity capture-the-flag challenges. Released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Code Assistants
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- MIT
- Added
- Apr 3, 2026
Related Tools
Open-source CLI and IDE tool for source-controlled AI code review checks enforceable in CI.
Open-source AI code assistant for VS Code and JetBrains connecting to any LLM.
Open-source version of Bolt.new that builds and runs full-stack web apps in the browser with any LLM.
Anthropic's terminal-based agentic coding tool that edits code, runs tests, and drives git workflows.
OpenAI's open-source Rust coding agent that edits repos and runs code in a sandboxed terminal session.
AI pair programming tool in the terminal that edits code in your local git repo.