S
SWE-agent
FreeAI Coding3k views
Open source AI agent from Princeton that autonomously fixes bugs in GitHub repositories.
About SWE-agent
SWE-agent is an open source AI software engineering agent developed by researchers at Princeton University. It autonomously resolves GitHub issues by interacting with a codebase through a custom agent-computer interface. SWE-agent achieved state-of-the-art results on the SWE-bench benchmark, demonstrating that LLM-based agents can fix real-world software bugs with high success rates.
Key Features
- Autonomous GitHub issue resolution
- Custom agent-computer interface for code interaction
- State-of-the-art SWE-bench benchmark performance
- Open source and research-ready
- Supports multiple LLM backends
Best For
✓ AI researchers✓ Developers experimenting with agents✓ Open source contributors