SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can resolve issues in real GitHub repositories. On the SWE-bench, the SWE-agent resolves 12.47% of issues, achieving state-of-the-art performance on the full test set. We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, and view, edit, and execute code files. We call this an Agent-Computer Interface (ACI).

Features

  • My Movie 3 You can use SWE-agent either through a web interface
  • SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can resolve issues in real GitHub repositories
  • Documentation available
  • On SWE-bench, SWE-agent resolves 12.47% of issues, achieving the state-of-the-art performance on the full test set
  • SWE-agent is built and maintained by researchers from Princeton University

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow SWE-agent

SWE-agent Web Site

Other Useful Business Software
Demo Series - Small Business Backup By Veeam Icon
Demo Series - Small Business Backup By Veeam

Learn how to protect your Microsoft 365 data, with simple, actionable tips today.

Watch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
Watch Demo Series
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of SWE-agent!

Additional Project Details

Programming Language

Python

Related Categories

Python Intelligent Agents, Python Agentic AI Tool, Python AI Coding Tool, Python AI Agents

Registered

2024-09-02