AI AGENTS
SWE-agent
by SWE-agent
Overview
Open-source coding agent that takes GitHub issues and attempts to automatically fix them using a chosen language model.
Details
SWE-agent is an open-source coding agent for automated software engineering. Its public site and documentation describe it as a tool that takes GitHub issues and attempts to automatically fix them using a chosen language model. The project’s arXiv paper describes SWE-agent as a system that helps language-model agents autonomously use computers to solve software engineering tasks through a custom agent-computer interface. Official setup documentation covers installing locally from source and running in a browser-based VS Code environment.
When to Use
Use SWE-agent to experiment with language-model agents that attempt to resolve GitHub issues automatically. Use it when evaluating open-source software-engineering agents agent-computer interfaces or coding-agent workflows tied to repositories. Use it for research or trials around autonomous software engineering tasks before considering production reliance.
Getting Started
- Read the SWE-agent website for the project overview and intended GitHub-issue workflow.
- Follow the official installation documentation
- which describes local source installation and a browser-based VS Code option.
- Review the GitHub repository for the source code and project assets.
- Consult the SWE-agent paper for background on its agent-computer interface approach.
Key Features
- •Takes GitHub issues as input and attempts to automatically fix them.
- •Supports use with a chosen language model.
- •Open-source project with an official GitHub repository.
- •Designed around a custom agent-computer interface for automated software engineering tasks.
- •Official documentation includes setup paths for local source installation and browser-based VS Code use.
Capabilities
- •coding-agent
- •github-issue-resolution
- •automated-software-engineering
- •agent-computer-interface
Last updated Jun 25, 2026