- Home
- AI Coding Assistants
- SWE-agent
On the recordRead 12 Oct 202624 facts
SWE-agent
On the record
- Coding agent
- Yesgithub.com · read 22 Sep 2026
- Browser setup
- SWE-agent can be run in a browser-based VS Code environment, where users provide language-model API keys in a .env file.swe-agent.com · read 11 Oct 2026
- Browser use
- The setup guide offers a browser-based VS Code environment for a quick first look and lists Node.js as a requirement for the web-based GUI.swe-agent.com · read 12 Oct 2026
- Configuration
- The project describes itself as configurable through a YAML file and designed to be simple and hackable for research.swe-agent.com · read 12 Oct 2026
- Credentials
- Users supply their own language-model keys and need a GitHub key to access private repositories.swe-agent.com · read 12 Oct 2026
- Current recommendation
- The maintainers recommend mini-swe-agent, which they say matches SWE-agent’s performance while being simpler.swe-agent.com · read 11 Oct 2026
- Customization
- Users can add custom tools and change the demonstration trajectory supplied to the agent at the start of each run.swe-agent.com · read 12 Oct 2026
- Images
- SWE-agent supports vision-capable models for processing images from GitHub issues, and the FAQ says images must be under 10 MB.swe-agent.com · read 12 Oct 2026
- Image support
- The documentation describes multimodal support for processing images from GitHub issues and says images must be under 10 MB.swe-agent.com · read 11 Oct 2026
- Installation
- The preferred setup is installation from source using pip.swe-agent.com · read 11 Oct 2026
- Local model limits
- For local models, the documentation says cost tracking cannot be used unless a custom model registry supplies cost information.swe-agent.com · read 11 Oct 2026
- Models
- The documentation says SWE-agent supports models served through LiteLLM and local models with an OpenAI-compatible API.swe-agent.com · read 12 Oct 2026
- Model support
- The documentation says SWE-agent supports models available through LiteLLM and local models served through an OpenAI-compatible API.swe-agent.com · read 11 Oct 2026
- Operating systems
- The FAQ says SWE-agent runs on Windows, macOS, and Linux, with Docker container availability possibly limiting environment choices.swe-agent.com · read 11 Oct 2026
- Project status
- The documentation says SWE-agent has been superseded by mini-swe-agent and is now in maintenance-only mode.swe-agent.com · read 12 Oct 2026
- Purpose
- SWE-agent uses language models to autonomously work on software engineering tasks, including fixing issues in GitHub repositories.swe-agent.com · read 12 Oct 2026
- Research design
- Its Agent-Computer Interface provides commands and feedback for models to browse repositories, view and edit files, and run code.swe-agent.com · read 12 Oct 2026
- Research focus
- The project describes itself as made for research and simple and hackable by design.swe-agent.com · read 11 Oct 2026
