SWE-agent
The facts below are what the maker publishes about SWE-agent, checked and dated. Our editors have not written about it yet.
The facts
Each one read from SWE-agent's own pages, with the date it was checked.
Where it runs
- 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.checked 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.checked 12 Oct 2026
- Platforms
- The FAQ says SWE-agent runs on Windows, macOS, and Linux, with Docker environment availability as a possible limitation.checked 12 Oct 2026
What it does
- Coding agent
- Yeschecked 22 Sep 2026
- Configuration
- The project describes itself as configurable through a YAML file and designed to be simple and hackable for research.checked 12 Oct 2026
- Credentials
- Users supply their own language-model keys and need a GitHub key to access private repositories.checked 12 Oct 2026
- Current recommendation
- The maintainers recommend mini-swe-agent, which they say matches SWE-agent’s performance while being simpler.checked 11 Oct 2026
- Customization
- Users can add custom tools and change the demonstration trajectory supplied to the agent at the start of each run.checked 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.checked 12 Oct 2026
- Image support
- The documentation describes multimodal support for processing images from GitHub issues and says images must be under 10 MB.checked 11 Oct 2026
- Installation
- The preferred setup is installation from source using pip.checked 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.checked 11 Oct 2026
- Models
- The documentation says SWE-agent supports models served through LiteLLM and local models with an OpenAI-compatible API.checked 12 Oct 2026
- Model support
- The documentation says SWE-agent supports models available through LiteLLM and local models served through an OpenAI-compatible API.checked 11 Oct 2026
- Operating systems
- The FAQ says SWE-agent runs on Windows, macOS, and Linux, with Docker container availability possibly limiting environment choices.checked 11 Oct 2026
- Project status
- The documentation says SWE-agent has been superseded by mini-swe-agent and is now in maintenance-only mode.checked 12 Oct 2026
- Purpose
- SWE-agent uses language models to autonomously work on software engineering tasks, including fixing issues in GitHub repositories.checked 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.checked 12 Oct 2026
- Research focus
- The project describes itself as made for research and simple and hackable by design.checked 11 Oct 2026
- Run records
- The FAQ says `.traj` output files contain complete records of SWE-agent's thought process and actions.checked 12 Oct 2026
- Runtime
- Docker is the default backend; the documentation says cloud code evaluation is an option for users who do not want to use Docker.checked 12 Oct 2026
- Status
- SWE-agent has been superseded by mini-swe-agent and is now in maintenance-only mode.checked 11 Oct 2026
- Support
- The FAQ directs users to open GitHub issues for questions, bug reports, and feature requests, and links to Slack discussions.checked 12 Oct 2026
- Terminal access
- Yeschecked 22 Sep 2026
Alternatives to SWE-agent
- 1
OpenCode
Free planOpen sourceiOSWebAPIExtension9.2From $10 a month - 2
GitHub Copilot
Free planAndroidiOSWebExtension9.1From $10 a month - 3
Amazon Q
Free planAndroidiOSWebAPI9.1Free plan - 4
Claude Code
Free planAndroidiOSWebAPI9.0From $17 a month - 5
Kilo Code
Free planAndroidiOSWebAPI8.8From $15 a month - 6
Devin
Free planWebAPILinuxmacOS8.5From $20 a month