OpenDevin: Code Less, Make More

---

Welcome to OpenDevin, a platform for autonomous software engineers, powered by AI and LLMs.

OpenDevin agents collaborate with human developers to write code, fix bugs, and ship features.

⚡ Getting Started

OpenDevin works best with Docker version 26.0.0+ (Docker Desktop 4.31.0+). You must be using Linux, Mac OS, or WSL on Windows.

To start OpenDevin in a docker container, run the following commands in your terminal:

Warning

When you run the following command, files in ./workspace may be modified or deleted.

WORKSPACE_BASE=$(pwd)/workspace
docker run -it \
    --pull=always \
    -e SANDBOX_USER_ID=$(id -u) \
    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
    -v $WORKSPACE_BASE:/opt/workspace_base \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
    ghcr.io/opendevin/opendevin:0.8

Note

By default, this command pulls the latest tag, which represents the most recent release of OpenDevin. You have other options as well:

• For a specific release version, use ghcr.io/opendevin/opendevin:<OpenDevin_version> (replace <OpenDevin_version> with the desired version number).
• For the most up-to-date development version, use ghcr.io/opendevin/opendevin:main. This version may be (unstable!) and is recommended for testing or development purposes only.

Choose the tag that best suits your needs based on stability requirements and desired features.

You'll find OpenDevin running at http://localhost:3000 with access to ./workspace. To have OpenDevin operate on your code, place it in ./workspace. OpenDevin will only have access to this workspace folder. The rest of your system will not be affected as it runs in a secured docker sandbox.

Upon opening OpenDevin, you must select the appropriate Model and enter the API Key within the settings that should pop up automatically. These can be set at any time by selecting the Settings button (gear icon) in the UI. If the required Model does not exist in the list, you can manually enter it in the text box.

For the development workflow, see Development.md.

Are you having trouble? Check out our Troubleshooting Guide.

🚀 Documentation

To learn more about the project, and for tips on using OpenDevin, check out our documentation.

There you'll find resources on how to use different LLM providers (like ollama and Anthropic's Claude), troubleshooting resources, and advanced configuration options.

🤝 How to Contribute

OpenDevin is a community-driven project, and we welcome contributions from everyone. Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of software engineering with AI, there are many ways to get involved:

• Code Contributions: Help us develop new agents, core functionality, the frontend and other interfaces, or sandboxing solutions.
• Research and Evaluation: Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
• Feedback and Testing: Use the OpenDevin toolset, report bugs, suggest features, or provide feedback on usability.

For details, please check CONTRIBUTING.md.

🤖 Join Our Community

Whether you're a developer, a researcher, or simply enthusiastic about OpenDevin, we'd love to have you in our community. Let's make software engineering better together!

• Slack workspace - Here we talk about research, architecture, and future development.
• Discord server - This is a community-run server for general discussion, questions, and feedback.

📈 Progress

📜 License

Distributed under the MIT License. See LICENSE for more information.

📚 Cite

@misc{opendevin,
      title={{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}},
      author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
      year={2024},
      eprint={2407.16741},
      archivePrefix={arXiv},
      primaryClass={cs.SE},
      url={https://arxiv.org/abs/2407.16741},
}