No Description

Xingyao Wang a6ba6c5277 Add SWEBench-docker eval (#2085) 1 year ago
.github 003b599dd0 Issues Category Update: Removed Question Type (#2345) 1 year ago
agenthub 9605106e72 feat: append_file incl. all tests [agentskills] (#2346) 1 year ago
containers e0ad289483 Downgraded Python version to 3.12.3 (#2331) 1 year ago
dev_config b9a5be2569 Add ruff for shared mutable defaults (B) (#1938) 1 year ago
docs f1760f3a67 remove some MonologueAgent mentions (#2364) 1 year ago
evaluation a6ba6c5277 Add SWEBench-docker eval (#2085) 1 year ago
frontend a5f5bc30b4 chore(deps): bump @vitejs/plugin-react from 4.3.0 to 4.3.1 in /frontend (#2371) 1 year ago
opendevin 9605106e72 feat: append_file incl. all tests [agentskills] (#2346) 1 year ago
tests 9605106e72 feat: append_file incl. all tests [agentskills] (#2346) 1 year ago
.dockerignore 516c9bf1e0 Revamp docker build process (#1121) 1 year ago
.gitattributes e32d95cb1a lint: simplify hooks already covered by Ruff (#1204) 1 year ago
.gitignore b431fce938 tests: more Agentskills tests; updated .gitignore (#2307) 1 year ago
CODE_OF_CONDUCT.md 780db1e906 Rename CodeOfConduct.md to CODE_OF_CONDUCT.md (#1665) 1 year ago
CONTRIBUTING.md e7b5ddfe06 Add integration test framework with mock llm (#1301) 1 year ago
Development.md 3b0e1361a4 fix typos (#2267) 1 year ago
LICENSE 39add27f15 Create MIT LICENSE (#8) 1 year ago
Makefile a400e94971 Parameterize Python version (#2348) 1 year ago
README.md 221a4e83f1 doc: Added citation subsection in README (#2339) 1 year ago
poetry.lock a6ba6c5277 Add SWEBench-docker eval (#2085) 1 year ago
pydoc-markdown.yml cd58194d2a docs(docs): start implementing docs website (#1372) 1 year ago
pyproject.toml a6ba6c5277 Add SWEBench-docker eval (#2085) 1 year ago
pytest.ini b6ff201780 Refactor integration test framework and relieve the pain of regeneration (#1818) 1 year ago

README.md

Contributors Forks Stargazers Issues MIT License
Join our Slack community Join our Discord community
SWE-bench CodeCov

Logo

OpenDevin: Code Less, Make More

Check out the documentation

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.

App screenshot

⚡ Getting Started

The easiest way to run OpenDevin is inside a Docker container. It works best with the most recent version of Docker, 26.0.0. 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.

OPENDEVIN_WORKSPACE=$(pwd)/workspace
docker run -it \
    --pull=always \
    -e SANDBOX_USER_ID=$(id -u) \
    -e PERSIST_SANDBOX="true" \
    -e SSH_PASSWORD="make something up here" \
    -e WORKSPACE_MOUNT_PATH=$OPENDEVIN_WORKSPACE \
    -v $OPENDEVIN_WORKSPACE:/opt/workspace_base \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
    ghcr.io/opendevin/opendevin:0.6

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.

🚀 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

SWE-Bench Lite Score

Star History Chart

📜 License

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

📚 Cite

@misc{opendevin2024,
  author       = {{OpenDevin Team}},
  title        = {{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}},
  year         = {2024},
  version      = {v1.0},
  howpublished = {\url{https://github.com/OpenDevin/OpenDevin}},
  note         = {Accessed: ENTER THE DATE YOU ACCESSED THE PROJECT}
}