davia
v0.1.10
Published
Interactive, editable docs designed for coding agents
Downloads
1,792
Readme
What is Davia?
Davia is an open-source tool designed for AI coding agents to generate interactive internal documentation for your codebase. When your AI coding agent uses Davia, it writes documentation files locally with interactive visualizations and editable whiteboards that you can edit in a Notion-like platform or locally in your IDE.
Quick Start
1. Install Davia CLI
npm i -g davia2. Initialize Davia
Initialize Davia with your coding agent:
davia init --agent=[name of your coding agent]Replace [name of your coding agent] with the name of your coding agent (e.g., cursor, github-copilot, windsurf).
3. Generate Documentation
Ask your AI coding agent to write the documentation for your project. Your agent will use Davia's tools to generate interactive documentation with visualizations and editable whiteboards.
4. View Your Documentation
Once your agent has generated the documentation, open the Davia workspace:
davia openIf the page doesn't load immediately, refresh the page in your browser.
5. Collaborate with Your Team
Sync your local documentation to a remote workspace where you can collaborate with your team in real-time:
davia pushThis command will:
- Ask you to log in if you haven't already (opens browser for authentication)
- Create a new workspace for your project
- Upload your documentation to the cloud
- Open your workspace in the browser
📝 Note: Currently, updating a workspace you've already pushed isn't supported yet, but we'll be adding this feature very soon!
This is the view you'll have after sending your docs to the workspace:
Contributing
Contributions are welcome! We'd love your help to make Davia better:
- Report bugs or request features — Open an issue to let us know what's not working or what you'd like to see
- Improve the codebase — Submit pull requests with bug fixes, new features, or optimizations
- Share feedback — Share your feedback on Discord and help shape Davia's future
Example
https://github.com/user-attachments/assets/dc2121c3-811d-47da-8762-0d5afd5c845d
Another example with flows:
https://github.com/user-attachments/assets/6eecb62f-3c13-434a-9aa0-a8dd3840bf49
License
This project is licensed under the MIT License - see the LICENSE file for details.
