Getting Started
Welcome to Mirobody
An open-source, self-hosted data engine that bridges your personal data with the latest AI.
What is Mirobody?
Section titled “What is Mirobody?”Mirobody is an open-source, self-hosted health-data + AI engine — a lightweight C++ core that links your personal health data to LLMs and runs anywhere, including fully on-device so your data never has to leave the phone.
For the full architecture, feature list, and tech stack, see the GitHub README — this docs site is where you build, configure, and extend it.
Build the C++ core and run it in minutes
Add a new device or data source in hours
Who is this for?
Section titled “Who is this for?”Anyone who wants a private home for their health data — one an AI can read, without handing the data to a third party
Engineers building personal-data AI products who want a private, embeddable, on-device-capable health engine instead of building the data + FHIR + MCP plumbing themselves
Built into other products
Section titled “Built into other products”Add AI chat over your device data without building the backend
Drop custom tools into res/mcp_tools/ to deploy subject-facing research apps
Use Mirobody as the data + AI backend behind your product
Contact us for custom integrations and enterprise support
We open-sourced the engine so you can run the same private health core yourself — self-hosted for the whole family, on your phone offline, or embedded in your own app via the C API.
Next steps
Section titled “Next steps”Get started
Follow the Quick Start to build the core (./build.sh) and run it.
Configure providers
Set OAuth credentials for the devices you want — see Configuration.
Explore the API
Read the API Reference for the OpenAI-compatible /v1 endpoints.
Add custom providers or tools
Use Provider Integration for new data sources, or add a C++ tool in res/mcp_tools/.
Contributing
Section titled “Contributing”We welcome contributions — new providers, new tools, framework improvements, anything.
Source code, issues, and PRs
How to submit changes
Community & Support
Section titled “Community & Support”Community discussions (coming soon)
Bug reports and feature requests
Direct technical support