mirobody

View on GitHub

The AI-native health data engine — collect, translate, and reason with AI Agents over labs results, wearables & genomics.

★ 1.3K231 forksPythonApache-2.0thetahealth

Python health data engine that ingests labs, wearables and genomics, maps names and units to LOINC/UCUM offline, and lets AI agents answer trend questions over the coded, self-hosted record. Also exposes every tool over MCP.

Use Cases

Standardize lab report names to LOINC codes across languagesAsk trend questions over a personal health record with source citationsIngest PDFs, photos, CSVs and wearable exports into one coded recordTrack family or care-circle health records with permissioned sharingServe health data tools to Claude Desktop or Cursor over MCPNormalize units to UCUM and compare values across labs and devicesRead medications and genetic variants alongside lab indicators

Built With

Language: Python
Frameworks: MCP · Claude Agent SDK · Postgres · pgvector · Redis · Docker Compose · FastAPI

mirobody

Use Cases

Built With

Tags