Skip to main content

Open source · Self-hosted · Apache 2.0

Turn scattered health data into answers you can trace.

Bring lab reports, wearable data and genetic files into one standardized record. Run Mirobody with Docker, using a cloud model or models on your own machine.

Start with Docker →GitHub
Asking how cholesterol has changed: the agent finds three files that name the test differently, charts one trend and names the file behind every number

Three reports, three names for the same test. One trend, with the file behind every number.

​
What is Mirobody?

Mirobody is an open-source health-data engine. It brings reports, device data, photos and genetic files into a shared record, standardizes recognized names and units, and lets you ask questions with references to the original sources. Built by Theta Health, it powers the Theta Wellness app and is available under the Apache 2.0 license.
Collect reports, device data and genetics; translate names and units so sources compare; ask across your history and trace each answer to its sourceCollect reports, device data and genetics; translate names and units so sources compare; ask across your history and trace each answer to its source

Collect, translate, and ask: the three stages from a source file to a traceable answer.

​
Getting started

Run it with Docker

Start the web app and demo records with ./deploy.sh, then choose a cloud or local model. Your records stay in your own Postgres database.

Try the walkthrough

Upload, standardize, ask across reports, share with family, write a journal entry.

Keep every model on your machine

Run models locally with llama.cpp. Check hardware requirements and setup instructions for your platform.

Connect your own agent

Query your records from Claude Code, Codex, Cursor or Gemini CLI through MCP.

Resolve names in Python

pip install mirobody: names to LOINC and units to UCUM, offline, with no key.

Deploy on a server

Production settings, secrets, HTTPS, upgrades and backups.

​
Use it without running anything

Use Theta on the web or in its mobile app to manage your own records without deploying Mirobody. You can also try the live demo with synthetic records; no account is required. Find source code, releases and support on GitHub.