Mirobody

Turn scattered health data into answers you can trace.

A self-hosted AI health data engine for lab reports, wearables and genetic files.
Start with Docker and one model key, or run every model on your own machine.

English · 中文

▶ Live demo · 🐳 Start with Docker · 📚 Documentation

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

Start with Docker

Docker with Compose is all the stack needs: no Python, Node.js or GPU. On Windows, run these in a WSL 2 terminal.

git clone --depth 1 https://github.com/thetahealth/mirobody.git && cd mirobody
./deploy.sh

Open the setup link the script prints and paste one model key: OpenRouter, OpenAI, Gemini, Anthropic, DeepSeek, DashScope, or any OpenAI-compatible gateway. The key is kept only after one real request through it works. Postgres, the server, the worker and a synthetic demo record start together.

1. Sign in as you@mirobody.ai, code 111111, on the Email code tab. The demo holds 2,019 readings across two records: yours, and mom@mirobody.ai's, which she shares with you view-only.
2. Ask "How has my cholesterol changed?" The answer charts the trend and names the file behind each number.
3. Upload a sample from demo/upload/ on the Data page, or switch to mom's record and ask again.

COMPOSE_PROFILES=local-cpu ./deploy.sh

→ Self-host guide · Walkthrough · Deploy on a server

What you can do

• Compare reports across labs. PDFs, phone photos and spreadsheets, 23 file types in all, land in one history. Every reading links to the page it was read from.
• Bring in everyday data. Import an Apple Health export, or connect Garmin, Oura and Whoop.
• Look after your family. Invite someone who shares their own record, or keep one for a parent who never signs in.
• Write a health journal. headache since last night, BP 150/95, no fever becomes a coded complaint and two coded readings; "no fever" is not logged as a fever.
• Explore genetic data. Upload a 23andMe, AncestryDNA or WeGene export, or a VCF, and ask by rsID, gene or region. Drug questions get CPIC coverage, never a change of medication.
• Use your own agent. Connect Claude Code, Codex or Cursor over MCP, or embed the offline engine in Python.

Collect · Translate · Agent

The model reads documents and reasons; the codes and units come from vocabularies bundled with the package, never from the model. How a reading moves through the pipeline.

Care for your family

Joining a care circle shares nothing by itself. Each member decides whether others may view or edit their own record. A parent who never signs in can be managed by you until they claim the record and choose what you keep. See it in the walkthrough.

What stays on your machine

Your record lives in a Postgres you run, and nothing here reports usage anywhere. What leaves depends on who reads it:

Device vendors see data only after you link one. Before this reaches a network you do not control, read SECURITY.md: it lists every address the server can call.

Build on Mirobody

Over MCP the stack serves seven tools, each scoped to the signed-in person: four read your record (readings, medications, genotypes, pharmacogenomics) and three resolve names and units.

Try the vocabulary with no key, no network and, with uvx, no install:

uvx --python 3.12 mirobody resolve "LDL cholesterol" 血红蛋白 ヘモグロビン 血脂

from mirobody.engine import resolve, resolve_reading

resolve("血红蛋白").loinc                                     # '718-7'   any language, one code
resolve_reading("total cholesterol", "5.0", "mmol/L").loinc  # '14647-2' the unit picks the code...
resolve_reading("total cholesterol", "193", "mg/dL").loinc   # '2093-3'  ...mass, not moles
resolve("中性粒细胞百分比").loinc                               # '26511-6' Neutrophils/Leukocytes
resolve("血脂").resolved                                     # False    a category, not one test

Numbers you can check

Mirobody is the engine under Theta Wellness, a live consumer health app.

Contributing

The most useful contribution is a term the resolver gets wrong. Run mirobody resolve "<term>"; if the answer is wrong or empty, report it or send a fix with a test case. CONTRIBUTING.md has the setup and the checks.

Built on HL7 FHIR, LOINC from the Regenstrief Institute, UCUM, ICPC-3 (WONCA), CPIC, llama.cpp and deepagents, with thanks. Terminology licences: LICENSE-3RD-PARTY.