Version 1.0 centralizes what your providers gave you — locally, on your machine — and turns it into what to bring up at the next appointment. It is free (GPLv3) and has been tested on synthetic cases and a few real documents, not yet with real patients.
local by default · no cloud storage · no sync · nothing leaves your machine unless you opt in to a cloud model
Conditions with ICD-10 codes, medications, doctors, and appointments, kept in one place.
An agentic loop drafts personalized questions for an upcoming visit, pulling relevant history and calling tools (medication lookup, past-visit lookup) before it finalizes anything. Runs fully local via Ollama by default — Claude API and other providers are opt-in.
Upload the PDF you're handed on the way out. Parsed locally with Ollama, reviewed by you, then applied to your profile.
Follow-ups to book, labs to get done, referrals to schedule — surfaced right after a visit, and again in a persistent "needs attention" list until you snooze or resolve them.
Health data is sensitive by default, so nothing crosses a boundary un-redacted.
PDF parsing always runs on a local model, and visit prep does too by default. Your raw records never touch the network unless you opt out.
Switch visit prep to Claude API or any OpenAI-compatible provider from Settings — names, dates of birth, and contact details are removed before anything is sent, using pattern matching and spaCy name detection.
This reduces exposure but isn't a guarantee — name detection is statistical and can miss names or identifying details in unusual free-text phrasing. Local-only mode (Ollama for both parsing and visit prep, the default) needs no anonymization step, since nothing leaves the machine.
Everything, including the database, stays in a folder on your machine. Needs Python 3.11+, Node 18+/pnpm, and Ollama.
$ git clone https://github.com/nidhi-menon/HealthSteward.git && cd HealthSteward $ pip install -r requirements.txt $ python -m alembic upgrade head $ python -m uvicorn src.main:app --reload --host 127.0.0.1 --port 8000
$ cd frontend && pnpm install && pnpm dev
$ ollama serve $ ollama pull qwen2.5:7b $ ollama pull llama3.2
Full setup, including the .env file, is in the README. A one-step installer for people who'd rather not open a terminal is on the way — track progress on GitHub.
This page is about the open-source v1.0 you run yourself. A hosted consumer app, with record linking, a Village of trusted people, and chat over your record, is being built separately and is not available yet. The main page explains the problem and the plan, and you can join the waitlist.