#5454th of 54 in AssistantsFor science, health and research

open-health

Web app that parses personal health records and chats about them with an LLM

Stars
4k
License
AGPL-3.0
Last commit
Jan 2026
Last release
Feb 2025
Language
TypeScript
Stars, last 29 weeks+148
21 Apr 2026: 3,822 stars28 Apr 2026: 3,824 stars5 May 2026: 3,830 stars12 May 2026: 3,837 stars19 May 2026: 3,849 stars26 May 2026: 3,854 stars2 Jun 2026: 3,856 stars9 Jun 2026: 3,862 stars16 Jun 2026: 3,868 stars23 Jun 2026: 3,870 stars30 Jun 2026: 3,876 stars7 Jul 2026: 3,880 stars14 Jul 2026: 3,882 stars21 Jul 2026: 3,889 stars28 Jul 2026: 3,897 stars4 Aug 2026: 3,905 stars11 Aug 2026: 3,909 stars18 Aug 2026: 3,914 stars25 Aug 2026: 3,919 stars1 Sept 2026: 3,921 stars8 Sept 2026: 3,927 stars15 Sept 2026: 3,931 stars22 Sept 2026: 3,937 stars29 Sept 2026: 3,945 stars6 Oct 2026: 3,951 stars13 Oct 2026: 3,953 stars20 Oct 2026: 3,956 stars27 Oct 2026: 3,961 stars3 Nov 2026: 3,963 stars10 Nov 2026: 3,970 stars

3,822 on 21 Apr 20263,970 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

OpenHealth is a Next.js app that takes health inputs such as blood tests, checkup data, family history and symptoms, parses them into structured data, and uses that as context for chat with an LLM. It supports hosted models (GPT, Claude, Gemini, DeepSeek-V3) and local ones through Ollama, and can parse documents locally with docling. Parsing currently runs in a separate Python server.

Who it is for: Self-hosters who want a private LLM chat over their own health records

Strengths

  • Can run fully local: docling for parsing, Ollama for the LLM
  • Works with LLaMA, DeepSeek-V3, GPT, Claude and Gemini
  • Docker/Podman Compose setup with a .env file, served on port 3000
  • Converts uploaded health data into structured files used as chat context

Weaknesses

  • Parsing runs in a separate Python server, with a planned TypeScript migration
  • Last release was 2025-02-21, so tagged releases lag behind recent commits
  • Apple Health, Google Fit and wearable sources appear only in the diagram, not the source list
  • AGPL-3.0 license restricts closed-source network deployments

What it needs

  • GPU optional
  • Docker + Compose
  • Needs Docker or Podman Compose, Ollama (for local LLMs), docling (for local parsing), Python parsing server
  • Models: LLaMA, DeepSeek-V3, GPT, Claude, Gemini
  • port 3000

Quick answers

Is open-health open source?

Yes. Its code is on GitHub under the AGPL-3.0 license.

Can you run open-health with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does open-health need a GPU?

No. It runs on a CPU and can use a GPU when you have one.

Also in Assistants

See all 54
Also in Assistants
RankProjectScore
1ai-job-searchClaude Code workflow that searches job boards and drafts tailored CVs and cover letters71.2k starsMIT96 out of 100
2career-opsJob-search agent that scores listings, tailors CVs and drafts applications81.9k stars+8,035 (+11%) in 30 daysMIT95 out of 100
3OpenClawPersonal AI assistant reachable through Discord, Slack, Telegram, WhatsApp and more394.3k stars+4,398 (+1.1%) in 30 daysMIT93 out of 100
#4openhumanRust agent harness with desktop app, built-in memory and embeddable library42.7k stars+984 (+2.4%) in 30 daysGPL-3.093 out of 100
#5airiAI VTuber companion with VRM and Live2D avatars, voice, and game-playing Live demo ↗ (opens in a new tab)51.3k stars+1,184 (+2.4%) in 30 daysMIT91 out of 100