AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Medical › OpenHealth
✦ Free & open sourceMedical

OpenHealth

Consolidates health records, blood tests, and symptoms to feed structured context into local or cloud AI models.

Private AI health assistant built on personal medical data

Aggregate medical records and run contextual queries through local models like Ollama or commercial APIs.

Free forever · open source · AGPL-3.0
✓ Needs IT✓ Browser-based✓ Real-time collaboration
6.3
ZEKAI
Data-focused private health AI.
Free & open source · Medical
Ease of setup5
Usefulness7
Maintenance5.5
Community7.5
★ 3,948
GITHUB
Jan 2026
UPDATED
AGPL-3.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

OpenHealth aggregates scattered health inputs—such as blood tests, physical metrics, and symptom logs—into a structured format for AI-assisted analysis. You can run it fully offline using Docker and Ollama or access hosted web interfaces. It targets individuals and practitioners looking for structured, private context management alongside LLM models.

Runs on
Web
Hosting
Cloud or self-host
Languages
TypeScript
License
AGPL-3.0

What it is

The platform parses raw medical inputs like lab results, personal physical metrics, and family history into a standardized data file. It then uses this parsed structure as context for conversations with models such as LLaMA, DeepSeek-V3, GPT, Claude, or Gemini. For local execution, it pairs with Docling for parsing and Ollama for private inference.

Who it's for

It suits tech-savvy medical professionals and patients who want data privacy by running health assistant workflows locally. It is also usable via hosted web platforms for quick consultations. It does not suit non-technical users looking for a pre-built native desktop application without server configuration.

Key features

Multi-Source Data Consolidation

Aggregates blood tests, wearable data, family history, and personal symptom records into one structured repository.

Flexible LLM Engine Integration

Connects to commercial APIs like Claude and GPT or local models via Ollama and LLaMA.

Local Document Parsing

Processes documents locally using Docling to extract structured files without sending raw data to third parties.

Context-Aware AI Chat

Provides tailored responses by injecting your standardized medical data into model interaction context.

How to start

Up and running in 3 steps

1
Clone the repository and copy .env.example to .env while generating a 32-byte encryption key.
2
Configure your target LLM endpoints, adjusting host URLs if running Ollama in Docker.
3
Launch the container stack using docker compose --env-file .env up and access port 3000.
Real talk

Our honest verdict

What's great

  • Supports full local privacy using Docker, Docling, and local Ollama instances.
  • Compatible with both open local models and top commercial LLM APIs.
  • Accepts diverse inputs including blood lab results, wearable metrics, and family history.
  • Offers pre-hosted web variants alongside the self-hosted codebase.

Where it falls short

  • Requires running Docker or Podman and managing containerized services manually.
  • Data parsing currently relies on an external Python backend separate from the main repository.
  • Local inference demands hardware capable of running LLMs efficiently.
  • Setup requires manual environment variable configuration and encryption key generation.
Cost

Pricing & license

OpenHealth is free and open-source under the AGPL-3.0 license. Hosted options like Clinic and Full Platform exist online, but self-hosting requires hosting infrastructure and your own API keys for paid LLMs.

Paid work

Open remote AI-training roles

883 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: OpenHealth for Medical
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure OpenHealth for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can I run OpenHealth without sending data to external cloud APIs?

Yes, you can run the entire stack locally using Docling for document parsing and Ollama for local LLM inference.

What data formats and inputs can I add to OpenHealth?

You can input blood test results, health checkup reports, physical info, symptom logs, and family history.

Which AI models can be connected?

It natively supports LLaMA, DeepSeek-V3, GPT, Claude, and Gemini.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Medical — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google