Consolidates health records, blood tests, and symptoms to feed structured context into local or cloud AI models.
Aggregate medical records and run contextual queries through local models like Ollama or commercial APIs.
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.
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.
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.
Aggregates blood tests, wearable data, family history, and personal symptom records into one structured repository.
Connects to commercial APIs like Claude and GPT or local models via Ollama and LLaMA.
Processes documents locally using Docling to extract structured files without sending raw data to third parties.
Provides tailored responses by injecting your standardized medical data into model interaction context.
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.
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.
These reviewed AI tools do the same job instantly — from our scored directory.
Yes, you can run the entire stack locally using Docling for document parsing and Ollama for local LLM inference.
You can input blood test results, health checkup reports, physical info, symptom logs, and family history.
It natively supports LLaMA, DeepSeek-V3, GPT, Claude, and Gemini.
See Zekai first in Google