Open Wearables
Unified wearable health data platform with an AI-ready API and MCP server.
Collect normalized health metrics from Garmin, Apple Health, Whoop, and more behind a single API.
Open Wearables is a self-hosted platform that consolidates data from fitness devices and health platforms into a single normalized API. It suits software developers and researchers building health apps, fitness coaching tools, or AI agents that query real biometric data.
What it is
The platform aggregates multi-provider device data such as heart rate, sleep, workouts, and time-series biometrics through one REST API. It includes a built-in Model Context Protocol (MCP) server so language models in Claude or Cursor can directly query your users' health data.
Who it's for
It suits developers building health applications, AI fitness coaches, or researchers collecting standardized multi-source metrics. It is not built for end-users who want a ready-made consumer app without deploying infrastructure or managing server configurations.
Key features
Unified Provider API
Connect Garmin, Oura, Whoop, Apple Health, and others through a single data model.
Built-in MCP Server
Expose user health metrics directly to LLMs and AI agents via Model Context Protocol.
Mobile Sync SDKs
Native SDKs for iOS, Android, Flutter, and React Native for on-device health store sync.
Webhook Notifications
Trigger HTTPS endpoints automatically when new user data arrives on the platform.
Up and running in 3 steps
Our honest verdict
What's great
- Normalizes fragmented device APIs into one consistent data model
- Includes a native MCP server for querying data with Claude or Cursor
- Provides mobile SDKs for iOS, Android, Flutter, and React Native
- Supports Apple Health XML bulk file imports via S3 multipart upload
Where it falls short
- Requires managing your own self-hosted infrastructure and Docker containers
- Must handle OAuth configurations and developer accounts for each external wearable provider
- Setting up database seed data and environment variables requires technical proficiency
Pricing & license
The software is free to run under its open-source license. The only cost is running it yourself on your own servers or infrastructure.
Open remote AI-training roles
874 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
What devices does Open Wearables support?
It supports cloud-based providers like Garmin, Oura, Whoop, Strava, Fitbit, and Google Health, plus SDK-based integrations for Apple Health, Samsung Health, and Google Health Connect.
How do AI tools access the health data?
The platform features a built-in MCP server that allows AI clients like Claude Desktop and Cursor to query user profiles, sleep, workouts, and time-series metrics via natural language.
