Summary

This Python tool analyzes exported Apple Health data, generating visualizations and AI-driven insights. It targets users seeking to understand their fitness, health metrics, and activity patterns, offering a comprehensive overview and personalized analytics.

How It Works

The project parses Apple Health's export.xml file using Python. It generates interactive charts for metrics like steps, heart rate, sleep, and workouts. A key feature is its integration with various Large Language Models (LLMs), including OpenAI's services and local Ollama instances, to provide AI-powered analysis and personalized insights directly from the user's health data.

Quick Start & Requirements

Installation involves cloning the repository, installing Python dependencies (pip install -r requirements.txt), and running the main script (python src/applehealth.py). Docker support is also provided. Prerequisites include Python 3.6+, pandas, matplotlib, and LLM provider API keys (e.g., OpenAI) for AI features. Local LLM analysis requires Ollama to be installed and a model (like deepseek-r1) to be pulled, with a minimum of 8GB RAM recommended for performance. Users must export their Apple Health data to export.xml.

Highlighted Details

• AI-Powered Analysis: Integrates with multiple LLMs (OpenAI, Anthropic, Google, Grok, xAI, OpenRouter, Ollama) for personalized insights.
• Local LLM Support: Enables private data analysis using Ollama models directly on the user's machine.
• Interactive Visualizations: Generates dynamic charts for key health metrics.
• WHOOP Integration: Specialized support for analyzing WHOOP workout data.

Maintenance & Community

The project welcomes contributions via standard GitHub pull requests. A roadmap outlines planned features such as support for more data types and enhanced visualizations. Community interaction channels like Discord or Slack are not explicitly mentioned.

Licensing & Compatibility

The project is released under the MIT License, which permits broad use, including commercial applications and linking within closed-source projects, with minimal restrictions.

Limitations & Caveats

The tool exclusively supports Apple Health's XML export format. WHOOP integration is limited to workout data. AI analysis necessitates API keys and internet connectivity for external LLMs. Local LLM performance is dependent on hardware, with 8GB RAM minimum recommended. Sleep analysis assumes standard Apple Health data formatting.