Can ChatGPT analyze my entire Apple Health export?

Not effectively. Apple Health exports can be huge. The practical approach is to query targeted summaries and trends via a local API and send the compact result to ChatGPT for analysis.

What’s the base URL for the local API?

By default it runs at http://127.0.0.1:8765 on your Mac.

Do I need function calling/tools to use this?

No. You can paste API responses into ChatGPT manually. Tools/function calling make it automated, but the workflow works either way.

OpenAI + Local API

Apple Health + OpenAI / ChatGPT (via a Local API)

Fetch the exact metric slice you need locally (sleep, steps, workouts, heart rate), then ask ChatGPT to summarize, detect trends, and return structured next steps.

Export → AirDrop → Analyze with Claude, ChatGPT, or any AI.

Prerequisite: install the Mac app. The app runs the local API on your Mac at 127.0.0.1. If the app isn’t running, the API won’t respond.

Download Mac App Setup guide

Base URL: http://127.0.0.1:8765
Auth header (most routes): X-Health-Analyzer-Token: <token>
Token file path: returned by GET /status

Docs: Apple Health Local API · Hub: Apple Health + AI

Why OpenAI + local query endpoints works

Time-series health data explodes in size. The trick is to keep the model focused: query summaries and trends (already aggregated), then ask ChatGPT to reason over the compact payload.

Quickstart

Confirm the API is running: GET http://127.0.0.1:8765/status
Load your token (path returned by /status)
Pull one metric slice (e.g., 30–90 days) using a summary/trend endpoint
Paste the JSON into ChatGPT and ask for structured outputs

Prompts that work well (OpenAI-optimized)

Prompt 1 — Findings + next queries

Analyze the JSON below.

Return:
1) Key findings (bullets)
2) Confidence level (high/med/low) with reasons
3) Outliers/anomalies
4) The next 3 API queries to run (endpoint + date range) to validate your hypothesis

Prompt 2 — Structured action plan

Based on the dataset below, produce:

A) A plain-English summary (max 8 bullets)
B) A JSON action plan with fields:
- goals
- constraints
- interventions
- metrics_to_track
- 14_day_experiment
- follow_up_questions

Example API calls

Daily steps (chart-ready):

curl -s \
  -H "X-Health-Analyzer-Token: $TOKEN" \
  "http://127.0.0.1:8765/steps/daily?start=2026-01-01&end=2026-03-27"

Workouts summary:

curl -s \
  -H "X-Health-Analyzer-Token: $TOKEN" \
  "http://127.0.0.1:8765/workouts/summary?start=2026-02-25&end=2026-03-27"

Blood glucose summary:

curl -s \
  -H "X-Health-Analyzer-Token: $TOKEN" \
  "http://127.0.0.1:8765/blood-glucose/summary?start=2026-02-25&end=2026-03-27"

Cost & accuracy best practices

Prefer /summary and */summary endpoints over raw samples
Start with 30–90 days; expand only if needed
Ask ChatGPT to explicitly request more data (endpoint + range) before making strong claims

Compatibility routes

Compatibility endpoints also exist under /health/* (for example /health/sleep and /health/workouts).

Want the docs + endpoints list?

Start with the Local API, then build your ChatGPT workflow.

Local API Docs Next: Gemini