# StanfordBDHG/HealthGPT

Query your Apple Health data with natural language 💬 🩺

Repository: https://github.com/StanfordBDHG/HealthGPT
Canonical: https://ross.abutalabs.com/products/healthgpt
Language: Swift
License: MIT
License Family: permissive
Topics: apple-health, healthkit, ios, openai, swift
Last push: 2026-07-14T00:25:45+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 69, longevity 88
- inputs: {"age_days": 1234, "days_push": 51, "days_rel": 51, "gap_med": 137, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1964, forks 185 (observed 2026-08-28T04:05:59.793619+00:00)

## What it is
HealthGPT is an experimental open-source iOS app built on the Stanford Spezi framework that lets users query their Apple Health data using natural language through a chat interface. It integrates HealthKit with GPT-3.5/GPT-4 via OpenAI and also supports privacy-preserving local LLM execution with Llama 3 8B.

## Use cases
- ask questions about my apple health data in natural language
- chat with an llm about my health metrics
- build an llm-powered app on top of healthkit
- run health data queries locally without sending data to openai
- export conversations about my health data
- voice-based interaction with health records

## When to choose
- you want an ios app to interact with apple health data via llm
- you need an extensible swift starting point for health-focused llm apps
- you want both cloud (GPT-4) and local (Llama 3) inference options

## When to avoid
- you need an android or web solution
- you need clinical-grade medical advice or diagnostics
- you want a non-iOS or non-Swift integration with health data

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, chat-interface, speech-recognition, tts
- domain: healthcare, large-language-models, mobile-development, artificial-intelligence
- platform: -
- tags: healthkit, apple-health, openai, spezi, digital-health, gpt-4, local-llm, ios, swift, mobile

## Member repositories
- StanfordBDHG/HealthGPT (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:59.793619+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:05:29.921067+00:00, confidence not recorded.
  - readme: https://github.com/StanfordBDHG/HealthGPT (fetched 2026-08-28T04:05:59.793619+00:00, sha 5a0fe3d87cb0)
- Data as of 2026-08-30T08:39:29.467469+00:00.