Skip to main content

Expo AI Runtime

A mobile-native AI runtime for Expo and React Native. One TypeScript API over:

  • Apple Foundation Models (on-device, iOS 26+)
  • Android Gemini Nano via ML Kit GenAI / AICore (on-device)
  • An explicit, app-controlled cloud fallback

…with runtime capability detection, normalized errors, privacy metadata on every result, sessions, streaming, and structured output.

This is a provider layer, not an agent framework

This is the v1 provider layer — a reliable way to call the best available native or local model from a React Native app. It is intentionally not an agent framework yet. See the roadmap for where it's headed.

Packages

PackageWhat it is
@stewmore/expo-ai-corePure-TS heart: public ExpoAI API, adapter contract, provider router, capability registry, sessions, structured-output validation/repair, privacy, normalized errors. No native code.
@stewmore/expo-ai-apple-foundation-modelsiOS adapter wrapping Apple's FoundationModels framework (Swift).
@stewmore/expo-ai-android-aicoreAndroid adapter wrapping ML Kit GenAI / Gemini Nano via AICore (Kotlin).
@stewmore/expo-ai-cloudCloud fallback client adapter (configurable endpoint, streaming via expo/fetch).
@stewmore/expo-ai-evalsNode-first evaluation harness (quality, schema validity, latency, fallback frequency).

Next steps

  • Install the packages your app needs.
  • Follow the quick start for your first generation.
  • Read the concepts to understand routing, capabilities, privacy, and structured output.