Skip to main content

Expo AI Runtime

One AI API. On-device first, cloud when it counts.

A mobile-native AI runtime for Expo & React Native. It detects what each device can run, routes to the best provider, and tells you the privacy implications of every response.

Default routing order
  1. apple-foundation-modelsApple Foundation ModelsiOS 26+ · Apple Intelligence
    on-device
  2. android-aicore-gemini-nanoGemini NanoAndroid · ML Kit GenAI / AICore
    on-device
device boundary
  1. apple-private-cloud-computePrivate Cloud ComputeApple-operated, stateless
    private cloud
  2. cloudCloud fallbackYour backend · opt-in
    third-party cloud
  3. noneUnavailableNo eligible provider
    n/a

Two lines to your first generation

The same call works across Apple Foundation Models, Android Gemini Nano and your cloud backend. Capability detection and fallback are handled for you.

import { ExpoAI } from "@stewmore/expo-ai-core";

const { text, provider, privacy } = await ExpoAI.generate({
prompt: "Summarize this in one sentence.",
});

// text -> the model output
// provider -> which engine answered (e.g. "apple-foundation-models")
// privacy -> { isOnDevice, sendsPromptOffDevice, privacyMode }

The packages

A pure-TypeScript core plus thin native adapters. Import only what your app needs.