Back to directory

React Native AI

A collection of on-device AI primitives for React Native, compatible with the Vercel AI SDK, for running text generation, embeddings, transcription and speech synthesis directly on a user's phone.

React Native AI

React Native AI is a toolkit of on-device AI primitives for React Native apps, designed as a drop-in, Vercel AI SDK-compatible replacement so existing AI SDK code can run against on-device models for privacy-preserving, low-latency inference with no server cost. Apple's built-in Foundation Models, embeddings, transcription and speech synthesis work immediately on iOS with no model download, while other providers, such as llama.rn for GGUF models and MLC LLM, run on-device on iOS and Android.

A companion DevTools package captures OpenTelemetry spans from Vercel AI SDK requests and surfaces them inside Rozenite DevTools, working with both on-device and remote model runtimes, and an Expo example app demonstrates the native-development wiring needed to use it. It is written in TypeScript under the MIT license.

More in Mobile

See all 90
  • Dart and Flutter bindings for the Zvec in-process vector engine, letting mobile and desktop apps run on-device semantic search, retrieval-augmented generation and similarity queries with no separate server.

  • Mobile Claw

    github.com

    A Capacitor plugin that embeds a native Rust AI agent engine directly on Android and iOS, running Claude with file tools, code execution, git and extensible MCP device tools, on-device vector memory and background scheduling, with no cloud relay.

  • A Swift package for streaming, on-device speech recognition on iOS, built on a custom Rust inference runtime (VoxRT) rather than ONNX Runtime or PyTorch Mobile, running a 32-million-parameter FastConformer model with roughly 90ms per-chunk latency on an iPhone 13 Pro Max.