Back to directory

Awesome On-Device AI Apps

A collection of 36 finished, cloneable mobile app templates that run their AI features entirely on the phone's own hardware, spanning chat, translation, vision, health, voice and forecasting.

Awesome On-Device AI Apps

Every app in the collection runs its model directly on the device's NPU using the Melange on-device runtime, so no user data is sent to a server, there is no per-token inference bill, and the app keeps working offline with no network round-trip. Each folder is a complete, runnable app rather than a snippet, covering categories such as language and text, vision, health and wellbeing, audio and forecasting, with examples including a private meeting-notes app, an on-device rewriting keyboard, real-time grammar correction, offline machine translation and medical-domain speech recognition.

A generator script rebuilds the project's own catalog table, including each app's short description, the specific on-device model it uses and which platforms it supports, from a per-app metadata file, whenever a new app is added to the repository.

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.