Back to directory

Foundation Lab

A native iOS and macOS workbench for learning, testing and shipping with Apple's Foundation Models framework, combining editable prompt recipes, guided labs and run inspection in one app.

Foundation Lab

Foundation Lab is built around three destinations: a Library of eighteen editable recipes, fourteen guided labs, three workshops and saved experiments; a Playground for editing prompts and instructions, configuring the model and its tools, streaming responses, using voice input and exporting working Swift code; and a Runs view for inspecting persisted run status, configuration, transcript events, tool calls, timing and token usage.

A recipe opens directly in the Playground and can be edited, run and saved, a guided lab uses a focused interface built for one specific Foundation Models API, a workshop groups related schema, language or Xcode 27 examples without adding another top-level destination, and a workspace opens a dedicated tool such as an adapter-comparison view.

The app requires iOS 26 or macOS 26 or later, Apple Silicon and Apple Intelligence enabled for live model runs, and builds with either Xcode 26.6 or Xcode 27, with newer APIs gated behind availability checks so the core app still builds on the older toolchain. It is released 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.