The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
-
Updated
Aug 5, 2026 - Swift
The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoring (IROS 2026)
a Swift framework for intelligent document analysis/text operation powered by on-device and cloud-based AI models.
A collection of examples using Apple’s FoundationModels framework
A Swift package that acts as a dynamic bridge between Apple's FoundationModels framework and any server implementing the Model Context Protocol (MCP)
Unified Swift interface for Foundation Models — Ollama, Claude, OpenAI Responses API, and MLX backends via trait-based configuration
Apple FoundationModels API on iOS 18+. Same call site, native passthrough on iOS 26 (Apple Intelligence), CoreML / MLX backends on older OSes. Drop-in source compatible.
[DEPRECATED] Use AnyFoundationModels instead. OpenAI integration for OpenFoundationModels.
MCP Server to generate message with Apple FoundationModels
The private alternative to Perplexity. Native iOS 26 / macOS 26 answer engine — searches the web via SearXNG, generates answers on-device with Apple Intelligence. Zero tracking. Zero cloud AI. Zero dependencies.
Example NativeScript using iOS 26+ FoundationModels
Example using ServerLanguageModel private API in FoundationModels
Run Apple Intelligence, CoreML, and MLX models using a unified Swift interface for local language model sessions on iOS and macOS.
Modern iOS app showcasing SwiftUI, SwiftData, and MVVM architecture — built to explore Apple’s latest ecosystem.
A macOS framework for generating plant care guidance using FoundationModels.
Typed, model-agnostic LLM agents in Swift — a pydantic-ai port built on Apple FoundationModels. Anthropic Claude, OpenAI, Google Gemini, and on-device, with tools, structured output, streaming, and a graph-based run engine.
Repository associated with the journal article on zero-shot inference strategies for foundation models used on satellite images
To associate your repository with the foundationmodels topic, visit your repo's landing page and select "manage topics."