SwiftAI

We added an experimental support for MLX see README [https://github.com/mi12labs/SwiftAI/?tab=readme-ov-file#loca...]. We also added an chat demo where you can interact with 20+ models [https://github.com/mi12labs/SwiftAI/tree/main/Examples/ChatA...]

I’ve added documentation on creating new LLM integrations in SwiftAI [https://github.com/mi12labs/SwiftAI/blob/main/Docs/Guides/cu...]. We also have a proof-of-concept using MLX-optimized models from Hugging Face [https://huggingface.co/mlx-community], which we’ll release once it’s ready.

We built SwiftAI, an open-source Swift library that lets you use Apple’s on-device LLMs when available (Apple opened access in June), and fall back to a cloud model when they aren’t available — all without duplicating code. SwiftAI gives you: - A single, model-agnostic API - An agent/tool loop - Strongly-typed structured outputs - Optional chat state Backstory: We started experimenting with Apple’s local models because they’re free (no API calls), private, and work offline. The problem: not all devices support them (older iPhones, Apple Intelligence disabled, low battery, etc.). That meant writing two codepaths — one for local, one for cloud — and scattering branching logic across the app. SwiftAI centralizes that decision. Your feature code stays the same whether you’re on-device or cloud. Example import SwiftAI let llm: any LLM