Foundation Models On Device

This wraps Apple's FoundationModels framework for building on-device LLM features in iOS 26+. You get text generation, structured output with the @Generable macro, custom tool calling, and snapshot streaming for real-time UI updates. Everything runs locally, so no cloud dependency and no data leaves the device. The patterns cover availability checks (critical since not all devices support Apple Intelligence), session management with instruction-based steering, and streaming partial results to SwiftUI views. The 4,096 token context limit is tight, so you'll need to chunk larger inputs. Good fit if you're building privacy-first AI features or need offline text generation without reaching for third-party SDKs.

Install to Claude Code

npx -y skills add affaan-m/everything-claude-code --skill foundation-models-on-device --agent claude-code