apple-foundation-models

Name: apple-foundation-models
Availability: InStock
Author: ios-agent

Integrate Apple Foundation Models for on-device AI in iOS and macOS apps.

10|Updated Jan 13, 2026

Search Tags:#ai #llm #ios #macos #swiftui #on-device #foundation models

Ready to run

npx skills add https://github.com/ios-agent/iosagent.dev --skill apple-foundation-models

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: apple-foundation-models
Source: https://github.com/ios-agent/iosagent.dev/tree/main/apple-foundation-models
Command: npx skills add https://github.com/ios-agent/iosagent.dev --skill apple-foundation-models

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables developers to integrate powerful on-device AI and Large Language Model (LLM) capabilities directly into their iOS and macOS applications, ensuring privacy and offline functionality.

Core Features & Use Cases

On-Device AI: Leverage Apple's Foundation Models framework for local LLM processing.
SystemLanguageModel: Work with Apple's on-device LLM API for tasks like text generation, summarization, and more.
Guided Generation: Generate structured Swift types from prompts, ensuring type-safe output.
Tool Calling: Extend model capabilities by allowing it to interact with custom tools and APIs.
Use Case: Build an intelligent note-taking app that can summarize user notes, answer questions about the content, and even generate structured to-do lists based on the notes, all without sending data off-device.

Quick Start

Use the apple-foundation-models skill to create a language model session and respond to a prompt about Swift closures.

Frequently Asked Questions about apple-foundation-models

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I integrate on-device LLM capabilities into my iOS app?▼

On-device AI processes data locally using Apple's Foundation Models framework, ensuring privacy and offline functionality by leveraging SystemLanguageModel and LanguageModelSession without sending data off-device.

How do I generate structured Swift types from LLM prompts?▼

You can generate structured Swift types from prompts using the guided generation feature of Apple's Foundation Models, ensuring type-safe output directly within your iOS or macOS application.

Can I use Foundation Models for tool calling in macOS applications?▼

Yes, Foundation Models support tool calling in macOS applications, allowing the on-device LLM to interact with custom tools and APIs to extend model functionality.

Does on-device AI with Foundation Models work offline?▼

Yes, on-device AI with Apple's Foundation Models works offline by processing local LLM tasks directly on iOS and macOS devices, ensuring privacy and functionality without an internet connection.

What are the limitations of using on-device Foundation Models for text generation?▼

On-device Foundation Models are limited by hardware capabilities and local memory, meaning complex natural language understanding tasks may perform slower than server-side LLMs, though they ensure privacy and offline functionality.

How do I manage transcripts and custom adapters in a LanguageModelSession?▼

You manage transcripts and custom adapters within a LanguageModelSession using Apple's Foundation Models framework to handle dynamic conversations and customize on-device LLM behavior in iOS/macOS apps.