掌控你的 AI。面向 AI 智能体的原生 macOS 运行框架——支持任意模型、持久化记忆、自主执行、密码学身份。用 Swift 构建。完全离线。开源。
apple-foundation-models 开源项目推荐(66 个)
apple-foundation-models 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 66 个仓库A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.
'afm' 命令 CLI:macOS 服务器和单提示符模式,通过一个聚合的 OpenAI 兼容 API 端点,暴露苹果的 Foundation 和 MLX 模型及其他 API,运行在你的 Mac 上。支持Apple Vision和单一命令(非服务器)推理,同时支持管道。现在有了网页浏览器和本地 AI API 聚合器
React Native Apple LLM plugin using Foundation Models
Document chat app for macOS / iOS. Upload files, ask questions. Everything runs locally on your Mac / iPhone.
On-device AI for Expo and React Native. Local LLM, speech-to-text, vision, and embeddings. No API keys, no cloud.
A Swift command-line interface tool for interacting with macOS Apple Intelligence foundation models.
Production-ready architectural patterns and implementation skills for building modern iOS apps with Swift, SwiftUI, and Tuist — designed as context for AI coding agents.
A collection of Agent Skills for building iOS/macOS applications with Apple's Foundation Models framework (Apple Intelligence). These skills are designed for zero-friction AI-assisted development with on-device models.
TypeScript/Node.js bindings for Apple's on-device Foundation Models (macOS 26+ only)
apfelclaw is an AI agent for tasks with macOS using Apple's Foundation model via apfel.
iOS app that turns Ray-Ban Meta smart glasses into a hands-free study tool. Scan documents, extract text with OCR, generate AI summaries with Apple Foundation Models (Apple's On-Device AI) or online LLM models and organize content into decks with flashcards and quizzes. Built with SwiftUI, SwiftData, Vision, PDFKit, and Meta Wearables SDK.
Intents is a native macOS workbench for evaluating Apple's on-device Foundation Models.
Python SDK for WildEdge
Expo module for on-device LLM inference via Apple Foundation Models (iOS) and Gemini Nano (Android)
A collection of examples using Apple’s FoundationModels framework
Offline LLM app for iPhone: run open models from Hugging Face on-device with llama.cpp, MLX, Core ML and Apple Foundation Models. No account, MIT.
Commit messages written on your Mac by Apple Intelligence. Your code never leaves the machine.
Make Apple's Foundation Models accessible over web APIs
Multiplatform 3D chess app powered by Stockfish, featuring on-device AI move coaching and cloud-based RAG for position chat.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/apple-foundation-models。
- 该话题在 GitHub 上共有 66 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1.1 万 Star,覆盖 5 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。