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-neural-engine 开源项目推荐(67 个)
apple-neural-engine 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 67 个仓库Local Laya在Apple Core ML和Neural Engine上输入决策。经过验证的端口、M3 Max上约5 ms的短决策、可再现的速度和能耗基准。
World's first Face Authentication enabled MacOS App-locker, completely free and open-source. Unlock your Mac apps using Face , TouchID or password. Completely local and encrypted - your data never leaves your Mac
🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.
On-device meeting transcriber for macOS — auto-records Teams/Zoom/Webex, transcribes & separates speakers locally. No cloud. Open-source alternative to Otter/Granola/Fireflies.
Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU
Run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely
Your models on any xPU
Kokoro TTS 9.8x faster than MLX on an M1 Mac. Speaks 27 seconds of audio in under a third of a second on a Mac Mini or iPhone, on the Apple Neural Engine. Swift + Core ML, no Python.
Python runtime for the Apple Neural Engine
ModernBERT model optimized for Apple Neural Engine.
Apple Neural Engine (ANE) LLM inference engine — reverse-engineered private APIs, Metal GPU shaders, hybrid ANE+GPU+CPU on Apple Silicon. 32 tok/s matching llama.cpp, 3.6 TFLOPS fused ANE mega-kernels.
Correctness-validated heterogeneous Laya runtime for Apple Silicon (MLX GPU + Apple Neural Engine)
Push-to-talk voice dictation for macOS. 100% local, free, open source. Apple Silicon MLX. No cloud, no subscription.
A reference manual for the Apple Neural Engine
First super-resolution model designed for Apple Neural Engine. 2x upscale, real-time, on-device. Built by Ben Racicot.
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.
Typed decisions over text in milliseconds. A Rust inference engine and server that answers choice, score and yes or no questions with calibrated probabilities, compatible with Jev and Laya. The bar is 10x faster on every benchmark at equal or better accuracy.
Apple Neural Engine Microarchitecture Study: M6 — report, raw data, tools and figures | Apple M6 神经网络引擎微体系结构研究:报告、原始数据、工具与插图
A toolkit for BLE digital stethoscopes — capture, DSP, log-mel spectrograms, and murmur classification on the Apple Neural Engine
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-neural-engine。
- 该话题在 GitHub 上共有 67 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 1.2 万 Star,覆盖 4 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。