Daisuke Majima

Converted CoreML Model Zoo.

Community model zoo for Apple Core AI (iOS/macOS 27): 49 models — LLM, VLM, OCR, ASR, TTS, image/video/music gen, forecasting — converted, verified on real devices, downloadable from Hugging Face, and runnable in one line of Swift via CoreAIKit. Plus conversion recipes, on-device benchmarks, custom Metal kernels, and a knowledge base.

a sample collection of basic functions of Apple's AR framework for iOS.

Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU

A collection of easy-to-use image/video filter.

iPhone/iPad version of lama cleaner

A sample project how to use YOLOv5 in iOS

No description.

No description.

Neutral, reproducible benchmark for local LLMs on Apple Silicon (Mac · iPhone · iPad) — MLX, llama.cpp, CoreML, Apple Foundation Models

No description.

Simple LLM package for ios devices.

No description.

Run Gemma 4 (LiteRT-LM) on iPhone the easy way — and as an Apple Foundation Models backend. Metal GPU, multimodal, in-app download.

No description.

Run LLMs, VLMs, ASR, TTS, diarization and more fully on-device with Apple's Core AI framework (iOS/macOS 27) — one line of Swift per model, 49 verified models, pinned catalog, nightly device gate. Plugs into Apple's FoundationModels API: LanguageModelSession with tool calling + guided generation.

simple usage of yolov8 on android device

segment person sample on iOS

The sample project how to use MobileStyleGAN in iOS.

No description.

Relightable 3D Gaussian Splatting viewer in Swift + Metal: split-sum image-based lighting, HDR environment with skybox, deferred PBR for Ref-Gaussian assets. Based on scier/MetalSplatter.

No description.

Converted TFLite Model Zoo for Android with LiteRT CompiledModel GPU acceleration

No description.

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.

On-device structured VLM fan-out on Apple Silicon (MLX): pair Apple Vision with a local VLM to count, locate, and describe. Multi-demo example app.

The Art of Core AI — a free hands-on book on shipping AI models on iPhone/Mac with Apple's Core AI framework (iOS/macOS 27). 13 chapters + 7 labs, from first export to custom Metal kernels. Japanese edition on Zenn.

Claude Code の応答を日本語音声で読み上げるCLIツール（VOICEVOX連携）

No description.

No description.

No description.

Curated resources for Apple's Core AI framework (iOS/macOS 27) — official tooling, converted models, conversion pipelines, sample apps, benchmarks, and learning material.

No description.

easyportrait run on swift sample

The camera shoot a photo when animals apear in the frame.

Models you can use them on iOS.

Sample apps for Apple's Core AI framework — chat with any exported LLM bundle on macOS, more coming

No description.

No description.

No description.

Ultralytics YOLO iOS App source code for running YOLOv8 in your own iOS apps 🌟

On-device agentic API demos (Foundation Models) running on third-party Core AI zoo models via coreai-kit

No description.

Fastest mobile Gemma 4 E2B — llama.cpp Metal + speculative decode on iPhone 17 Pro

Superscale is a plug-and-play super-resolution toolkit. Run the latest 6 SOTA models with a single line of Python or via a zero-setup GUI.

A collection of samples for using various AI models on iOS.

Custom converter: open-weight Hugging Face LLMs/VLMs -> on-device LiteRT-LM (.litertlm), with one-command reproduction

Open-vocabulary on-device photo tagging for construction / facility / industrial inspection. YOLO-World via CoreMLZoo. iOS 17+.

No description.

No description.

Evaluate whether your PyTorch vision model is actually ready for on-device deployment on iPhone.

No description.

pretrained tflite models.

No description.

You can process

Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

Local Office Evidence Layer for Claude Code — turn messy PDFs/Office docs/scans into grounded, actionable context Claude Code can use to do real office work safely. OSS-first adapter architecture.

No description.

Transparent sticker maker — offline cutout of any video subject, powered by CoreMLZoo (MatAnyone + RMBG). iOS 17+.

No description.

No description.

Homebrew formulae for john-rocky tools

No description.

No description.

No description.

Models and examples built with TensorFlow

No description.

Detecting no mask face app.

AI Photo Coach analyzes your iPhone camera frame and gives you advice on how to take better photos.

Swift Package to implement a transformers-like API in Swift

Marketing, privacy, and support pages for the Core ML Models iOS app.

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

No description.

A GPU accelerated image and video processing framework built on Metal.

No description.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

Simple Swift AVPlayerView

No description.

No description.

プルリクエストの練習用リポジトリ (ISC License)

No description.

入門コースの3章4節 npmの練習 (ISC License)

入門コースの3章2節の練習 (ISC License)

プルリクエストの練習用リポジトリ (ISC License)

No description.

No description.

入門コースの3章1節の練習 (ISC License)

入門コースの3章2節 集計処理プログラム (ISC License)

入門コースの3章3節 フィボナッチ数列 (ISC License)

No description.

入門コースの3章22節の練習 (ISC License)

入門コースの3章4節の練習 (ISC License)

入門コースの3章6節の練習 (ISC License)

入門コースの3章7節の練習 (ISC License)

入門コースの3章8節の練習 (ISC License)

入門コースの3章9節の練習 (ISC License)

入門コースの3章10節の練習 (ISC License)

入門コースの3章11節の練習 (ISC License)

入門コースの3章12節の練習 (ISC License)

入門コースの3章13節の練習 (ISC License)

入門コースの3章14節の練習 (ISC License)

入門コースの3章17節の練習 (ISC License)

入門コースの3章18節の練習 (ISC License)

入門コースの3章30節の練習 (ISC License)

入門コースの3章19節の練習 (ISC License)

入門コースの3章20節の練習 (ISC License)

入門コースの3章21節の練習 (ISC License)

入門コースの4章6節の練習 (ISC License)

入門コースの4章5節 damage-calc (ISC License)

入門コースの4章18節の練習 (ISC License)

Spika is universal chat module with backend, web, ios and Android client.

Create Anime Characters with MakeGirlsMoe

No description.

No description.

猫と河村さんを学習させた

myhomepage

No description.

No description.

No description.

Demo media for coreai-kit / coreai-model-zoo READMEs — kept out of the code repos to keep clones small

The canonical list of repositories indexed by the Swift Package Index

An API-compatible, drop-in replacement for Apple's Foundation Models framework with support for custom language model providers.

Use Hugging Face with JavaScript

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

Support PyTorch model conversion with LiteRT.

No description.

Privacy policy for the CoreAI Zoo apps (iOS + macOS)

No description.

No description.

A modular Swift SDK for audio processing with MLX on Apple Silicon

No description.

A minimalistic Swift implementation of the Jinja templating engine, specifically designed for parsing and rendering ML chat templates.

Swift API for MLX

A curated list of awesome iOS ecosystem, including Objective-C and Swift Projects

No description.

Koe — iPhone accessibility communication aid. Landing, privacy, support pages.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

A lightweight, powerful framework for multi-agent workflows

Public repository for Agent Skills

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Fast, flexible LLM inference

On-device Speech AI for Apple Silicon

LiveKit Swift Client SDK. Easily build live audio or video experiences on iOS, macOS, tvOS, and visionOS.

LLM inference in C/C++

On-device AI across mobile, embedded and edge for PyTorch

LLMs and VLMs with MLX Swift

Examples using MLX Swift

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Privacy Policy & Support for ProductMeasure

No description.

Tasmon - Slay Tasks, Collect Monsters

No description.

No description.

OpenMMLab Detection Toolbox and Benchmark

The collection of the sample codes using Vision.

NEW - YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

This is user-friendly SF Symbols.

No description.

The camera automatically shoot a photo when animals appear in the frame.

No description.

Collection of sample apps showcasing popular use cases using Cloud Functions for Firebase

The Camera you can specify the interval of continuous shooting and the crop size.