Production ready toolkit to run AI locally

Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.

Low-latency AI engine for mobile devices & wearables

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.

AI You Control: Choose your models. Own your data. Eliminate vendor lock-in.

On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

On-device LLM execution in React Native with Vercel AI SDK compatibility

on_device Face Recognition 、 Liveness detection and 1:N & M:N Face Search SDK。离线版设备端人脸识别 动作活体、炫彩活体、近红外双目活体检测 以及1:N M:N 人脸搜索算法SDK 封装；全程可开飞行模式不用联网

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

NativeMind: Your fully private, open-source, on-device AI assistant

Example apps for Foundation Models Framework in iOS 26 and macOS 26

TinyChatEngine: On-Device LLM Inference Library

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

Local-first, open-source AI assistant for your data. Unify tasks, notes, docs, photos, and bookmarks. Private, self-hosted, and extensible via APIs.

Optimized Whisper models for streaming and on-device use

Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/MacBook 上或通过算力棒本地运行推理，实现纯视觉驱动的跨平台 GUI 自动化操作。数据完全本地处理，支持复杂多步骤任务规划与执行。