On device ai

React Native ExecuTorch enables on-device AI model inference in React Native applications using Meta's ExecuTorch framework, supporting computer...

Needle is a 26-parameter distilled language model optimized for function calling on resource-constrained devices like phones and watches. It excels...

React Native AI provides on-device LLM execution and AI primitives (text generation, embeddings, transcription, speech synthesis) for React Native...

Parlor is a self-contained, on-device multimodal AI assistant that runs voice and vision conversations entirely locally using Gemma 4 E2B and Kokoro...

GenieX is an on-device inference runtime for running large language models and vision models locally on Qualcomm Snapdragon devices (NPU, GPU, CPU)....

LiteRT-LM is Google's production inference framework for deploying Large Language Models on edge devices across Android, iOS, Web, Desktop, and IoT...

MLX-Tune enables fine-tuning of large language models, vision models, and audio systems directly on Apple Silicon Macs using the native MLX...

PhoneClaw transforms iPhones into local AI agent runtimes that execute on-device tasks through native mobile Skills (calendar, reminders, contacts,...

NobodyWho is a multi-platform inference engine written in Rust that enables running LLMs locally and offline across Kotlin, Swift, Python, Flutter,...

Cactus is a low-latency AI inference engine purpose-built for mobile devices and wearables, enabling on-device LLM, vision, and speech processing via...

Claude Code Local enables running Claude Code 100% on-device using local AI models (Qwen 3.5, Llama 3.3, Gemma 4, DeepSeek V4 Flash) on Apple Silicon...

Foundation Lab is a native iOS and macOS workbench for learning, testing, and building applications with Apple's Foundation Models framework. It...

Mano-P is an open-source GUI-VLA (Vision-Language-Action) agent designed for edge devices, enabling local GUI automation on Apple Silicon Macs...

RunAnywhere is a production-ready SDK for running AI models (LLMs, vision, speech) entirely on-device across iOS, Android, Flutter, React Native, and...

NativeMind is a browser extension (Chrome and Firefox) that brings local AI models directly into your browser using Ollama and WebLLM, enabling...

FaceAISDK is an on-device Android face recognition, liveness detection, and face search library supporting 1:1 and 1:N/M:N scenarios entirely offline...

Thunderbolt is an open-source, cross-platform AI client designed for on-premise deployment that lets users choose their model providers, retain data...

RCLI is a voice-activated AI assistant for macOS that runs entirely on-device without cloud services, combining speech-to-text, LLM inference,...