Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.5, Claude, DeepSeek V4, Grok, OpenRouter, Kimi 2.6, GLM 5, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.7

Steno is the privacy-first AI notepad for all your confidential conversations. On Windows & MacOS. Perfect for government, healthcare, defence, legal and CXOs.

OpenClaw alternative in your pocket

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

Plug-and-play local AI studio: uncensored chat, image & video generation, coding agent. Runs abliterated LLMs + ComfyUI 100% offline. One installer, no Docker, no cloud.

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Local AI Assistant on your phone

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

An open-source Cotypist with macOS system wide AI autocomplete

Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

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.

🤖FFPA: Extends FA-2/3 via Split-D for large headdims, 1.5x~6×↑🎉 vs SDPA, up to 513~535 TFLOPS🎉 on NVIDIA H200.

llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% throughput).

A native .NET LLM inference engine for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/Linux with full GPU capability

This is end to end course on AI Agents and Agentic AI with 15+ AI Agent Projects with real time use cases and industry expertise.

Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection. + GPU Acceleration

Agentic ✧ Gemma Inference for Android System Intelligence

Automated image & video captioning using Qwen-VL, Gemma4 and SAM3.