YellowKey Bitlocker Bypass Vulnerability

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

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

Claude Code CLI integration for Unreal Engine 5.7 - Get AI coding assistance with built-in UE5.7 documentation context directly in the editor.

LLAMA Turboquant implementation with CUDA support

LLM inference in C/C++

KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.

Open-Source Frontier Voice AI

Python tool for converting files and office documents to Markdown.

Official inference framework for 1-bit LLMs

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

JavaScript in-page GUI agent. Control web interfaces with natural language.

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

LLM inference in C/C++

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

Powerful AI Client

Minimalistic server (written in C) and a python3 client to allow calling native functions on a remote host for automation purposes

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

Python bindings for llama.cpp

AI Agent for testing Android, iOS, and Web apps. Get Started in 5 Minutes. Arbigent's intuitive UI and powerful code interface make it accessible to everyone, while its scenario breakdown feature e…

The open source coding agent.

Let you use your device to turn it into a decrypt iPA bot Telegram.

A file server that supports static serving, uploading, searching, accessing control, webdav...

A high-throughput and memory-efficient inference and serving engine for LLMs

Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)

Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖