Fast and secure initramfs generator

Build AI agents for your PC

World's first AMD NPU driver for TUXEDO laptops - Enable AI acceleration on Linux

Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.

Production-ready implementation of InvisPose - a revolutionary WiFi-based dense human pose estimation system that enables real-time full-body tracking through walls using commodity mesh routers

Secure and fast microVMs for serverless computing.

Extract any website’s design system into tokens in seconds: logo, colors, typography, borders & more. One command.

Soho vibes for Wallpapers

AMD APU compatible Ollama. Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

☄🌌️ The minimal, blazing-fast, and infinitely customizable prompt for any shell!

A Zsh theme

Voronoi / Delaunay tessellations on the sphere

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

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Port of OpenAI's Whisper model in C/C++

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Hierarchical Reasoning Model Official Release

Pybind11 bindings for Whisper.cpp

Robust Speech Recognition via Large-Scale Weak Supervision

minimal, multi-process, super fast http server written in assembly

Towards Human-Sounding Speech

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

WAHA - WhatsApp HTTP API (REST API) that you can configure in a click! 3 engines: WEBJS (browser based), NOWEB (websocket nodejs), GOWS (websocket go)

Text-audio foundation model from Boson AI

Beautiful, Modern & Opinionated Linux

We write your reusable computer vision tools. 💜

PlayStation 4 emulator for Windows, Linux and macOS written in C++

Federated Query Engine for AI - The only MCP Server you'll ever need

An optimal MAPF sovler: CBS+prioritizing conflicts+bypassing+high-level heuritstics+symmetry reasoning