LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

vLLM + Qwen3.5-122B-A10B-NVFP4 on NVIDIA DGX Spark (GB10/SM121) — single-GPU NVFP4 W4A4 with MTP speculative decoding, self-contained Docker build

cuTile Rust provides a safe, tile-based kernel programming DSL for the Rust programming language. It features a safe host-side API for passing tensors to asynchronously executed kernel functions.

This comprehensive learning repository is designed to transform software engineers into expert AI kernel developers, focusing on the cutting-edge technologies required for developing high-performan…

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

A library that generates OpenAPI (Swagger) docs from Zod schemas

Custom Elements HMR polyfill

Build Notion-like, Craft-like, Coda-like, Medium-like editors with Yoopta

Docker configuration for running VLLM on dual DGX Sparks

A components library built with Tailwind CSS that works with any web stack.

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

realfft is the most accurate and best "sounding" real FFT/iFFT SIMD vector templated C++ class in existence

FastAPI to serve Qwen-ASR with streaming support. Tested. Benchmarked. Flash Attention 2. Fast & Stable.

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

Java-App for creating and validating Factur-X / ZuGFeRD / X-Rechnung invoices conforming with EU-Norm EN 16931.

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

The Ultimate Express. Fastest http server with full Express compatibility, based on µWebSockets.

A smart source code globber that collects relevant code and puts it into your agent.md: npx update-agents-md

A curated collection of over 600 daily web games.

A modern shell with functional programming synatx.

In fluid dynamics, an eddy is the swirling of a fluid and the reverse current created when the fluid is in a turbulent flow regime.

Self-Hosting Guide. Learn all about locally hosting (on premises & private web servers) and managing software applications by yourself or your organization. Including Cloud, LLMs, WireGuard, Automa…

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

CrisprWhisper for Mac - MLX - inference code and 8b quants

The open source Zapier alternative. Build workflow automation without spending time and money.