Robyn is a Super Fast Async Python Web Framework with a Rust runtime.

Generate a pixel art style profile card from your GitHub data! ✨

Collections of awesome neovim plugins.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Claude Code without any telemetry - the perfect cli to combo with CCR

OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.

A curated list of Best Artificial Intelligence Resources

TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration

From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.

A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.

Learn it. Build it. Ship it for others.

Beginner, advanced, expert level Rust training material

A Claude Code skill that turns any codebase into a beautiful, interactive single-page HTML course for non-technical vibe coders.

AI Flipper control

Collabora Online is a collaborative online office suite based on LibreOffice technology. This is also the source for the Collabora Office apps for iOS and Android.

An end-to-end machine learning pipeline and ensemble solution for the DataOrg Financial Health Prediction Challenge on Zindi.

LLM Architecture Gallery source data

Human brain cells play Doom (CL1)

Simple Online Realtime Tracking with a Deep Association Metric

Public repository for Agent Skills

My full Windows 11 setup — from YASB bar to tiny tweaks. Fonts, mods, configs, and guides, all in one repo.

Algorithm powering the For You feed on X

🎵 Search Spotify and download music from YouTube to your Navidrome server with automatic metadata tagging

An extendable async API using FastAPI, Pydantic V2, SQLAlchemy 2.0, PostgreSQL and Redis.

Full-stack AI app generator — FastAPI + Next.js with agents, RAG, streaming, auth, and 20+ integrations out of the box.

Make beautiful isometric infrastructure diagrams

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.