Quokka is a UCI compatible chess engine rated around 17-1800 ELO

A strong UCI chess engine with a neural network based evaluation.

Library for fast text representation and classification.

Liar's Dice AI in Pytorch: www.dudo.ai

Clustered Compositional Embeddings

Teaching Addition to Small Transformers

The FSRS algorithm in 100 lines of Rust.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Force LLM to talk with the top 1000 words only.

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

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

LLaMA 2-based chat for ultra-low-memory hardware with a 60 MB footprint

Code for minimum-entropy coupling.

Collaborative cheatsheets for console commands 📚.

Pytorch implementation of Hyperspherical Variational Auto-Encoders

matplotlib: plotting with Python

Structured data exports from forensic analysis of the 218GB DOJ Epstein file release — knowledge graph, entity extractions, image catalog, EFTA mapping

Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.

LLM Council works together to answer your hardest questions

AI agents running research on single-GPU nanochat training automatically

Phaser is a fun, free and fast 2D game framework for making HTML5 games for desktop and mobile web browsers, supporting Canvas and WebGL rendering.

🕵🏻 Anonymous network in 100 lines of code

A language to transpile to brainfuck

P523 Code

Essential of Compilation

anti-dpi software

x86-64 assembler library

STOKE: A stochastic superoptimizer and program synthesizer

A superoptimizer for LLVM IR