A minimalist, terminal-native coding agent written in C.

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

A Call of Duty-quality FPS in Three.js, built from a single prompt.

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

BookSim 2.0

Grid-Free Monte Carlo Solvers for Physics Simulations Involving Partial Differential Equations

Box3D is a 3D physics engine for games

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…

Learn and Master Node.js. V8, libuv, event loop, buffers, streams, async internals, performance, security, deployment, and production architecture.

A modern C standard library

A contact solver for physics-based simulations involving 👚 shells, 🪵 solids, 🪢 rods, 🧱 rigid bodies and ⏳ sand.

Lightweight 3d physics engine for javascript

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…

Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.

Website for Dynamic Programming TextBook

🌱Light and powerful C++ web framework for highly scalable and resource-efficient web application. It's zero-dependency and easy-portable.

Optimizing diffusion for production-ready speeds

Flash Attention in ~100 lines of CUDA (forward pass only)

Code from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch

Machine Learning Engineering Open Book

Dive into CPython internals, trying to illustrate every detail of CPython implementation

Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.

CUDA by Example, written by two senior members of the CUDA software platform team, shows programmers how to employ this new technology. The authors introduce each area of CUDA development through w…

Python bindings for llama.cpp

Minimal Claude Code alternative. Single Python file, zero dependencies, ~250 lines.

A fast communication-overlapping library for tensor/expert parallelism on GPUs.

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local