Better C++ bindings for the OpenCL API

The most atomic way to train and inference a GPT in pure, dependency-free C

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

The Arduino Library Registry

Implementation of C++ standard libraries in C

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

Algorithm powering the For You feed on X

100 days of LLM inference engineering — daily posts, experiments, and visualizations

C++14 lock-free queue.

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

Library for custom colors and dark mode support for most common controls in applications using Win32 API

Redis 6.0.20 6.2.18 7.0.15 7.2.8 7.4.3 8.0.0 for Windows

Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.

Fast and memory-efficient exact attention

Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.

A Transformer Implementation that is easy to understand and customizable.