GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

LLM inference in C/C++

Distribute and run LLMs with a single file.

MLX: An array framework for Apple silicon

Control WS2812B and many more types of digital RGB LEDs with an ESP8266 or ESP32 over WiFi!

Development repository for the Triton language and compiler

Unsupervised text tokenizer for Neural Network-based text generation.

lightweight, standalone C++ inference engine for Google's Gemma models.

Udacity Self-Driving Car Engineer Nanodegree projects.

HomeKit Library for the Arduino-ESP32

Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)

Efficient framework-agnostic data loading

C++ sudoku game

Holiday Light Strand with Special Effects

Demonstrates how to add a Web Server alongside HomeSpan to create a Programmable Hub