Starred repositories
Voxel sandbox game with a large render distance, procedurally generated content and some cool graphical effects.
A curated list of high-signal analyses, design notes, and discussions emerging from the Claude Code leak.
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
a header-only, constexpr alternative to gperf for C++14 users
Simple, secure & standards compliant web server for the most demanding of applications
Cross-platform C++ example for WebGPU and Dawn
Portable Python 3.x Interpreter in Modern C for Game Scripting
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Dev repo for @zig-gamedev libs and sample applications
Self-contained, minimalistic implementation of diffusion models with Pytorch.
AIGC, Pixelization, Pixel Art, SIGGRAPH ASIA 🌠 If you like this work~ 🌠
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
Reformer, the efficient Transformer, in Pytorch
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch
The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Dagor Engine and Tools source code from Gaijin Games KFT
Training small GPT-2 style models using Kolmogorov-Arnold networks.
A Variational Autoencoder in PyTorch for the CelebA Dataset.
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level