Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Code repository for my book, Coding for (Computational) Engineers

implementation of Weight-sparse transformers have interpretable circuits for PPO algorithm https://cdn.openai.com/pdf/41df8f28-d4ef-43e9-aed2-823f9393e470/circuit-sparsity-paper.pdf

Algorithm powering the For You feed on X

bevy gaussian splatting render pipeline plugin

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode & Gemini CLI.

Embeddable library or single binary for indexing and searching 1B vectors

Experimental new browser engine

PicoGK is a compact and robust geometry kernel for Computational Engineering

Customized version of the Linux kernel maintained by Armbian team to support Rockchip SoCs

A refreshingly simple data-driven game engine built in Rust

CLI and C library for processing triangulated solid meshes

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

Python Wrapper for MeshFix: easily repair holes in surface meshes

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Official Implementation of NeuralSound and DeepModal

Native and Compact Structured Latents for 3D Generation

PC Software for BambuLab and other 3D printers

Mastering Diverse Domains through World Models

Fast Tetrahedral Meshing in the Wild

Run frontier AI locally.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Cambrian-S: Towards Spatial Supersensing in Video

LLM inference in C/C++

A local macOS setup for LoRA fine-tuning Gemma 3n in chat format — minimal overhead, optimized for Metal Performance Shaders.