A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Eigent: The Open Source Cowork Desktop to Unlock Your Exceptional Productivity.

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

A Python package for calling Slang modules from PyTorch.

[SIGGRAPH Asia 2025] OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion

Hunyuan 3D Part Segmentation and Generation Pipeline

[ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"

Generate OpenPGP keys with fingerprints that match a specific pattern (a.k.a. vanity keys)

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

The best way to learn from long videos

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

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)

An experimental 3D Gaussian Splat viewer written in Rust (CPU rendering)

A set of coding style guidelines for Vibe Coding or SWE-Agents that maximize efficiency and improve human readability.

美国华人技术创业的快速公司/银行/税务/投资操作白皮书

Build 3D Gaussian Splatting from scratch with NVIDIA Warp in Python — CPU/GPU compatible, with a clean and minimalist design focused on learning modern graphics.

(WIP) Open-source Rust gate-level EDA infrastructure: parsers and databases

📦 Plugin, App, and Theme store which includes plugin injection for macOS

Unofficial Implementation of Animate Anyone by Novita AI

Mattermost is an open source platform for secure collaboration across the entire software development lifecycle..

Official implementation of AnimateDiff.

Chrome extension for recording your test run!

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

Intent-based UI automation that runs locally. Record real workflows, generate reusable scripts, and safely use local credentials and files.

A high-throughput and memory-efficient inference and serving engine for LLMs