draw.io is a JavaScript, client-side editor for general diagramming.

Eigent: The World's First Multi-agent Workforce to Unlock Your Exceptional Productivity.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale

Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction

A framework for efficient model inference with omni-modality models

Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?

Using CRDs to manage GPU resources in Kubernetes.

python module to load the mosaic dataset (Lahner et al.)

NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models

Open-source release accompanying Gao et al. 2025

[NeurIPS 2025] BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals

获取微信4.0版本以上数据库密钥和图片密钥的工具 | A tool for obtaining database keys and image keys for WeChat versions 4.0 and above

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

A HTML5 video player with a parser that saves traffic

PyTorch media decoding and encoding

SAM 3D Objects

A character-level language diffusion model trained on Tiny Shakespeare

Three.js-based implementation of 3D Gaussian splatting

✨ An advanced 3D Gaussian Splatting renderer for THREE.js

CUDA accelerated rasterization of gaussian splatting

Wan: Open and Advanced Large-Scale Video Generative Models

💌 Build and send emails using React

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

Contexts Optical Compression

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"