zjucat

multica. The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

awesome-design-md. A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.

gbro-collage-broll. 半调纸拼贴 B-roll 生成 skill：三闸门审批，Gemini Omni Flash 首尾帧组装动画 | Editorial halftone paper-collage B-roll agent skill

makelive. Create Live Photos from a photo+video pair compatible with Apple Photos

auto-motion. Automated SRT-to-motion workflow with Codex cli + Claude Code with any LLM

particles.js. A lightweight JavaScript library for creating particles

codex-trace. OpenAI Codex CLI session log viewer for JSONL files in ~/.codex/sessions. Browse conversations, tool calls, tokens, collaboration chains, and live sessions on desktop and web.

LLaVA-OneVision-2. Fully Open Framework for Democratized Multimodal Training

video-use. Edit videos with coding agents

Spatial-TTT. [ECCV 2026] Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Awesome-Incremental-Learning. Awesome Incremental Learning

phosphene. Local generative video panel for Apple Silicon. Wraps LTX-2 MLX, joint audio+video, one-click Pinokio install.

LTX-2. Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

DeepInterestNetwork. Python

Llama-3.1-Centaur-70B. Python

ai4animationpy. A Python framework for AI-driven character animation using neural networks.

JoltPhysics. A multi core friendly rigid body physics and collision detection library. Written in C++. Suitable for games and VR applications. Used by Horizon Forbidden West and Death Stranding 2.

GameplayFootball. Football game, discontinued

football. Check out the new game server:

chrome-ui. Chrome browser UI built with web technologies

clawd-on-desk. A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents — so you don't have to.

ProjectGibbon. C#

synthcity. An Infinite Procedural Cyberpunk City

collective_motion_actinf. Code for simulating collective motion from groups of continuous-time and -space active inference agents.

Geographical-Adventures. C#

three-flow-ts. Diagramming library for adding to a threejs scene

The-Great-Wall-of-China-geodata. This repository introduces the coordinates of direction and passes of the Great Wall of China

threejs-earth. A scene containing a lovely multi-layered model of the earth

m_flow. A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

3d-force-graph. 3D force-directed graph component using ThreeJS/WebGL

my-room-in-3d. JavaScript

drei. 🥉 useful helpers for react-three-fiber

Code2Video. [ICML 2026] Video generation via code

recharts. Redefined chart library built with React and D3

create-vibe-motion. Vibe Motion scaffolding monorepo

git-city. Your GitHub profile as a 3D pixel art building in an interactive city

vibe-motion.github.io. Vibe Motion Official Website

skills. agent skills for vibe motion

perfect-freehand. Draw perfect pressure-sensitive freehand lines.

excalidraw. Virtual whiteboard for sketching hand-drawn like diagrams

claude-code-telegram. A powerful Telegram bot that provides remote access to Claude Code, enabling developers to interact with their projects from anywhere with full AI assistance and session persistence.

python-telegram-bot. We have made you a wrapper you can't refuse

manim. A community-maintained Python framework for creating mathematical animations.

claude-code-playwright-mcp-test. A YAML-based Playwright MCP automation testing framework designed for Claude Code

rive-ios. iOS runtime for Rive

dotlottie-ios. Official Lottie & dotLottie player for iOS, macOS, tvOS, watchOS & visionOS — SwiftUI & UIKit, Rust-powered core.

Alamofire. Elegant HTTP Networking in Swift

LivePhoto. A single-file library for working with Apple Live Photos

DiffSinger. DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

DDSP-SVC. Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

so-vits-svc-Deployment-Documents. So-VITS-SVC 本地部署使用帮助文档，提供Colab笔记本 So-VITS-SVC Local Deployment Document and provide Colab notebook

robo-gym. An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.

sapiens. High-resolution models for human tasks.

WatermarkRemover. 批量去除视频中位置固定的水印

rocket. ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels

pycatch22. python implementation of catch22

catch22. catch22: CAnonical Time-series CHaracteristics

GENDIS. Contains an implementation (sklearn API) of the algorithm proposed in "GENDIS: GEnetic DIscovery of Shapelets" and code to reproduce all experiments.

draft-js. A React framework for building text editors.

piecewise. ## Auto-archived due to inactivity. ## Functions for piecewise regression on time series data

tsrpc-examples. JavaScript

zvt. modular quant framework.

cocos-example-cartoon-vegetation. TypeScript

blivedm. 获取bilibili直播弹幕，使用WebSocket协议，支持web端和B站直播开放平台两种接口

LockStepH5. H5 帧同步小游戏

cocos-example-marionette. This project is to demonstrate the use of Cocos Creator Marionette animation system.

aiohttp. Asynchronous HTTP client/server framework for asyncio and Python

cocos-example-ball. A jumping ball demo created by Cocos Creator 3D

socket.io-unity. socket.io client for Unity, power game client with node.js back-end

weui. A UI library by WeChat official design team, includes the most useful widgets/modules in mobile web applications.

react-touch-carousel. Ultra-customizable carousel framework for React.JS

Semantic-UI. Semantic is a UI component framework based around useful principles from natural language.

react-chat-engine. React component for a cheap and easy chat API

samples. WebRTC Web demos and samples

RTCMultiConnection. RTCMultiConnection is a WebRTC JavaScript library for peer-to-peer applications (screen sharing, audio/video conferencing, file sharing, media streaming etc.)

jQuery.Keyframes. jQuery-Keyframes allows dynamic generation of CSS3 keyframes with callback events and other niceness.

spy-debugger. 微信调试，各种WebView样式调试、手机浏览器的页面真机调试。便捷的远程调试手机页面、抓包工具，支持：HTTP/HTTPS，无需USB连接设备。

ParrelSync. (Unity3D) Test multiplayer without building

pyAudioAnalysis. Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

uni-app. A cross-platform framework using Vue.js

forced-alignment-tools. A collection of links and notes on forced alignment tools

ms-tcn. Python

VideoPose3D. Efficient 3D human pose estimation in video using 2D keypoint trajectories

detectron2. detectron2 windows build

frankmocap. A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

coral-cnn. Rank Consistent Ordinal Regression for Neural Networks with Application to Age Estimation

3DMPPE_POSENET_RELEASE. Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

hand3d. Network estimating 3D Handpose from single color images

hand-graph-cnn. 3D Hand Shape and Pose Estimation from a Single RGB Image

MeshTransformer. Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"

awesome-hand-pose-estimation. Awesome work on hand pose estimation/tracking

bmc_hand_pose.

3dhand. Python

MegaTrack-pytorch. Facebook Oculus Quest Hand Detection&Pose Estimation System

imgclsmob. Sandbox for training deep learning networks

STM. Video Object Segmentation using Space-Time Memory Networks

tensorflow-windows-wheel. Tensorflow prebuilt binary for Windows

deep-voice-conversion. Deep neural networks for voice conversion (voice style transfer) in Tensorflow

face3d. Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.

tutorials. Tutorials for creating and using ONNX models

iOS-DeviceSupport. This repository holds the device support files for the iOS, and I will update it regularly.

CharacterLipSync. Real-Time Lip Sync for Live 2D Animation

DeepSpeech. DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

WebRTC-iOS. A simple native WebRTC demo iOS app using swift

regression-losses-pytorch. Experimenting with different regression losses. Implemented in Pytorch.

ijkplayer. Android/iOS video player based on FFmpeg n3.4, with MediaCodec, VideoToolbox support.

the-example-app.swift. Example app for Contentful in Swift

awesome-data-augmentation. This is a list of awesome methods about data augmentation.

pytorch_HMR. pytorch version of "End-to-end Recovery of Human Shape and Pose"

human_body_prior. VPoser: Variational Human Pose Prior

towr. A light-weight, Eigen-based C++ library for trajectory optimization for legged robots.

onnx. Open standard for machine learning interoperability

OpenSeeFace. Robust realtime face and facial landmark tracking on CPU with Unity integration

contact-human-dynamics. Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".

Live2d-model. Live2d model collection

UnityLive2DExtractor. Unity Live2D Cubism 3 Extractor

TNN. TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

sporco. Sparse Optimisation Research Code

DECA. DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

dlib-models. Trained model files for dlib example programs.

cvxpylayers. Differentiable convex optimization layers

supervision-by-registration. Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

pytorch_face_landmark. Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100 FPS landmark inference speed with SOTA face detector on CPU.

faster-rcnn.pytorch. A faster pytorch implementation of faster r-cnn

landmark-detection. Four landmark detection algorithms, implemented in PyTorch.

pytorch3d. PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

face-alignment. :fire: 2D and 3D Face alignment library build using pytorch

cvpr2018nkn. Tensorflow implementation of the CVPR 2018 paper: Neural Kinematic Networks for Unsupervised Motion Retargetting

MotioNet. A deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video [ToG 2020]

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

Skeleton_Aware_Networks_for_Deep_Motion_Retargeting. Reproduce the work of the paper "Skeleton-Aware Networks for Deep Motion Retargeting" in Pytorch

character-motion-vaes. Character Controllers using Motion VAEs

learnable-triangulation-pytorch. This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!

deformation-transfer. An implementation of Deformation Transfer algorithm in ANSI C

FLAME_PyTorch. This is a implementation of the 3D FLAME model in PyTorch

mediapipeFacegeometryPython. Jupyter Notebook

blenderStatisticalModeling. python implementation of basic Gaussian Process Morphable Models

TimeSformer-pytorch. Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

AWESOME-FER. Top conferences & Journals focused on Facial expression recognition (FER)/ Facial action unit (FAU)

PRNet. Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)

Deep3DFaceReconstruction. Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)

3DFace. This repository contains the dataset including the pair of 2D face image and its corresponding 3D face geometry model.

eos. A lightweight 3D Morphable Face Model library in modern C++

conv_arithmetic. A technical report on convolution arithmetic in the context of deep learning

AI4Animation. Bringing Characters to Life with Computer Brains in Unity

ml-agents. The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

ActiveRagdollStyleTransfer. Research into locomotion style transfer with Active Ragdolls (using MarathonEnvs +ml_agents)

hmr. Project page for End-to-end Recovery of Human Shape and Pose

motion_reconstruction. Motion Reconstruction Code and Data for Skills from Videos (SFV)

RP. a custom render pipline of unity

Seal3Dprint. C#

UnityOnline. Unity online game demo