Wenrui

open-saas. A 100% free modern JS SaaS boilerplate (React, NodeJS, Prisma). Full-featured: Auth (email, google, github, slack, MS), Email sending, Background jobs, Landing page, Payments (Stripe, Polar.sh), Shadcn UI, S3 file upload. AI-ready with tailored AGENTS.md, skills, and Claude Code plugin. One cmd deploy. Powered by Wasp full-stack framework.

DiffuEraser. DiffuEraser is a diffusion model for video inpainting, which performs great content completeness and temporal consistency while maintaining acceptable efficiency.

dexjoco. Python

svor. SVOR - Stable Video Object Removal

HumanNet. HumanNet: Scaling Human-centric Video Learning to One Million Hours

EgoForce. [SIGGRAPH 2026] Official implementation for "EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera"

Mitty. Official code implementation of "Mitty: Diffusion-based Human-to-Robot Video Generation"

ProPainter-Webui. A webui for propainter. Easily pick up objects from the video and eliminate them.

hand-tracking-streamer. Meta Quest VR App for tracking and streaming hand and wrist landmark telemetry.

beavr-bot. Bimanual, multi-Embodiment, Accessible, Virtual Reality Teleoperation System for Robots

HumanEgo. HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos

GraspGenX. Code Release for GraspGenX

gmr-motionlab. An extended GMR toolkit for humanoid motion retargeting, pkl motion visualization/editing, and motion segmentation.

ConTrack. [ECCV 2026] ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control

humanoid-retarget. Retargeting motion from human to humanoid robots.

TeleVision. [CoRL 2024] Open-TeleVision: Teleoperation with Immersive Active Visual Feedback

hommi. [RSS'26] HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

H2R-Aug. Python

moveit. :robot: The MoveIt motion planning framework

xr_teleoperate. This repository implements teleoperation of the Unitree humanoid robot using XR Devices.

GeoRT. Geometric Retargeting A Principled, Ultrafast Neural Hand Retargeting Algorithm

universal_manipulation_interface. Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

MakeTrackingEasy. Python

GENMO. Python

CARI4D. [CVPR 2026] CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction

mjswan. MuJoco Simulation on Web Assembly with Neural netwroks

MimicKit. A lightweight suite of motion imitation methods for training controllers.

DART. Code release for the paper "DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control"

PARC. PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers

pink. Python inverse kinematics using Pinocchio and QP solvers

twist2_mjlab. Python

UnrealRoboticsLab. A high-fidelity, open-source robotics simulator integrating Unreal Engine's photorealistic rendering with MuJoCo's precision physics.

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

waoowaoo. 首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.

FlowMDM. [CVPR 2024] Official Implementation of "Seamless Human Motion Composition with Blended Positional Encodings".

DiffuseLoco. Source code for the paper DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets

FMPose3D. A monocular 3D pose estimation algorithm for humans and other animals

GlobalPose. 3D-space human motion capture from 6 IMUs built upon TransPose, PIP, and PNP

soma-retargeter. SOMA BVH to humanoid robot motion retargeting library built with Newton and NVIDIA Warp

OmniClone. Python

kimodo. Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

seed-viewer. A web application for browsing and viewing the BONES-SEED motion capture dataset

Motion_Editor. TypeScript

ACoT-VLA. [CVPR 2026] Official implementation of "ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models"

SMPL-to-FBX. Load SMPL in blender

CLOT. official code for paper CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation

brs-algo. Official Algorithm Codebase for the Paper "BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities"

loco-mujoco. Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

dexbotic. Dexbotic: Open-Source Vision-Language-Action Toolbox

DeepMimic_mujoco. DeepMimic Mujoco version; Python only; No Bullet, No C++

DexGraspNet. Python

RynnBrain. RynnBrain: Open Embodied Foundation Models

DreamDojo. Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)

GR00T-WholeBodyControl. Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC

AMO. [RSS 2025] AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control

Awesome-Embodied-AI-Robot. 🤖 RoboLLM Hub | A curated collection of embodied AI and robot learning resources.具身智能与机器人学习资源集合，包含最新论文、代码与工具。👉

Genesis-Humanoid. An all-in-one humanoid research platform on top of Genesis.

Ego-VCP. Ego-Vision World Model for Humanoid Contact Planning

gvhmr_gmr_beyondmimic. Training scripts combining HVGMR, GMR, and Beyondmimic

PhysHSI. Official implementation of the paper: "PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System"

Lumina-mGPT. Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining"

Paper2Code. Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

robot-motion-editor. A web-based tool that edits the robot motion file in instinctlab ecosystem

InstinctLab. Python

WholebodyVLA. [ICLR 2026] Towards Unified Latent VLA for Whole-body Loco-manipulation Control

awesome-embodied-vla-va-vln. A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

GR00T-Dreams. DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models

awesome-bfm-papers. A curated list of behavior(al) foundation model (BFM) papers, articles, tutorials, slides, and projects

awesome-human-motion. 🏃‍♀️ A curated list about human motion capture, analysis and synthesis.

Awesome-Trajectory-Motion-Prediction-Papers.

urdf_importer. Add-on for Blender, provides importing robots from URDF format

Action100M. A Large-scale Video Action Dataset

Gen2Humanoid. Python

whole_body_tracking. Python

Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

viser. Web-based 3D visualization in Python

UniAct. [CVPR 2025] The offical Implementation of "Universal Actions for Enhanced Embodied Foundation Models"

HumanMM-code. [CVPR 2025] HumanMM: Global Human Motion Recovery from Multi-shot Videos

spider. A general physic-based retargeting framework.

urdf-loaders. URDF Loaders for Unity and THREE.js with example ATHLETE URDF Files open sourced from NASA JPL

HumanoidVerse. Python

LaserGRBL. Laser optimized GUI for GRBL

HMD-Poser. Python

spider. A general physic-based retargeting framework.

TWIST2. [arXiv 2025] TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System

newton. An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

FluxWeave. Urdf tool

Awesome-Video-Datasets. Video datasets

OakInk2. 🌴[CVPR 2024] OakInk2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion

matrix. MATRiX is an advanced simulation platform that integrates MuJoCo, Unreal Engine 5, and CARLA to provide high-fidelity, interactive environments for robotics research.

ProtoMotions. ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

HoloMotion. HoloMotion: A Foundation Model for Whole-Body Humanoid Control

InternHumanoid. A versatile, all-in-one toolbox for whole-body humanoid robot control.

locoformer. LocoFormer - Generalist Locomotion via Long-Context Adaptation

RoboPhD. A curated collection of papers, seminars, courses, and technical resources for robotic research.

humanoid-general-motion-tracking. The official codebase of paper "GMT: General Motion Tracking for Humanoid Whole-Body Control"

XGO-Rider. The XGO-Rider is a desktop-sized, dual-wheeled, bipedal robot based on the micro:bit platform. It uses 4.5KG.CM all-metal servos and FOC wheel hub motors for omnidirectional movement and stability. Equipped with an IMU for advanced algorithms and secondary development, it supports graphical programming.

unifolm-world-model-action. Python

omomo_release. Official Implementation of the Paper: Object Motion Guided Human Motion Synthesis (SIGGRAPH Asia 2023 (TOG))

TokenHSI. [CVPR 2025 Oral] TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

InterMimic. [CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions

StableMotion. [SIGGRAPH Asia 2025] Implementation of "StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data"

deep-motion-editing. An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]

Fabrik-Inverse-kinematics. A very simple implementation of the Fabrik inverse kinematics algorithm. Useful for games and animations.

fabric-fabrik-fullbody-ik. Fabric Engine Canvas tool for full-body IK system, based on FABRIK (Forward And Backward Reaching Inverse Kinematics)

DigitRobot.jl. URDF and Meshes for the Agility Robotics Digit Robot

graphtransformer. Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to Graphs", DLG-AAAI'21.

PHC. Official Implementation of the ICCV 2023 paper: Perpetual Humanoid Control for Real-time Simulated Avatars

RSMT-Realtime-Stylized-Motion-Transition. The official repository for the paper "RSMT: Real-time Stylized Motion Transition for Characters".

PMG. Python

LGTM. Jupyter Notebook

ReMoMask. [ECCV 2026] ReMoMask: Retrieval-Augmented Masked Motion Generation

EmLoco. [CVPR2025] Official PyTorch implimentation for "Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment"

diffusion-motion-inbetweening. The official implementation of Flexible Motion In-betweening with Diffusion Models, SIGGRAPH 2024

Robust-Motion-In-betweening. 📖 Paper: Robust Motion In-betweening 🏃

awesome-humanoid-robot-learning. A Paper List for Humanoid Robot Learning.

Control-VAE. C++

expressive-humanoid. [RSS 2024]: Expressive Whole-Body Control for Humanoid Robots

momask-codes. Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions (CVPR2024)"

MoConVQ. C++

ARP-Batch-Retargeting. Personal pipeline for batch retargeting kinematic motions (BVH) between different skeletons with the help of Auto-Rig Pro in Blender.

DeepMimic. Motion imitation with deep reinforcement learning.

rapid-locomotion-rl. Code for Rapid Locomotion via Reinforcement Learning

mocap_retarget. mocap_retarget

dex-retargeting. Various retargeting optimizers to translate human hand motion to robot hand motion.

MotionLab. [ICCV 2025] The official implementation of MotionLab

PFNN. Phase-Functioned Neural Networks for Character Control

marathon-envs. A set of high-dimensional continuous control environments for use with Unity ML-Agents Toolkit.

AI4Animation. Bringing Characters to Life with Computer Brains in Unity

character-motion-vaes. Character Controllers using Motion VAEs

AGRoL. Code release for "Avatars Grow Legs Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model", CVPR 2023

motion-diffusion-model. The official PyTorch implementation of the paper "Human Motion Diffusion Model"

EasyMocap. Make human motion capture easier.

BillionMail. BillionMail gives you open-source MailServer, NewsLetter, Email Marketing — fully self-hosted, dev-friendly, and free from monthly fees. Join the discord: https://discord.gg/asfXzBUhZr

Resume-Matcher. The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.

MediaCrawler. 小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

social_media_app. Build a modern social app with a stunning UI with a native mobile feel, a special tech stack, an infinite scroll feature, and amazing performance using React JS, Appwrite, TypeScript, and more.

star-vector. StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

awesome-LLM-game-agent-papers. A Survey on Large Language Model-Based Game Agents (ACM CSUR)

StdGEN. [CVPR 2025] StdGEN: Semantic-Decomposed 3D Character Generation from Single Images

DeepSeek-V3. Python

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

Unreal-Movement. Body, Eye and Face Tracking code sample.

CLoSD. CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

XCharacter-UEPlugin. XVERSE Character UE plugin (XCharacter-UEPlugin) a 3D digital human creation plugin for Unreal Engine 5, developed by XVERSE Technology Inc. (Zhenshen, China).

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

ChatGPT-Web. 使用GPT-3.5 API创建的ChatGPT聊天页面，支持云部署，多用户使用，多对话管理，公式显示，流式动态显示，windows和linux均可极简部署，网页版 html python flask

kool. A Vulkan / WebGPU / OpenGL engine for Desktop JVM, Android and Javascript written in Kotlin

t5c. Building a open source multiplayer 3d rpg using babylon.js and colyseus

noa. Experimental voxel game engine.

Babylon.js. Babylon.js is a powerful, beautiful, simple, and open game and rendering engine packed into a friendly JavaScript framework.

first-order-model. This repository contains the source code for the paper First Order Motion Model for Image Animation

darknet. YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

arfoundation-samples. Example content for Unity projects based on AR Foundation

VR-Observatory. Building a VR observatory for Giant Magellan Telescope

Deep-Image-Matting. Deep Image Matting

MachineLearning_Python. 机器学习算法python实现

JS-Sorting-Algorithm. 一本关于排序算法的 GitBook 在线书籍 《十大经典排序算法》，多语言实现。

pytorch-book. PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

dacemo. Data Centric Modelling Ontologies, tools and documentation

d3-force. Force-directed graph layout using velocity Verlet integration.