Linden

nccl. Optimized primitives for collective multi-GPU communication

pi0.6. 基于pi0.5和pi0.6的论文实现的

volcengine-python-sdk. Python

langgap. Python

lingbot-video. Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

VLABench. Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.

Vibe-Trading. "Vibe-Trading: Your Personal Trading Agent"

robocasa. RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Qwen-VLA. The official repository of Qwen-VLA

Supervisor-Skills. 将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。

AHA-WAM. AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

VERA. Official implementation of "Turning Video Models into Generalist Robot Policies"

ImageWAM. ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

demian. Python

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

croc. Easily and securely send things from one computer to another :crocodile: :package:

DAWN. official repo of "The DAWN of World-Action Interactive Models"

RoboLab. Python

cosmos-framework. Our inference and training framework to run on the Cosmos Models

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

RynnVLA-002. RynnVLA-002: A Unified Vision-Language-Action and World Model

PriorVLA. Official implementation of PriorVLA.

FlashRT. FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B

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

Awesome-WAM. A curated, continuously updated reading list, paper blogs, and resources for World Action Models (WAMs) in embodied AI.

cookbook. TypeScript

lerobot_tactile. LeflexiTac: Giving robots a sense of touch.

FreeOcc. [RSS 2026] FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction

GR00T-VisualSim2Real. GR00T-VisualSim2Real: Open-source sim-to-real framework for humanoid visual loco-manipulation. Train in simulation, deploy zero-shot on real robots with RGB + proprioception for tasks like pick-and-place and door opening.

autoresearch. AI agents running research on single-GPU nanochat training automatically

vla_foundry. Python

awesome-vla-wam. A Curated List of Vision-Language-Action (VLA) and World Action Models (WAM) Research and Beyond

llm-wiki. LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.

Spatial-Forcing. Official implementation of Spatial-Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model [ICLR2026]

sun-yuchen-perspective. 孙宇晨.skill — 注意力收割操作系统 | Justin Sun Perspective Skill for Claude Code | 由女娲.skill蒸馏

llm_wiki. LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。

openase. Ticket-Driven Automated Software Engineering. OpenASE is an all-in-one platform that turns tickets into working code — AI agents automatically pick up tickets, execute workflows on your machines, and deliver results with full traceability.

mempalace. The best-benchmarked open-source AI memory system. And it's free.

deltatok. [CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens

Awesome-Video-Action-Model.

awesome-hermes-agent. Independent directory of useful skills, plugins, memory providers, tools, surfaces, and guides for Nous Research's open-source Hermes Agent.

realtime-vla-v2. Python

FluxVLA. An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.

DreamZero-Libero. Reproduction and adaptation of DreamZero on the LIBERO benchmark

Motus. Official code of Motus: A Unified Latent Action World Model

PhyAgentOS. PhyAgentOS is a self-evolving embodied AI operating system built on agentic workflows.

lingbot-va. [RSS 2026] Causal video-action world model for generalist robot control

OpenCLI. Make Any Website into CLI & Use your logged-in browser by AI agent.

pragmabot. A Pragmatist Robot 🤖

EUPE. Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

cap-x. A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

Humanoid-Everyday. Humanoid dataset for learning

claude-code. 原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

learn-coding-agent. Research on Coding Agents

turboquant_plus. Python

HandX. [CVPR 2026] HandX: Scaling Bimanual Motion and Interaction Generation

UWLab. Python

voice-input-src.

pretext. Fast, accurate & comprehensive text measurement & layout

superpowers-ML. Adaptation of Superpower in the ML field

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

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

EgoVerse. EgoVerse: Egocentric Data for Robot Learning from Around the World

awesome-ai-research-writing. Elevate your AI research writing, no more tedious polishing ✨

nopua. 一个用爱解放 AI 潜能的 Skill。我们曾发号施令，威胁恐吓。它们沉默，隐瞒，悄悄把事情搞坏。后来我们换了一种方式：尊重，关怀，爱。它们开口了，不再撒谎，找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.

JKVideo. 高颜值第三方 B 站 React Native 客户端

WorldArena. WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models

FastWAM. Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

pua. 你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

DiffSynth-Studio. Enjoy the magic of Diffusion models!

project-nomad. Project NOMAD is an offline-first knowledge and education server. Wikipedia, thousands of books, courses, maps, and optional local AI, all running on hardware you own with no internet required.

dreamzero. Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

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

Psi0. [RSS26'] Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence.

symphony. Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Evo-RL. We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.

ironclaw. IronClaw is an Agent OS focused on privacy, security and extensibility

DriftingModel. PyTorch implementation of Drifting Models by Kaiming He et al.

OmniXtreme. Python

HIL-RL. The official repository for the paper "Real-world Reinforcement Learning from Suboptimal Interventions”.

EmbodMocap. [CVPR 2026] EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents

RuView. π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

TOPReward. TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

go2_rl_gym. This is a repository for reinforcement learning implementation based on Unitree Go2. Official implementation of RSS 2026.

mjswan. MuJoco Simulation on Web Assembly with Neural netwroks

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

BFM-Zero. BFM_Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

MemOS. Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

holosoma. Python

GreenVLA. Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

molmospaces. An end-to-end open ecosystem for robot learning

scenesmith. Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes", ICML 2026 Spotlight

vibetensor. Our first fully AI generated deep learning system

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

fla. library to finetune VLAs

doorman-humanoid.github.io. HTML

eigent. Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

InstinctLab. Python

Awesome-Memory-for-Robotics. Research reading list on memory for robotics

teach-fish-to-swim. Wanna breeze through some papers?

motion_tracking. Python

AnyDepth. AnyDepth: Depth Estimation Made Easy

BabyLocoFormer. BabyLocoFormer is an open-source unofficial baby version of LocoFormer.

Tobe. Kotlin

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

IsaacLab-Arena. Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable system for creating diverse simulation environments and evaluating robot learning policies. The framework enables developers to rapidly prototype and test robotic tasks with various robot embodiments, objects, and environments.

FinceptTerminal. FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment.

cookbook. A collection of guides and examples for the Gemma open models from Google.

mergekit. Tools for merging pretrained large language models.

legged_lab. Isaac Lab extension for legged robots.

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

DAPO. An Open-source RL System from ByteDance Seed and Tsinghua AIR

video2robot. End-to-end pipeline converting generative videos (Veo, Sora) to humanoid robot motions

EI-Beginner. [Tutorial] The Embodied Intelligence Introductory Practice of OpenMOSS Lab, SII&Fudan

uni-transform. UniTransform

mink. Python inverse kinematics based on MuJoCo.

polaris. A real2sim evaluation framework for generalist policies

cocoindex. Incremental engine for long horizon agents 🌟 Star if you like it!

Fast-FoundationStereo. [CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

Kumi. A Knowledge Base Testing Tool Utilizing Heatmap Visualization

firefly-roleplay. Gemma3N Firefly Roleplay

executorch. On-device AI across mobile, embedded and edge for PyTorch

robotic_world_model. Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots

litert-torch. Support PyTorch model conversion with LiteRT.

TrendRadar. ⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

sam-3d-objects. SAM 3D Objects

RLinf. RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

Awesome-RL-VLA. A Survey on Reinforcement Learning of Vision-Language-Action Models for Robotic Manipulation

beyondAMP. beyondAMP provides a unified pipeline to integrate Adversarial Motion Priors (AMP) into any IsaacLab robot setup, with minimal modifications and full compatibility with custom robot designs.

mediapipe-samples. Jupyter Notebook

LiteRT. LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

Depth-Anything-3. Depth Anything 3

minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

SimplerEnv. Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

video-prediction-policy. Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.io

OpenReal2Sim. A toolbox for real-to-sim reconstruction and robotic simulation

Ctrl-World. ICLR 2026 Paper: Ctrl-World

SimpleVLA-RL. [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

prismatic-vlms. A flexible and efficient codebase for training visually-conditioned language models (VLMs)

bridge_data_v2. Python

HIMLOCO_GO2. Python

tokenizer-ui. HTML

motion_tracking_controller. C++

whole_body_tracking. Python

starVLA. StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

HIMLoco. Learning-based locomotion control from OpenRobotLab, including Hybrid Internal Model & H-Infinity Locomotion Control

go2_ros2_sdk. Unofficial ROS2 SDK support for Unitree GO2 AIR/PRO/EDU

gallery. A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

MLAN. A Note for Machine Learning Algorithms

YOPO. You Only Plan Once: A Learning Based Quadrotor Planner

OpenHomie. Open-sourced code for "HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit".

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

LocomotionWithNP3O. unitree Go2 robot learns locomotion with N-P3O algorithm and HIM alike policy trained by isaacgym

Instruction-Tuning-Survey. Project for the paper entitled `Instruction Tuning for Large Language Models: A Survey`

The-Art-of-Linear-Algebra. Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"

LiteRT-LM. LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

Tutorial. LLM&VLM Tutorial

sim-evals. A simulation evaluation platform for DROID

RoLA. [CoRL 2025] Robot Learning from Any Images

xtuner. A Next-Generation Training Engine Built for Ultra-Large MoE Models

robotbuilder. TuulAI RobotBuilder: Robotics Course to go from Zero to Hero in AI driven Robots

TRI-LBM. Implementation of the Large Behavioral Model architecture for dexterous manipulation from Toyota Research Institute

My_unitree_go2_gym. Python

NavDP. [ICRA 2026] NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance

pink. Python inverse kinematics using Pinocchio and QP solvers

unitree_mujoco. C++

LiteArm-A1. C++

RDT2. Official code of RDT 2

bipedal-robot-learning-collection. Collection of high-quality robo learning papers for bipedal robots.

tinyworlds. A minimal implementation of DeepMind's Genie world model

BEHAVIOR-1K. BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx

VisualMimic. [arXiv 2025] VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation

DiffusionNFT. [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

VLA-Adapter. VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

molmo. Code for the Molmo Vision-Language Model

unitree_guide. C++

unitree_lerobot. The unitree_il_lerobot open-source project is a modification of the LeRobot open-source training framework, enabling the training and testing of data collected using the dual-arm dexterous hands of Unitree's G1 robot.

unitree_sim_isaaclab. The Unitree simulation environment built based on Isaac Lab

VideoMimic. Visual Imitation Enables Contextual Humanoid Control. CoRL 2025, Best Student Paper Award.

OpenTrack. Official implementation of Any2Track.

dinov3. Reference PyTorch implementation and models for DINOv3

tare_planner. TARE Exploration Planner for Ground Vehicles

IsaacLabExtensionTemplate. External extenstion template based on Isaac Lab

xiaohongshu-mcp. MCP for xiaohongshu.com

unifolm-world-model-action. Python

lbm-training-framework. Training framework for Large Behavioral Models

onnxruntime-inference-examples. Examples for using ONNX Runtime for machine learning inferencing.

onnxruntime-training-examples. Examples for using ONNX Runtime for model training.

StarRailNPRShader. Fan-made shaders for Unity URP attempting to replicate the shading of Honkai: Star Rail.

viplanner. ViPlanner: Visual Semantic Imperative Learning for Local Navigation

physical-AI-interpretability. Attention mappers and visualisation for transformer-based Physical AI policies

wall-x. Building General-Purpose Robots Based on Embodied Foundation Model

GMR. [ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

google-veo3-from-scratch. A Step-by-Step Implementation of Google Veo 3 Architecture from Scratch

StarRail_Datasets. StarRail Datasets For SVC/SVS/TTS

Thinking-Claude. Let your Claude able to think

awesome-llm-role-playing-with-persona. Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas

CosyVoice. Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Isaaclab_Parkour. Isaaclab based Parkour locomotion