Repos

The code people actually bring to a reading club

Most clubs let you present a repository instead of a paper, and it is often the better talk, because a repo has to run. 262 robotics and robot-learning repositories, 82 of them pointed at by a paper's own authors or by a club's reading list. Sortable by anything; Age is time since the last push, which is the fastest way to spot a benchmark everyone cites and nobody maintains.

Linked from a paper only

Repository	Creator	What it is	Area	Stars	Language	Age
google-research	Google Research Google DeepMind google-research	Google Research paper		38,627	·	2d
bullet3	Bullet Physics SDK bulletphysics	Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics,	Simulation, sim-to-real & benchmarks	14,700	C++	10mo
carla	CARLA carla-simulator	Open-source simulator for autonomous driving research.	Simulation, sim-to-real & benchmarks Navigation & mobility	14,328	C++	2d
vision_transformer	Google Research Google DeepMind google-research	paper	Foundation models & pretraining	12,683	·	27d
GroundingDINO	IDEA-Research	[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set paper	Foundation models & pretraining	10,517	·	2.0y
IsaacLab	NVIDIA Isaac Sim NVIDIA isaac-sim	Unified framework for robot learning built on NVIDIA Isaac Sim		7,966	Python	2d
ProPainter	Shangchen Zhou person sczhou	[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting paper		6,916	·	1.5y
ml-depth-pro	Apple apple	Depth Pro: Sharp Monocular Metric Depth in Less Than a Second. paper	3D & spatial reasoning Foundation models & pretraining	5,683	·	1.4y
moco	Meta Research Meta FAIR facebookresearch	PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722 paper		5,136	·	7mo
simclr	Google Research Google DeepMind google-research	SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners paper		4,502	·	3.3y
lingbot-world	Robbyant	Advancing Open-source World Models paper	World models	4,393	·	2mo
scenic	Google Research Google DeepMind google-research	Scenic: A Jax Library for Computer Vision Research and Beyond paper		3,821	·	18d
every-embodied	Datawhale datawhalechina	仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0，深入理解具身智能	Vision-language-action	3,359	Python	4d
ManiSkill	ManiSkill mani-skill	Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark	Simulation, sim-to-real & benchmarks	3,264	Python	24d
AgiBot-World	OpenDriveLab	[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent paper	Vision-language-action Foundation models & pretraining	3,157	·	3mo
habitat-lab	Meta Research Meta FAIR facebookresearch	A modular high-level library to train embodied AI agents across a variety of tasks and environments.	Simulation, sim-to-real & benchmarks	3,108	Python	4mo
openarm	Enactic, Inc. enactic	A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.	Humanoids & locomotion Tactile & force sensing	2,889	MDX	8d
mjlab	mujocolab	Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research paper		2,837	·	2d
robosuite	ARISE Initiative ARISE-Initiative	robosuite: A Modular Simulation Framework and Benchmark for Robot Learning	Humanoids & locomotion Simulation, sim-to-real & benchmarks	2,581	Python	2mo
flow_grpo	Jie Liu person yifan123	[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL paper		2,499	·	4mo
VLA-Adapter	OpenHelix Robotics OpenHelix-Team	VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model	Vision-language-action	2,294	Python	5mo
Awesome-World-Model	Xin Zhou person LMD0311	Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.	World models Navigation & mobility	2,225	·	11d
garage	Reinforcement Learning Working Group rlworkgroup	A toolkit for reproducible reinforcement learning research. paper	Reinforcement learning & control	2,126	·	3.3y
humanoid-gym	RobotEra TECHNOLOGY CO.,LTD. roboterax	Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.0569	Humanoids & locomotion Simulation, sim-to-real & benchmarks	2,075	Python	1.6y
alpamayo	NVIDIA Research Projects NVIDIA NVlabs	NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with C	World models Vision-language-action	2,005	Python	23d
mar	Tianhong Li person LTH14	PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838 paper	Video & generative modeling	1,949	·	6mo
Awesome-World-Models	Leo Fan person leofan90	A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, E	World models Navigation & mobility	1,985	Python	2d
Metaworld	Farama Foundation Farama-Foundation	Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning paper	Reinforcement learning & control	1,871	·	18d
ShowUI	Show Lab showlab	[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.	Vision-language-action	1,893	Python	4mo
Awesome-LLM4AD	Thinklab (SJTU & SII) Thinklab-SJTU	A curated list of awesome LLM/VLM/VLA/World Model for Autonomous Driving(LLM4AD) resources (continually updated)	World models Vision-language-action	1,892	·	2mo
Awesome-Embodied-Robotics-and-Agent	Haonan Zhang person zchoi	This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the late	Vision-language-action Navigation & mobility	1,858	·	14d
Emu	BAAI-Vision baaivision	Emu Series: Generative Multimodal Models from BAAI paper	Foundation models & pretraining	1,778	·	8mo
legged_control	Qiayuan Liao person UC Berkeley qiayuanl	NMPC, WBC, state estimation, and sim2real framework for legged robots based on OCS2 and ros-controls	Humanoids & locomotion Simulation, sim-to-real & benchmarks	1,793	C++	1.5y
lingbot-vla	Robbyant	A Pragmatic VLA Foundation Model	Vision-language-action Foundation models & pretraining	1,777	Python	3mo
VBench	Vchitect	[CVPR2024 Highlight] VBench - We Evaluate Video Generation paper	Video & generative modeling	1,747	·	7d
xr_teleoperate	Unitree Robotics Unitree unitreerobotics	This repository implements teleoperation of the Unitree humanoid robot using XR Devices.	Humanoids & locomotion Data collection & teleoperation	1,633	Python	25d
NavRL	Zhefan Xu person CMU Zhefan-Xu	[IEEE RA-L'25] NavRL: Learning Safe Flight in Dynamic Environments (NVIDIA Isaac/Python/ROS1/ROS2)	Navigation & mobility	1,587	C++	1.2y
HY-WorldPlay	Tencent-Hunyuan	HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency paper	World models	1,586	Python	3mo
walk-these-ways	Improbable-AI @MIT Improbable-AI	Sim-to-real RL training and deployment tools for the Unitree Go1 robot.	Humanoids & locomotion Simulation, sim-to-real & benchmarks	1,438	Python	2.2y
ml-aim	Apple apple	This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects. paper		1,424	·	1.1y
DRL-robot-navigation	Reinis Cimurs person reiniscimurs	Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic P	Simulation, sim-to-real & benchmarks Reinforcement learning & control	1,356	Python	9mo
Motus	TSAIL group Tsinghua thu-ml	Official code of Motus: A Unified Latent Action World Model	World models Vision-language-action	1,246	Python	8mo
wall-x	X Square Robot X-Square-Robot	Building General-Purpose Robots Based on Embodied Foundation Model	Foundation models & pretraining	1,236	Python	10d
UniVLA	OpenDriveLab	[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions paper	Vision-language-action	1,124	Python	9mo
ir-sim	hanruihua person	A Python-based lightweight robot simulator designed for navigation, control, and learning	Simulation, sim-to-real & benchmarks Navigation & mobility	1,119	Python	2d
visual-pushing-grasping	Andy Zeng person andyzeng	Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.	Dexterous manipulation Reinforcement learning & control	1,109	Python	5.3y
rex-gym	Nicola Russo person nicrusso7	OpenAI Gym environments for an open-source quadruped robot (SpotMicro)	Humanoids & locomotion	1,102	Python	3.4y
Awesome-Robotics-Manipulation	Bai Shuanghao person BaiShuanghao	A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.	Vision-language-action Dexterous manipulation	1,098	·	3d
skrl	Toni-SM person	Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gy	Reinforcement learning & control	1,089	Python	4mo
rl-mpc-locomotion	Yulun Zhuang person silvery107	Deep RL for MPC control of Quadruped Robot Locomotion	Humanoids & locomotion Simulation, sim-to-real & benchmarks	1,020	Python	4mo
rq-vae-transformer	kakaobrain	The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22) paper	Video & generative modeling	1,030	·	2.7y
dial-mpc	LeCAR Lab at CMU LeCAR-Lab	Official implementation for the paper "Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-S	Humanoids & locomotion	995	Python	1.3y
calvin	Oier Mees person mees	CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks	Vision-language-action	972	Python	12mo
awesome-3d-4d-world-models	worldbench	[TPAMI 2026] 3D and 4D World Modeling: A Survey paper	World models 3D & spatial reasoning	971	HTML	7d
GibsonEnv	Stanford Vision and Learning Lab Stanford StanfordVL	Gibson Environments: Real-World Perception for Embodied Agents	Simulation, sim-to-real & benchmarks	946	C	2.4y
spot_mini_mini	OpenQuadruped	Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.	Humanoids & locomotion Simulation, sim-to-real & benchmarks	941	C++	3.9y
diffusion-literature-for-robotics	Moritz Reuss person mbreuss	Summary of key papers and blogs about diffusion models to learn about the topic. Detailed list of all published diffusio	Dexterous manipulation Video & generative modeling	919	·	1.9y
Vista	OpenDriveLab	[NeurIPS 2024] A Generalizable World Model for Autonomous Driving	World models Navigation & mobility	895	Python	1.2y
TienKung-Lab	Open X-Humanoid Open-X-Humanoid	Tien Kung-Lab: Direct IsaacLab Workflow for Legged Robots	Humanoids & locomotion	870	Python	1mo
RynnBrain	Alibaba DAMO Academy alibaba-damo-academy	RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models paper	Foundation models & pretraining	869	·	18d
OpenWorldLib	OpenDCAI	Unified Codebase for Advanced World Models.	World models Vision-language-action	863	Python	5d
humanplus	Zipeng Fu person Stanford MarkFzp	[CoRL 2024] HumanPlus: Humanoid Shadowing and Imitation from Humans	Humanoids & locomotion	850	Python	2.2y
FSDrive	MIV-XJTU	[NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for A	World models Vision-language-action	821	Python	4mo
Awesome-Robotics-3D	zubair-irshad	A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by aw	Dexterous manipulation Navigation & mobility	819	·	8mo
lingbot-vla-v2	Robbyant	From Foundation to Application paper	Vision-language-action	800	·	18d
asimov-v0	Menlo Research menloresearch	v0 of Asimov, an open-source humanoid robot	Humanoids & locomotion	781	·	7mo
X-VLA	Jinliang Zheng person Tsinghua 2toinf	[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action	Vision-language-action Foundation models & pretraining	719	C++	3mo
pace-sim2real	Robotic Systems Lab - Legged Robotics at ETH Zürich ETH Zurich leggedrobotics	PACE: A systematic approach for sim-to-real transfer of legged robots, identifying actuator and joint dynamics with stan	Humanoids & locomotion Simulation, sim-to-real & benchmarks	687	Python	4d
robotic_world_model	Robotic Systems Lab - Legged Robotics at ETH Zürich ETH Zurich leggedrobotics	Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics an	World models Humanoids & locomotion	670	Python	5mo
HoloMotion	Horizon Robotics HorizonRobotics	HoloMotion: A Foundation Model for Whole-Body Humanoid Control	Humanoids & locomotion Foundation models & pretraining	664	Python	9d
SEED	TencentAILab-CVC AILab-CVC	Official implementation of SEED-LLaMA (ICLR 2024). paper		642	·	1.9y
AutoVLA	UCLA Mobility Lab ucla-mobility	[NeurIPS 2025] AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Rei	Vision-language-action Navigation & mobility	632	Python	3mo
ABS	LeCAR Lab at CMU LeCAR-Lab	[RSS 2024] Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion	Humanoids & locomotion	624	Python	2.1y
dobb-e	Nur Muhammad "Mahi" Shafiullah person notmahi	Dobb·E: An open-source, general framework for learning household robotic manipulation paper		621	G-code	1.9y
realtime-vla	Dexmal dexmal	Running VLA at 30Hz frame rate and 480Hz trajectory frequency paper	Vision-language-action	607	·	7mo
curl	Michael Laskin person Google DeepMind MishaLaskin	CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning paper	Reinforcement learning & control	605	·	5.8y
MDT	Sea AI Lab sail-sg	Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023) paper		596	·	2.3y
recogdrive	Xiaomi Research xiaomi-research	[ICLR 2026] ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving	Vision-language-action Navigation & mobility	594	Python	10d
rai	Robotec.ai RobotecAI	RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, d		575	Python	16d
tau-0-vla	Shanghai Innovation Institute sii-research	This repo is the official implementation of "τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test	World models Vision-language-action	563	Python	2d
quadruped_ros2_control	HUANG ZHENBIAO person NUS legubiao	ROS2-Control implementations for Quadruped robots, include sim2real	Humanoids & locomotion Simulation, sim-to-real & benchmarks	562	C++	6mo
WholebodyVLA	OpenDriveLab	[ICLR 2026] Towards Unified Latent VLA for Whole-body Loco-manipulation Control	Vision-language-action Humanoids & locomotion	553	·	3mo
Simulately	RoboVerse RoboVerseOrg	A universal summary of current robotics simulators	Simulation, sim-to-real & benchmarks	551	TypeScript	1.1y
VLA-Handbook	KenSou person sou350121	本项目旨在为致力于进入VLA(Vision-Language-Action)领域的算法工程师提供一份全中文、实战导向的学习/面试手册。不同于通用的 CV/NLP 面试指南，本项目聚焦于 Robotics 特有的挑战	Vision-language-action	551	HTML	2d
IsaacLab-Arena	NVIDIA Isaac Sim NVIDIA isaac-sim	Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable		546	Python	2d
InternVLA-A-series	Intern Robotics Shanghai AI Lab InternRobotics	InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation	Vision-language-action	539	Python	1mo
General-World-Models-Survey	GigaAI-research person	paper	World models	525	·	10mo
visionary	Visionary-Laboratory	Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform	World models 3D & spatial reasoning	523	Python	2mo
HumanEgo	Zhi (Leo) Wang person Amazon TX-Leo	HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos paper	Egocentric & human data	509	·	3d
VideoAlign	KlingAI Research KlingAIResearch	[NeurIPS 2025] Improving Video Generation with Human Feedback paper	Reinforcement learning & control Video & generative modeling	501	·	11mo
expressive-humanoid	Xuxin Cheng person UC Berkeley chengxuxin	[RSS 2024]: Expressive Whole-Body Control for Humanoid Robots	Humanoids & locomotion Simulation, sim-to-real & benchmarks	498	Python	1.4y
awesome-ros-mobile-robot	shannon112 person	😎 A curated list of awesome mobile robots study resources based on ROS (including SLAM, odometry and navigation, manip	3D & spatial reasoning Navigation & mobility	497	·	10mo
VAGEN	MLL Lab mll-lab-nu	World model reinforcement learning for multi-turn VLM agents. RL for vision framework (NeurIPS 2025).	World models Reinforcement learning & control	493	Python	2d
awesome-legged-locomotion-learning	Pengyu Chen person gaiyi7788	A curated list of resources relevant to legged locomotion learning of robotics.	Humanoids & locomotion	485	·	3.1y
ETPNav	Dong An person MarSaKi	[TPAMI 2024] Official repo of "ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Enviro paper	Navigation & mobility Foundation models & pretraining	484	Python	4mo
Awesome-Generalist-Robots-via-Foundation-Models	Yafei Hu person CMU JeffreyYH	Paper list in the survey paper: Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis	World models Vision-language-action	468	·	2mo
awesome-vla-for-ad	worldbench	🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future	Vision-language-action Navigation & mobility	465	HTML	7d
awesome-real-world-rl	Ugurkan Ates person ugurkanates	Great resources for making Reinforcement Learning work in Real Life situations. Papers,projects and more.	Simulation, sim-to-real & benchmarks Imitation & diffusion policies	458	·	3.8y
legged-loco	Zhaojing Yang person yang-zj1026	Low-level locomotion policy training in Isaac Lab	Humanoids & locomotion	452	Python	1.5y
CogACT	Microsoft microsoft	A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation	Vision-language-action	431	Python	10mo
horus	HORUS softmata	Fastest Robotics Runtime System. If phones have Android, robots deserve HORUS.	Humanoids & locomotion Navigation & mobility	425	Rust	4d
humanoid-motion-intelligence	XiaoZe person RealXiaoze	人形机器人运动智能论文、开源项目、产业与求职知识库	Vision-language-action Humanoids & locomotion	423	·	2d
rad	Michael Laskin person Google DeepMind MishaLaskin	RAD: Reinforcement Learning with Augmented Data paper	Reinforcement learning & control	416	·	5.4y
opendm	Dexmal dexmal	An Open-World Foundation Model for General-Purpose Embodied Intelligence.	Vision-language-action Foundation models & pretraining	412	Python	2d
Robotic-grasping-papers	Zibo Chen person rhett-chen	paper list of robotic grasping and some related works	Dexterous manipulation	407	·	1.8y
awesome-physical-ai	Keon person keon	A curated list of academic papers and resources on Physical AI — focusing on Vision-Language-Action (VLA) models, world	World models Vision-language-action	401	·	2mo
RoboManipBaselines	Intelligent Systems Research Institute, AIST isri-aist	A software framework integrating various imitation learning methods and benchmark environments for robotic manipulation	Imitation & diffusion policies	395	Python	2mo
mini-vla	Keivalya Pandya person keivalya	a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to generate actions	Vision-language-action	384	Python	5mo
openvla-mini	Stanford Intelligent and Interactive Autonomous Systems Group Stanford Stanford-ILIAD	OpenVLA: An open-source vision-language-action model for robotic manipulation.	Vision-language-action Imitation & diffusion policies	376	·	1.4y
ml-egodex	Apple apple	EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video	Dexterous manipulation Egocentric & human data	375	·	1.0y
WMP	Bytedance Inc. ByteDance bytedance	Reproduction code of paper "World Model-based Perception for Visual Legged Locomotion"	World models Humanoids & locomotion	372	Python	1.7y
CarDreamer	UCD DARE Lab ucd-dare	World Model based Autonomous Driving Platform in CARLA :car:	World models Simulation, sim-to-real & benchmarks	367	Python	9mo
awesome-vla-study	MilkClouds person	A structured reading list on Vision-Language-Action (VLA) models — from diffusion/flow matching foundations through stat	World models Vision-language-action	365	·	5mo
ReinFlow	ReinFlow person	[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0	Vision-language-action Humanoids & locomotion	360	Python	4mo
alpamayo1.5	NVIDIA Research Projects NVIDIA NVlabs	NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced	World models Vision-language-action	355	Python	4d
Robotics-Object-Pose-Estimation	Unity Technologies Unity-Technologies	A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural		349	Python	4.4y
v2x-vit	Runsheng Xu person DerrickXuNu	[ECCV2022] Official Implementation of paper "V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transfor paper	Video & generative modeling	348	·	2.0y
fc-clip	Bytedance Inc. ByteDance bytedance	[NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single paper		345	·	2.6y
RISE	OpenDriveLab	[RSS 2026] Code for RISE: Self-Improving Robot Policy with Compositional World Model	World models Vision-language-action	343	Python	2mo
ihmc-open-robotics-software	IHMC Robotics ihmcrobotics	Robotics software featuring legged locomotion algorithms and a momentum-based controller core with optimization. Support	Humanoids & locomotion	325	Java	2d
VADER	Mihir Prabhudesai person mihirp1998	Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, Ope paper	World models Reinforcement learning & control	318	·	1.5y
DiffTactile	Genesis AI Genesis-Embodied-AI	[ICLR 2024] DiffTactile: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation	Tactile & force sensing Simulation, sim-to-real & benchmarks	316	Python	2.4y
isaacLab.manipulation	NathanWu7 person NVIDIA	An independent extension based on IsaacLab. It provides support for Robot Manipulation tasks (Robot Arm and Dextrous Han		314	Python	1.2y
LeRobot-Anything-U-Arm	MINT-SJTU person	U-Arm: Lerobot-Everything-Cross-Embodiment-Teleoperation	Foundation models & pretraining Data collection & teleoperation	313	Python	1mo
WorldFoundry	OpenEnvision	Unified World Model Inference & Evaluation Infrastructure	World models Vision-language-action	311	Python	1mo
mimic-video	mimic-video person	Video-Action Models for Generalizable Robot Control Beyond VLAs	Vision-language-action	298	Python	2mo
Grounding_LLMs_with_online_RL	Flowers Team flowersteam	We perform functional grounding of LLMs' knowledge in BabyAI-Text paper		275	·	10mo
teleop	Spes Robotics SpesRobotics	Turns your phone or VR headset into a robot arm teleoperation device by leveraging WebXR	Data collection & teleoperation	272	Python	1mo
UniDexGrasp	PKU-EPIC	Official code for "UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-C	Dexterous manipulation	270	Python	2.3y
VideoGen-Eval	TencentAILab-CVC AILab-CVC	VideoGen-Eval: Agent-based System for Video Generation Evaluation paper	Video & generative modeling	269	·	9mo
OCRM_survey	RayYoh person	A Survey of Embodied Learning for Object-Centric Robotic Manipulation		258	·	1.9y
Orient-Anything-V2	SpatialVision	Orient Anything V2, NeurIPS 2025 Spotlight paper		251	·	7mo
joycon-robotics	Box2AI Robotics person box2ai-robotics	Joycon-Robotics: Low-Cost, Convenient Teleoperation for One- and Two-Arm Robots	Data collection & teleoperation	245	Jupyter Notebook	5mo
UniAct	Jinliang Zheng person Tsinghua 2toinf	[CVPR 2025] The offical Implementation of "Universal Actions for Enhanced Embodied Foundation Models"	Vision-language-action Foundation models & pretraining	244	Python	10mo
UFO	RoboParty Roboparty	An open-source unsupervised RL framework for humanoid control with FB/TeCH training, robot-aware motion import, and real	Humanoids & locomotion Data collection & teleoperation	240	Python	29d
AME_Locomotion	傅晟程 person SII-FUSC	This repository reproduces the Attention-Based Map Encoding (AME) method from the paper Attention-Based Map Encoding for	Humanoids & locomotion	240	Python	4mo
Awesome-Embodied-AI	Cheng Yin person Tsinghua wadeKeith	Curated embodied AI list: surveys, VLA models, datasets, simulators, humanoids, robot learning, and safety resources.	Vision-language-action Humanoids & locomotion	240	Python	2d
EgoHumanoid	OpenDriveLab	[RSS 2026] The first framework enabling humanoid robots to learn whole-body loco-manipulation from egocentric human demo	Vision-language-action Humanoids & locomotion	237	Python	3mo
pymanoid	Stéphane Caron person stephane-caron	Humanoid robotics prototyping environment based on OpenRAVE	Humanoids & locomotion	233	Python	2.5y
teleop_tools	ros-teleop	A set of generic teleoperation tools for any robot.	Data collection & teleoperation	232	Python	7mo
CityWalker	AI4CE Lab @ NYU ai4ce	[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos	Humanoids & locomotion Navigation & mobility	229	Python	11mo
LLaRA	Xiang Li person LostXine	[ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy	Vision-language-action	228	Python	1.4y
BridgeVLA	BridgeVLA person	✨✨Official implementation of BridgeVLA and BridgeVLA++	Vision-language-action Foundation models & pretraining	220	Python	15d
SPI-Active	LeCAR Lab at CMU LeCAR-Lab	Official Implementation of "Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learn	Humanoids & locomotion Simulation, sim-to-real & benchmarks	217	Python	9mo
MetalHead	inspir.ai inspirai	Natural Locomotion, Jumping and Recovery of Quadruped Robot A1 with AMP	Humanoids & locomotion	216	Python	3.3y
vq_bet_official	Seungjae Lee person Toyota Research Institute jayLEE0301	Official code for "Behavior Generation with Latent Actions" (ICML 2024 Spotlight) paper		214	·	2.5y
othello_world	Kenneth Li person likenneth	Emergent world representations: Exploring a sequence model trained on a synthetic task paper		214	·	3.1y
EmbodiChain	DexForce	An end-to-end, GPU-accelerated, and modular platform for building generalized Embodied Intelligence.	Simulation, sim-to-real & benchmarks	212	Python	2d
ViTamin	Jieneng Chen person Beckschen	[CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era" paper		211	·	2.2y
alpamayo2	NVIDIA Research Projects NVIDIA NVlabs	NVIDIA Alpamayo 2 Super is an open 34B multi-task foundation model designed to supercharge autonomous vehicle developmen	World models Vision-language-action	208	Python	23d
awesome-rl-for-legged-locomotion	ApexRL apexrl	A curated list of awesome material on legged robot locomotion using reinforcement learning (RL) and sim-to-real techniqu	Humanoids & locomotion Simulation, sim-to-real & benchmarks	206	·	1.4y
ScaleBFM	Weishuai Zeng person Peking University zengweishuai	The official implementation of the paper "Scaling Behavior Foundation Model for Humanoid Robots"	Humanoids & locomotion Foundation models & pretraining	203	Python	1mo
microban	Rhoban	Microban is an affordable, fully 3D-printable, and 100% open-source humanoid robot. Powered by a Raspberry Pi Zero 2W an	Humanoids & locomotion	202	Python	1mo
Taccel	Taccel Simulator Taccel-Simulator	Taccel: Scaling-up Vision-based Tactile Robotics with High-performance GPU Simulation	Tactile & force sensing Simulation, sim-to-real & benchmarks	199	Cuda	11mo
BodyTransformer	Carlo Sferrazza person carlosferrazza	Body Transformer: Leveraging Robot Embodiment for Policy Learning		199	Jupyter Notebook	11mo
DiffuseLoco	Hybrid Robotics HybridRobotics	Source code for the paper DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets	Humanoids & locomotion	198	Python	1.4y
Awesome-Video-Robotic-Papers	Freax Ruby person H-Freax	This repository compiles a list of papers related to the application of video technology in the field of robotics! Star⭐		193	·	1.6y
MultiModalWBC	Renforce Dynamics Renforce-Dynamics	MultiModalWBC is a fully open-source, IsaacLab-based framework for multi-modal whole-body control, designed for motion i	Humanoids & locomotion	192	Python	2mo
tortoisebot	RigBetel Labs LLP rigbetellabs	TortoiseBot is an extremely learner-friendly and cost-efficient ROS-based Open-sourced Mobile Robot that is capable of d	3D & spatial reasoning Navigation & mobility	189	Makefile	23d
act3d-chained-diffuser	Zhou Xian person zhouxian	A unified architecture for multimodal multi-task robotic policy learning.		186	Python	2.6y
space_robotics_bench	Andrej Orsula person AndrejOrsula	Robot Learning Beyond Earth paper		183	Python	9mo
XR-1	Open X-Humanoid Open-X-Humanoid	Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations	Vision-language-action Humanoids & locomotion	182	Python	1mo
Geometric-Action-Model	cvlab-kaist person	Official implementation of "Geometric Action Model for Robot Policy Learning"		180	Python	5d
OpenWBC	jiachengliu3(SII) person jiachengliu3	VR-based Robot Teleoperation and Data Collection System for Humanoid Whole-Body VLA (Unitree G1)	Vision-language-action Humanoids & locomotion	174	C++	6mo
Re3Sim	Intern Robotics Shanghai AI Lab InternRobotics	[ICRA 2026] Re3Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation	Simulation, sim-to-real & benchmarks	173	Jupyter Notebook	6mo
Teleopit	Wu Bingqian 吴秉谦 person BotRunner64	a full-embodiment humanoid teleoperation system	Humanoids & locomotion Data collection & teleoperation	172	Python	18d
awesome-embodied-data-pyramid	worldbench	🔥 Data Pyramid for Embodied Manipulation: A Survey paper	World models Vision-language-action	172	HTML	2d
AirGym	emNavi	A high-performance drone deep reinforcement learning platform built upon IsaacGym.	Simulation, sim-to-real & benchmarks Reinforcement learning & control	171	Python	24d
inspect-robots	robocurve	Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.	Vision-language-action Humanoids & locomotion	167	Python	8d
lap	Lihan Zha person Princeton lihzha	LAP: Language-Action Pre-Training Enables Zero-Shot Cross Embodiment Transfer	Vision-language-action Foundation models & pretraining	166	Python	3mo
VideoActionModel	valeo.ai valeoai	VaViM and VaVAM: Autonomous Driving through Video Generative Modeling (official repository). paper	World models Navigation & mobility	165	·	1.2y
awesome-reliable-robotics	Philip Fung person philfung	Robotics research demonstrating reliability and robustness in the real world (continuously updated)	World models Vision-language-action	163	·	1mo
awesome-humanoid-manipulation	Tsunami person Shanghai AI Lab Tsunami-kun	A curated list of awesome papers and resources on humanoid manipulation, dexterous manipulation, bimanual dexterous mani	Dexterous manipulation Humanoids & locomotion	157	·	3mo
RISE	📈 RISE Policy person rise-policy	[IROS 2024] 📈 RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective		157	Python	9mo
Galahad	Φ(fight) Research phi-monster	Instruction blindness in vision-language-action policies: diagnosis and a low-rank data cure. Paper, model, deconfounded	Vision-language-action	149	Python	1mo
alpamayo-recipes	NVIDIA Research Projects NVIDIA NVlabs	Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training	World models Vision-language-action	148	Python	23d
foundation_models	Argo Argo-Robot	Overview about state-of-art imitation learning techniques for robotic manipulation, enabling generalization across diver	Imitation & diffusion policies	145	·	1.4y
LocoWheeledLegged	Zijie Zhao person zhaozijie2022	RL-based Legged-Wheeled Robot locomotion sim-to-real based on NVIDIA Isaac Lab	Humanoids & locomotion Simulation, sim-to-real & benchmarks	143	Python	2mo
cyclo_lab	ROBOTIS ROBOTIS-GIT	This repository provides tutorials for reinforcement learning and imitation learning using ROBOTIS robots, and supports	Simulation, sim-to-real & benchmarks Imitation & diffusion policies	142	Python	2d
yubi-hw	Toyota	YUBI - Yielding Universal Bidigital Interface - Open source hardware design for a finger-driven teleoperation glove and	Data collection & teleoperation Hardware & morphology co-design	140	·	8d
FreeTacMan	OpenDriveLab	[ICRA 2026] FreeTacMan: Robot-free Visuo-Tactile Data Collection System for Contact-rich Manipulation	Tactile & force sensing Data collection & teleoperation	139	Python	7mo
navigation-locomotion	Zipeng Fu person Stanford MarkFzp	[CVPR 2022] Codebase for "Coupling Vision and Proprioception for Navigation of Legged Robots"	Humanoids & locomotion Navigation & mobility	134	C++	4.2y
handover-sim2real	NVIDIA Research Projects NVIDIA NVlabs	Official code for CVPR'23 paper: Learning Human-to-Robot Handovers from Point Clouds	Simulation, sim-to-real & benchmarks 3D & spatial reasoning	130	Python	1.5y
Awesome-Embodied-AI-Safety	Xiang Zheng person x-zheng16	Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses \| 500+ Papers \| Perception, Cognition, Planning, Interac	World models Vision-language-action	130	Python	2d
hei-rebot-lift	黑狗木 person lipengdong	HEI ReBot Lift is a LeRobot/ReBot-based dual-arm mobile robot with a lifting platform, omnidirectional chassis, three-vi	Vision-language-action Data collection & teleoperation	129	Python	27d
TRILL	UT Robot Perception and Learning Lab UT-Austin-RPL	Official codebase for TRILL (Teleoperation and Imitation Learning for Loco-manipulation)	Humanoids & locomotion Imitation & diffusion policies	127	Python	1.1y
SM4RT	Wenzhao Zheng person UC Berkeley wzzheng	Code for SM4RT: Learning Structured Motion Geometry for 4D Reconstruction paper		125	·	9d
graph-as-policy	graph-robots	gap — graph as policy: compile language instructions into typed, verified robot skill graphs and execute them on simulat	Simulation, sim-to-real & benchmarks	121	Python	28d
good_robot	JHU Laboratory for Computational Sensing and Robotics jhu-lcsr	"Good Robot! Now Watch This!": Repurposing Reinforcement Learning for Task-to-Task Transfer; and “Good Robot!”: Efficien	Dexterous manipulation Simulation, sim-to-real & benchmarks	121	Jupyter Notebook	4.4y
kinect_teleoperate	Unitree Robotics Unitree unitreerobotics	This repository implements teleoperation of the Unitree humanoid robot H1 / G1 using Azure Kinect DK camera.	Humanoids & locomotion Data collection & teleoperation	120	C	2.0y
MPI	OpenDriveLab	[RSS 2024] Learning Manipulation by Predicting Interaction paper	Foundation models & pretraining	118	·	1.2y
DreamWaQ_Go2W	Shengqian Chen person ShengqianChen	A Go2W legged-wheel robot locomotion reinforcement learning project based on NVIDIA Isaac Gym.	Humanoids & locomotion Reinforcement learning & control	115	Python	4mo
sage	isaac-sim2real	Framework for measuring sim-to-real gaps in robot joint motions. Supports different humanoids with physics simulation, r	Humanoids & locomotion Simulation, sim-to-real & benchmarks	113	Python	4mo
project_superdex	Meta Research Meta FAIR facebookresearch	SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning	Reinforcement learning & control Data collection & teleoperation	108	C++	2d
TactileSimulation	Jie Xu person NVIDIA eanswer	[CoRL 2022] Efficient Tactile Simulation with Differentiability for Robotic Manipulation	Tactile & force sensing	105	Python	2.6y
robot-arm	Bart Trzynadlowski person trzy	Imitation learning with iPhone based teleoperation of a low-cost robot arm.	Imitation & diffusion policies Data collection & teleoperation	105	Python	1.9y
tactile_envs	Carlo Sferrazza person carlosferrazza	Collection of MuJoCo robotics environments equipped with both vision and tactile sensing	Tactile & force sensing	102	Python	2.1y
awesome-touch	yuanliang sun person sun254667	A curated, learning-friendly list of tactile sensing research resources for robotic manipulation: papers, datasets, benc	World models Vision-language-action	97	·	26d
twm	Jan Robine person jrobine	Transformer-based World Models paper	World models	91	·	3.4y
fast_and_efficient	Yuxiang Yang person Google DeepMind yxyang	paper		91	·	3.4y
RynnWorld-4D	Alibaba DAMO Academy alibaba-damo-academy	RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation paper	World models	86	·	1mo
blender-robotics-utils	Robotology robotology	Set of utilities for exporting/controlling your robot in Blender	Humanoids & locomotion	83	Python	1.7y
HumanTyping	Alexandre person Lax3n	The most realistic keyboard typing simulator based on Markov Chains. Models authentic human behavior (errors, correction	Humanoids & locomotion Simulation, sim-to-real & benchmarks	78	Python	2mo
PACE-ICRA2026	purdue-tracelab	[ICRA2026] "PACE: Physics Augmentation for Coordinated End-to-end Reinforcement Learning toward Versatile Humanoid Table	Humanoids & locomotion Reinforcement learning & control	78	Python	4d
gesture-recognition-for-human-robot-interaction	Aravinth Panch person AravinthPanch	Gesture Recognition For Human-Robot Interaction with modelling, training, analysing and recognising gestures based on co	Humanoids & locomotion Human-robot interaction	76	C++	6.9y
osmo_tactile_glove	Jessica Yin person jessicayin	Open source tactile glove for robotics research	Tactile & force sensing	74	C	4mo
programming-humanoid-robot-in-python	DAInamite	Programming Humanoid Robot In Python	Humanoids & locomotion	73	Jupyter Notebook	1.9y
Dynamics-Modeling	Frank Zhiyang Dou person Frank-ZY-Dou	paper		72	·	1mo
tactile-dexterity	Irmak Guzey person irmakguzey	Official implementation of Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Pl	Dexterous manipulation Tactile & force sensing	70	Python	2.6y
CrowdNav_Sim2Real_Turtlebot	Shuijing Liu person Shuijing725	[ICRA 2023] Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph -- Sim2real code on Turtlebot2	Simulation, sim-to-real & benchmarks Navigation & mobility	67	Python	1.7y
PP-Tac	Beijing Institute for General Artificial Intelligence bigai-ai	This is the implementation of PP-Tac: Paper Picking Using Tactile Feedback in Dexterous Robotic Hands	Dexterous manipulation Tactile & force sensing	66	Python	2mo
ROS2_Walking_Pattern_Generator	open-rdc	Walking Pattern Generator (= Walking Controller) using ROS2 for Humanoid Robots	Humanoids & locomotion	63	C++	1.2y
DeformableObjectsGrasping	Laboratory for Intelligent Decision and Autonomous Robots GTLIDAR		Dexterous manipulation Tactile & force sensing	60	·	2.7y
LocoTouch	Changyi Lin person CMU linchangyi1	Perceptive Learning for Legged Robots in IsaacLab. \| LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sens	Humanoids & locomotion Tactile & force sensing	60	Python	4mo
DreamX-Phi	DreamX AMAP-ML	DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation paper	World models	61	·	14d
OmniVTA	Yuhang Zheng person MrSecant	OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation	World models Tactile & force sensing	59	·	18d
ppo-ewma	OpenAI openai	Code for the paper "Batch size invariance for policy optimization" paper	Reinforcement learning & control	59	·	3.4y
nvblox_mindmap	NVIDIA Isaac NVIDIA nvidia-isaac	mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies	Vision-language-action Humanoids & locomotion	58	Python	11mo
tingdeliu.github.io	Tingde Liu person TingdeLiu	My Personal Blog (Robotics)	Vision-language-action Navigation & mobility	57	SCSS	2d
sim2real-ur-gym-gazebo	Ammar N. Abbas person ammar-n-abbas	Universal Robot Environment for OpenAI Gymnasium and ROS Gazebo Interface	Simulation, sim-to-real & benchmarks	54	C++	1.4y
Visual-Tactile_Dataset	Tsinghua Robot Learning Lab Tsinghua tsinghua-rll	A novel visual-tactile dataset for robotic manipulation	Tactile & force sensing	53	·	7.0y
ZMP-Preview-Control-WPG	Eko Rudiawan Jamzuri person ekorudiawan	ZMP Preview Control Walking Pattern Generation for Biped Humanoid Robot	Humanoids & locomotion	51	Python	2mo
unitree-g1-autonomous	GalacTechNyc person	🤖 Fully autonomous navigation system for Unitree G1 humanoid robot using AI-powered visual analysis with Google Gemini	Humanoids & locomotion Navigation & mobility	50	Python	1.1y
Pepper-Controller	Incognite incognite-lab	Python controller for Pepper humanoid robot. It allows to write apps in Python. There are examples of simple application	Humanoids & locomotion Navigation & mobility	49	Python	6mo
roboprime	Simone Primarosa person simonepri	🤖 Full featured 21 DOF 3D Printed Humanoid Robot based on ATmega328P chip	Humanoids & locomotion	49	Arduino	8.9y
awesome-agentic-world-model	worldbench	🔥 Quo Vadis, World Modeling? Towards Interactive World Proxies for Continually Improving Agents paper	World models	48	·	6d
robot-blueberry	Jewel Nath person jewel-nath	Raspberry pi based humanoid robot.	Humanoids & locomotion	47	Python	4.8y
TeleoperationUnity	Abraham George person Abraham190137	paper	Simulation, sim-to-real & benchmarks Data collection & teleoperation	45	·	1.7y
LIBERO-Para	cau-hai-lab	Official code for "LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models" (EMNLP 2026	Vision-language-action Safety & evaluation	43	Python	7d
RynnWorld-Teleop	Alibaba DAMO Academy alibaba-damo-academy	RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation paper	World models Data collection & teleoperation	39	·	25d
REAL	Intern Robotics Shanghai AI Lab InternRobotics	[ECCV2026] Official open-source repository for REAL——Exploratory, Communicative, and Deployable: Vision-Driven Embodied paper	Simulation, sim-to-real & benchmarks Navigation & mobility	39	·	1mo
INT-ACT	AI4CE Lab @ NYU ai4ce	Official repo for From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models	Vision-language-action	34	Python	10mo
robots-sim	strands-labs	Simulated environments for robot agent evaluation and reinforcement learning.	Vision-language-action Reinforcement learning & control	34	Python	22d
RealDPO	Vchitect	paper		32	·	10d
Awesome-Post-Training-In-Autonomous-Driving-Papers	RY-ning person RYNing	A curated list of papers on post-training for end-to-end autonomous driving: distillation, preference alignment, reinfor	Vision-language-action Reinforcement learning & control	30	·	1mo
Anchor-Align	Dwip Dalal person dwipddalal	Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment paper	Vision-language-action Video & generative modeling	30	Python	3d
track2	robosense2025 person	Track 2: Social Navigation	Vision-language-action Navigation & mobility	27	·	1.0y
rad_procgen	Kimin Lee person pokaxpoka	RAD: Reinforcement Learning with Augmented Data (code for procgen experiments) paper	Reinforcement learning & control	19	·	5.4y
OBEYED_VLA	AICV Lab UARK-AICV	OBEYED-VLA: Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding	Vision-language-action	14	Python	4mo
awesome-vla-2026	Liu Yue person miracle-techlink	📚 Vision-Language-Action Models · 2026 categorized index — 250+ papers across 15 categories, synthesized from 11 survey	Vision-language-action	13	·	3mo
vernata	RAI Open Source Boston Dynamics rai-opensource	paper	3D & spatial reasoning	15	·	17d
DropVLA	Zonghuan Xu person megaknight114	Backdoor training and evaluation scripts for vision-language-action models on LIBERO.	Vision-language-action	12	Python	1mo
cbf-rl-navigation-demo	Lizhi Yang person lzyang2000	paper	Navigation & mobility	11	·	6mo
EAGG	Wanhao Niu person wanhaoniu	Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning paper	Dexterous manipulation	11	·	2mo
pybmtp	Peter Werner person MIT wernerpe	A python software package for computing smooth, minimum-time trajectories around convex obstacles paper		4	·	23d
seeker	Ryan.Z person zheyu-zhuang	[Seeker]: Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning paper		4	·	10d
ImprovedVBGS	damanimc person	Improved Variational Bayes Gaussian Splatting paper	3D & spatial reasoning	3	·	18d
paamp_underactuated	Akshay Jaitly person Akshay5312	Trusted Polytopic Action Sets for fast underactuated motion planning paper		1	·	22d
TAMS	Zexin Deng person Dzxx623	ROS 2 reference implementation of Task-Aware Multi-View Adaptive Streaming for wireless telerobotic manipulation. paper		1	·	18d
6-dof-arm-neuralnexus	Lasan Perera person Lasan-Perera	6_DoF_Arm NeuralNexus is a six-degree-of-freedom robotic arm designed for precise object manipulation and automation tas paper		1	·	20d
anytime_gtmp	CoMMALab	Anytime Global Tensor Motion Planning paper		0	·	1d
safe-actor-critic-aer-ue-reproducibility	Davoud Nikkhouy person SDNT8810	paper	Reinforcement learning & control	0	·	1mo
LabRobFail	PLANB person Su-ISE-2001	LabRobFail: A Benchmark for Robotic Failure Analysis in Scientific and Self-driving Laboratory paper	Simulation, sim-to-real & benchmarks	0	·	1mo
instant-episode-repetition	CARES UoA-CARES	Official implementation of Instant Episode Repetition (IER) for sample-efficient reinforcement learning with SAC and TD3 paper	Reinforcement learning & control	0	·	3d
descent	Alexander Prutsch person a-pru	[IROS 2026] DESCENT: Directed Edge Scene Encoding for Airport Surface Movement Prediction paper		0	·	1d
DynamicSpectraFormer	arifence2024 person	paper		0	·	2.5y
OSMa-Bench-v2	ITMO Biomechatronics and Energy Efficient Robotics Laboratory be2rlab	paper		0	·	3mo
SINDYc_MPC_RoSE_symmetric_peristaltic	Dipankar Bhattacharya person bhattner143	This repo is for raspberry pi only paper		0	·	5mo
mujoco	Calum Arnott person calumarnott	Multi-Joint dynamics with Contact. A general purpose physics simulator. This fork implements a custom gradient backend f paper	Simulation, sim-to-real & benchmarks	0	·	25d
PCDP	MARMot Lab @ NUS-ME NUS marmotlab	paper		0	·	11d
MAGIC-HRI-V01	ruancarminati person	paper		0	·	9d
excitation-supervised-closed-loop	Yash Bagla person yashbagla321	paper		0	·	14d

Click any heading to sort. Repository details are read from each project's own GitHub page; star counts move, so treat them as of the last refresh. Download the dataset.

Who publishes it

53 of these repos trace to an organisation we can name, and 116 are one person's account. The split matters when you are deciding what to build on: a lab's repo usually outlives the graduate student, and an individual's usually does not.

Organisation	Repos	Examples
NVIDIA	10	IsaacLab, alpamayo, IsaacLab-Arena
Google DeepMind	7	google-research, vision_transformer, simclr
Tsinghua	5	Motus, X-VLA, UniAct
Stanford	4	GibsonEnv, humanplus, openvla-mini
Shanghai AI Lab	4	InternVLA-A-series, Re3Sim, awesome-humanoid-manipulation
Meta FAIR	3	moco, habitat-lab, project_superdex
UC Berkeley	3	legged_control, expressive-humanoid, SM4RT
CMU	3	NavRL, Awesome-Generalist-Robots-via-Foundation-Models, LocoTouch
Unitree	2	xr_teleoperate, kinect_teleoperate
ETH Zurich	2	pace-sim2real, robotic_world_model
NUS	2	quadruped_ros2_control, PCDP
ByteDance	2	WMP, fc-clip
Amazon	1	HumanEgo
Toyota Research Institute	1	vq_bet_official
Peking University	1	ScaleBFM
Princeton	1	lap
Boston Dynamics	1	vernata
MIT	1	pybmtp

Straight from a paper

These were linked by the authors themselves or listed by a club, so pairing the repo with the paper makes an easy two-part talk: what they claimed, and whether the code backs it.

38,627★

google-research/google-research

Google Research

Paper: Finite Scalar Quantization: VQ-VAE Made Simple

12,683★

google-research/vision_transformer

Paper: An Image is Worth 16x16 Words: Transformers for Image Recognition at S

10,517★

IDEA-Research/GroundingDINO

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set

Paper: Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set

6,916★

sczhou/ProPainter

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

Paper: ProPainter: Improving Propagation and Transformer for Video Inpainting

5,683★

apple/ml-depth-pro

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Paper: Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

5,136★

facebookresearch/moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

Paper: Momentum Contrast for Unsupervised Visual Representation Learning

4,502★

google-research/simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

Paper: A Simple Framework for Contrastive Learning of Visual Representations

4,393★

Robbyant/lingbot-world

Advancing Open-source World Models

Paper: Advancing Open-source World Models

3,821★

google-research/scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

Paper: ViViT: A Video Vision Transformer

3,157★

OpenDriveLab/AgiBot-World

[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent

Paper: AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalabl

2,837★

mujocolab/mjlab

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research

Paper: mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning

2,499★

yifan123/flow_grpo

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Paper: Flow-GRPO: Training Flow Matching Models via Online RL

2,126★

rlworkgroup/garage

A toolkit for reproducible reinforcement learning research.

Paper: Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinfor

1,949★

LTH14/mar

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Paper: Autoregressive Image Generation without Vector Quantization

1,871★

Farama-Foundation/Metaworld

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

Paper: Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinfor

1,778★

baaivision/Emu

Emu Series: Generative Multimodal Models from BAAI

Paper: Emu: Generative Pretraining in Multimodality

1,747★

Vchitect/VBench

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

Paper: VBench: Comprehensive Benchmark Suite for Video Generative Models, VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic F

1,586★

Tencent-Hunyuan/HY-WorldPlay

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Paper: WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Inter

Python

1,424★

apple/ml-aim

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

Paper: Scalable Pre-training of Large Autoregressive Image Models

1,124★

OpenDriveLab/UniVLA

[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

Paper: UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

Python

1,030★

kakaobrain/rq-vae-transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

Paper: Autoregressive Image Generation using Residual Quantization

971★

worldbench/awesome-3d-4d-world-models

[TPAMI 2026] 3D and 4D World Modeling: A Survey

Paper: 3D and 4D World Modeling: A Survey

HTML

869★

alibaba-damo-academy/RynnBrain

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models

Paper: RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundat

800★

Robbyant/lingbot-vla-v2

From Foundation to Application

Paper: From Foundation to Application: Improving VLA Models in Practice