Tech Station

GitHub 项目

2026-11-04 · 从 449 个候选中选出 30 个

新项目

最近一个月内创建
#12026-10-30★ 16新项目76

anashoussaini/Dexsuite

Python

A Modular Robot Simulation Framework for Dexterous Manipulation

A Modular Robot Simulation Framework for Dexterous Manipulation

dexterityimitation-learningreinforcement-learningroboticsrobotics-simulationsimulationrobotmanipulationdexterous

兴趣:robot manipulation and grasping with learned policies

#42026-10-12★ 328 +17新项目74

robosimstudio/robosimstudio

Python

An open agentic toolkit for physics-based Real2Sim of Robot Manipulation Tasks

An open agentic toolkit for physics-based Real2Sim of Robot Manipulation Tasks

agentinverse-physicsreal2simreal2sim2realroboticssimulationrobotmanipulation

兴趣:humanoid robots and whole-body control

#122026-10-05★ 223 +-13新项目70

AetherLabsAI/Video2World

Python

Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective

Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective

benchmarkcoding-agentembodied-aifoundation-modelsreal-to-simrobot-learningroboticssimulationrobotembodied

兴趣:world models and video prediction for embodied agents

#172026-10-21★ 29 +1新项目69

xuyicheng-zju/TARSphere

Python

A robot-oriented full-stack framework for long-horizon embodied agents in evolving physical and social environments.

A robot-oriented full-stack framework for long-horizon embodied agents in evolving physical and social environments.

benchmarkembodied-aiisaac-simroboticsrobotembodied

兴趣:world models and video prediction for embodied agents

#212026-10-29★ 51新项目68

cair-vinuni/roboworm

Python

RoboWorM: Evaluating Movement Realism, Consistency and Acceleration Affects in Embodied Video World Models

RoboWorM: Evaluating Movement Realism, Consistency and Acceleration Affects in Embodied Video World Models

roboticsvlaworld-modelsVLAembodied

兴趣:world models and video prediction for embodied agents

活跃 / 趋势项目

按相关度 + star 增速排序
#22026-09-16★ 80 +1275

waltstephen/CaPtain

Python

CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters

CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters

code-as-policyembodied-ailiberollm-agentrobot-learningroboticsvision-language-modelrobotembodied

兴趣:vision-language-action (VLA) models and foundation models for robots

#32024-12-08★ 4.4k +1174

datawhalechina/every-embodied

Jupyter Notebook

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

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

embodied-agentembodied-aiembodied-intelligenceopenvlasmolvlavision-language-action-modelVLAvision-language-actionembodied

兴趣:world models and video prediction for embodied agents

#52026-09-30★ 320 +1673

groundingpi/GroundingPI

Python

A 4B grounding foundation model for physical intelligence. Unifies detection, referring, pointing, OCR, GUI, and layout grounding, achieving SOTA overall across 34 benchmarks and i…

A 4B grounding foundation model for physical intelligence. Unifies detection, referring, pointing, OCR, GUI, and layout grounding, achieving SOTA overall across 34 benchmarks and improving robot generalization and data efficiency in controlled evaluations.

embodied-aigui-groundingobject-detectionocrphysical-intelligencepointingrobot-learningvision-language-modelrobotVLAembodied

兴趣:vision-language-action (VLA) models and foundation models for robots

#62026-08-29★ 106 +272

OpenBMB/SimpleMemVLA

Python

Native-video memory for vision-language-action models, using timestamped visual history and exact streaming inference for long-horizon robot manipulation.

Native-video memory for vision-language-action models, using timestamped visual history and exact streaming inference for long-horizon robot manipulation.

embodied-ailong-horizon-roboticsmultimodal-learningnative-video-memoryrobot-learningrobot-manipulationstreaming-inferencevideo-understandingrobotmanipulationVLAvision-language-actionembodied

兴趣:vision-language-action (VLA) models and foundation models for robots

#82025-10-09★ 3.9k +371

starVLA/starVLA

Python

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

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

robotic-foundation-modelroboticsvision-language-action-modelworld-action-modelvision-language-action

兴趣:vision-language-action (VLA) models and foundation models for robots

#92024-01-26★ 28.7k +2271

huggingface/lerobot

Python

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

兴趣:imitation learning and diffusion policies for robot control

#102025-08-14★ 5.6k +1271

RLinf/RLinf

Python

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

agentic-aiembodied-aireinforcement-learningrl-infrarlinfvla-rlVLAembodied

兴趣:vision-language-action (VLA) models and foundation models for robots

#112025-11-23★ 759 +170

sou350121/VLA-Handbook

HTML

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

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

chinesedeep-learningembodied-aillmrobot-learningroboticsvision-language-actionvlarobotVLAvision-language-actionembodied

兴趣:vision-language-action (VLA) models and foundation models for robots

#132025-07-30★ 759 +370

HorizonRobotics/HoloMotion

Python

A Foundation Model for Whole-Body Humanoid Control

A Foundation Model for Whole-Body Humanoid Control

foundation-modelshumanoid-robotmotion-trackingroboticswhole-body-controlrobothumanoid

兴趣:humanoid robots and whole-body control

#142024-02-29★ 17070

RobotControlStack/robot-control-stack

Python

A lean, ROS-free sim-to-real framework for training and deploying Vision-Language-Action (VLA) models and RL agents. Native MuJoCo Gymnasium wrappers with synchronous execution for…

A lean, ROS-free sim-to-real framework for training and deploying Vision-Language-Action (VLA) models and RL agents. Native MuJoCo Gymnasium wrappers with synchronous execution for Franka, UR5e, xArm, SO101, YAM and Rizon.

frankagymnasiummujocoreinforcement-learningrobot-learningrobot-manipulationsim-to-realvision-language-actions-modelsrobotmanipulationVLAvision-language-actionsim-to-real

兴趣:vision-language-action (VLA) models and foundation models for robots

#152026-09-08★ 7269

lok-i/vibe

Python

Post-training humanoid whole-body trackers for perceptive control tasks

Post-training humanoid whole-body trackers for perceptive control tasks

humanoid-controlmjlabperceptive-locomotionpporeinforcement-learningrobot-learningviberobothumanoidlocomotion

兴趣:humanoid robots and whole-body control

#162026-02-08★ 533 +569

XPolicyLab/XPolicyLab

Python

[IROS 26 ScaleInfra Workshop Best Tool Paper] Involving over 50 Advanced Manipulation Policies

[IROS 26 ScaleInfra Workshop Best Tool Paper] Involving over 50 Advanced Manipulation Policies

embodied-aimanipulationpolicymanipulationembodied

兴趣:robot manipulation and grasping with learned policies

#182025-04-04★ 1.9k68

RoboVerseOrg/RoboVerse

Python

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

imitation-learningreinforcement-learningroboticssimulationrobot

兴趣:imitation learning and diffusion policies for robot control

#192026-07-19★ 695 +268

RealXiaoze/humanoid-motion-intelligence

人形机器人运动智能论文、开源项目、产业与求职知识库

人形机器人运动智能论文、开源项目、产业与求职知识库

embodied-aihumanoid-roboticslocomotionmotion-controlreinforcement-learningrobot-learningsim2realvlarobotVLAhumanoidlocomotionembodied

兴趣:humanoid robots and whole-body control

#202024-05-11★ 1.9k +368

robocasa/robocasa

Python

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

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

humanoid-robotphysics-simulationrobot-learningroboticsrobothumanoid

兴趣:humanoid robots and whole-body control

#222026-06-26★ 729 +468

robocurve/inspect-robots

Python

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

benchmarkembodied-aievaluationphysical-airerunroboticsvision-language-actionvlaVLAvision-language-actionhumanoidembodied

兴趣:vision-language-action (VLA) models and foundation models for robots

#232025-09-11★ 7.5k +2268

vllm-project/vllm-omni

Python

A framework for efficient model inference with omni-modality models

A framework for efficient model inference with omni-modality models

audio-generationdiffusionimage-generationinferencemodel-servingmultimodalpytorchtransformer

兴趣:vision-language-action (VLA) models and foundation models for robots

#242026-04-22★ 25.4k +20767

earthtojake/text-to-cad

Python

Design physical products with AI

Design physical products with AI

agentsai-agentscadmechanical-engineeringroboticsstepstlstp

兴趣:humanoid robots and whole-body control

#252024-12-24★ 38767

manumerous/wb_humanoid_mpc

C++

Whole-Body Nonlinear MPC for Realtime Humanoid Loco-Manipulation Planning and Control

Whole-Body Nonlinear MPC for Realtime Humanoid Loco-Manipulation Planning and Control

aidata-generationhumanoidhumanoid-robotlocomotionmpcnonlinearoptimizationrobotmanipulationhumanoidlocomotion

兴趣:humanoid robots and whole-body control

#262024-09-29★ 3.7k +365

enactic/openarm

MDX

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

bilateral-teleoperationforce-feedbackgenesisgravity-compensationhumanoid-robotimitation-learningmachine-learningmoveit2robothumanoid

兴趣:humanoid robots and whole-body control

#272026-03-18★ 76.8k +31965

rohitg00/ai-engineering-from-scratch

Python

Learn AI Engineering! Learn it. Build it. Ship it for others.

Learn AI Engineering! Learn it. Build it. Ship it for others.

agentsaiai-agentsai-engineeringcomputer-visioncoursedeep-learningdsh

兴趣:multi-agent systems and LLM agents

#282026-08-29★ 174 +465

nssmd/RoboRSI

Python

Robot-agent harness with a CLI and local Web console for LIBERO short evaluation

Robot-agent harness with a CLI and local Web console for LIBERO short evaluation

agentsembodied-aievaluationliberorobot-learningroboticsself-evolutionrobotembodied

兴趣:multi-agent systems and LLM agents

#292026-03-29★ 76.3k +57265

calesthio/OpenMontage

Python

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into…

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

agentagentic-aiaiclaudecopilotcursorelevenlabsffmpeg

兴趣:world models and video prediction for embodied agents

#302022-11-16★ 8.6k +465

isaac-sim/IsaacLab

Python

Unified framework for robot learning with multi-physics/renderer support

Unified framework for robot learning with multi-physics/renderer support

isaac-simomniverse-kit-extensionrobot-learningroboticsrobot

兴趣:3D perception, point clouds and scene understanding for robotics