Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
HY-Embodied-0.5
Modelsimage text to text model by tencent · transformers
tencent/HY-Embodied-0.5 -
PhysicalAI-Robotics-GR00T-X-Embodiment-Sim
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim -
rai
AI repositoriesRAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.
git clone https://github.com/RobotecAI/rai.git -
awesome-llm-powered-agent
AI repositoriesAwesome things about LLM-powered agents. Papers / Repos / Blogs / ...
git clone https://github.com/hyp1231/awesome-llm-powered-agent.git -
Embody
MCP serversThe most comprehensive MCP toolkit for TouchDesigner
git clone https://github.com/dylanroscover/Embody.git -
embodied-first-exam
Agents & frameworksThe first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
git clone https://github.com/mll-lab-nu/embodied-first-exam.git -
Spotter
Agents & frameworksOfficial codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It
git clone https://github.com/zqc3117/Spotter.git -
awesome-physical-ai
Docs & tutorialsA curated list of Robotics + AI resources to learn, build, deploy, and stay current in Physical AI / Embodied AI. 🌟 Star if you like it!
git clone https://github.com/natnew/awesome-physical-ai.git -
OmniAction
Datasets & benchmarksHugging Face dataset by OpenMOSS-Team
OpenMOSS-Team/OmniAction -
Odyssey
Agents & frameworksOdyssey: Empowering Minecraft Agents with Open-World Skills
git clone https://github.com/zju-vipa/Odyssey.git -
VLA-Handbook
AI repositories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
git clone https://github.com/sou350121/VLA-Handbook.git -
cs249r_book
Agents & frameworksMachine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai
git clone https://github.com/harvard-edge/cs249r_book.git -
opentai.github.io
SkillsThe official website of the Open Trustworthy AI Community (OpenTAI).
git clone https://github.com/OpenTAI/opentai.github.io.git -
EgoStandard
Datasets & benchmarksHugging Face dataset by LightwheelAI
LightwheelAI/EgoStandard -
py-xiaozhi
MCP serversOpen-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction.
git clone https://github.com/huangjunsen0406/py-xiaozhi.git -
10Kh-RealOmin-OpenData
Datasets & benchmarksHugging Face dataset by genrobot2025
genrobot2025/10Kh-RealOmin-OpenData -
Embodify
MCP serversGive your agent a body: observe and control simulated robots (LIBERO, RoboDojo) over MCP.
embodify-mcp@0.1.0a2 -
EgoPro
Datasets & benchmarksHugging Face dataset by LightwheelAI
LightwheelAI/EgoPro -
pidog-embodiment
MCP servers🐕 Give your AI a physical body — speak German/French/English, it understands locally (Ollama or zero-LLM keyword mode) and acts. MCP server included: Claude Code/Desktop as the robot's brain. Brain/Body over HTTP for SunFounder PiDog, robot cars, any hardware. No cloud. Try it without a robot: install.sh --mock
git clone https://github.com/rockywuest/pidog-embodiment.git -
Sub-millisecond 7-DoF trajectory episode memory and kinematic safety gates for robotics.
-
GameScaling
Modelsimage text to text model by THUSI-Lab · transformers
THUSI-Lab/GameScaling -
Persistent 6-DoF SE(3) spatial world state, object trajectories, and affordances for robotics.
slashml-robotics@1.0.1 -
EgoDemo
Datasets & benchmarksHugging Face dataset by LightwheelAI
LightwheelAI/EgoDemo -
CaPtain
Agents & frameworksCaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters
git clone https://github.com/waltstephen/CaPtain.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.