Human-Agent-Society/reef
Python
Infrastructure for continually self‑improving agents
Infrastructure for continually self‑improving agents
兴趣：multi-agent systems and LLM agents
GitHub 项目
phi-monster/Galahad
Python
A counterfactual battery for instruction following in vision-language-action policies: change one word of the instruction, hold the scene, and record which object the arm reaches. …
A counterfactual battery for instruction following in vision-language-action policies: change one word of the instruction, hold the scene, and record which object the arm reaches. Ships the deconfounded demonstration generators and their confounded control.
兴趣：vision-language-action (VLA) models and foundation models for robots
ZJU-OmniAI/vla-corrector
Python
[NeurIPS 2026] VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
[NeurIPS 2026] VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
兴趣：vision-language-action (VLA) models and foundation models for robots
OpenMOSS/EasyWAM
Python
A unified framework for training, fine-tuning, and evaluating World Action Models
A unified framework for training, fine-tuning, and evaluating World Action Models
兴趣：vision-language-action (VLA) models and foundation models for robots
deeplethe/utopia
Rust
World's first open-source enterprise world model.
World's first open-source enterprise world model.
兴趣：multi-agent systems and LLM agents
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
兴趣：vision-language-action (VLA) models and foundation models for robots
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.
兴趣：vision-language-action (VLA) models and foundation models for robots
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
兴趣：humanoid robots and whole-body control
rohitg00/ai-engineering-from-scratch
Python
Learn it. Build it. Ship it for others.
Learn it. Build it. Ship it for others.
兴趣：multi-agent systems and LLM agents
datawhalechina/every-embodied
Python
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
兴趣：world models and video prediction for embodied agents
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
兴趣：vision-language-action (VLA) models and foundation models for robots
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
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 and YAM.
兴趣：vision-language-action (VLA) models and foundation models for robots
mx-liu6/OptiGeo
Python
[CORL2026] Official implementation of the paper: "OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes"
[CORL2026] Official implementation of the paper: "OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes"
兴趣：3D perception, point clouds and scene understanding for robotics
RLinf/RLinf
Python
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
兴趣：vision-language-action (VLA) models and foundation models for robots
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
兴趣：imitation learning and diffusion policies for robot control
bojieli/ai-agent-book
Python
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
兴趣：multi-agent systems and LLM agents
dexmal/opendm
Python
An Open-World Foundation Model for General-Purpose Embodied Intelligence.
An Open-World Foundation Model for General-Purpose Embodied Intelligence.
兴趣：vision-language-action (VLA) models and foundation models for robots
shapsider/OmniJev
Python
OmniJev — multimodal finite-choice decision interface and MuJoCo embodied workbench: trajectory replays, decision probes, benchmark panels, 60s walkthrough.
OmniJev — multimodal finite-choice decision interface and MuJoCo embodied workbench: trajectory replays, decision probes, benchmark panels, 60s walkthrough.
兴趣：world models and video prediction for embodied agents
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.
兴趣：humanoid robots and whole-body control
1173591564/Dynamics-memory
TypeScript
LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamics + tension adjudication + causal-replay…
LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamics + tension adjudication + causal-replay evals.
兴趣：multi-agent systems and LLM agents
isaac-sim/IsaacLab
Python
Unified framework for robot learning with multi-physics/renderer support
Unified framework for robot learning with multi-physics/renderer support
兴趣：3D perception, point clouds and scene understanding for robotics
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.
兴趣：vision-language-action (VLA) models and foundation models for robots
RoboTwin-Platform/RMBench
Python
Memory-Dependent Manipulation Benchmark based on RoboTwin
Memory-Dependent Manipulation Benchmark based on RoboTwin
兴趣：robot manipulation and grasping with learned policies
earthtojake/text-to-cad
Python
A library of agent skills for CAD, CAE and CAM
A library of agent skills for CAD, CAE and CAM
兴趣：large language models for robot task planning and reasoning
OpenMOSS/Awesome-WAM
HTML
A curated collection of papers, explainers, and resources on World Action Models for embodied AI
A curated collection of papers, explainers, and resources on World Action Models for embodied AI
兴趣：world models and video prediction for embodied agents
OpenWAM-Official/OpenWAM
Python
Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".
Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".
兴趣：vision-language-action (VLA) models and foundation models for robots
verl-project/verl
Python
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
兴趣：vision-language-action (VLA) models and foundation models for robots
robocasa/robocasa
Python
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
兴趣：humanoid robots and whole-body control
3587jjh/HuRo
Python
HuRo: Robotizing Human Videos for Scalable VLA Pretraining (CoRL 2026)
HuRo: Robotizing Human Videos for Scalable VLA Pretraining (CoRL 2026)
兴趣：vision-language-action (VLA) models and foundation models for robots
