Stars
A system identification framework for robots
agent-from-scratch is a Python-based repository designed for developers and researchers interested in understanding the inner workings of single and multi-agent systems
Sample code for Agibot AgentSDK
Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe
Learning High-Frequency Continuous Action Chunks in Latent Space (ICML'26)
EmbodiedAgents is a fully-loaded ROS2 based framework for creating interactive physical agents that can understand, remember, and act upon contextual information from their environment.
Principia is an open-source CLI tool for building robotics simulations from natural language.
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
[CVPR 2026] Official implementation of "ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models"
Dependency-free C++11 & Python SDK for low-level motion control of LimX robots — cross-platform (Linux x86_64/aarch64, Windows), integrates with ROS/Gazebo and RL-based sim-to-real deployment.
Official home of the LimX Dynamics open-source ecosystem — humanoid robots, legged robots, locomotion & manipulation, and embodied AI.
Python RL deployment for LimX humanoid — ONNX runtime, MuJoCo sim & real-robot
Monorepo for all Pupperv3 public code
HOI-Retarget: Contact-Centric Retargeting for Human-Object Interaction
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots
maxwellrobotics / g1-ros2
Forked from Adyansh04/grove-g1An autonomy stack for the Unitree G1 humanoid, built on ROS 2.
Autonomous indoor guide robot for EMINES/UM6P campus — ROS2 SLAM + Nav2 navigation + multilingual AI chatbot (GPT-4o-mini, Whisper, Cartesia TTS) with voice/text interface. Built with Arduino, LD06…
Algorithm to filter noisy signals for high precision and responsiveness.
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
Markerless kinematics with any cameras — From 2D Pose estimation to 3D OpenSim motion
This repository builds on the Genesis framework for training and simulating reinforcement learning policies. It includes Unitree Go2–specific modifications focused on locomotion, with the goal of i…
[ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.
Reference workflow for generating large amounts of synthetic motion trajectories for robot manipulation from a few human demonstrations.