Awesome Robotics Libraries

Simulation platform for general-purpose robotics & embodied AI learning.

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

Multi-Joint dynamics with Contact. A general purpose physics simulator.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

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

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

NVIDIA PhysX SDK

Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

Model-based design and verification for robotics.

GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.

CUDA Accelerated Robot Library

RL implementations

Converting Onshape assembly to robot definition (URDF, SDF, MuJoCo) through Onshape API

Analytical inverse kinematics for 6R and 7R revolute arms. Returns every IK branch at machine-precision FK closure. Ships per-arm build artifacts; covers non-Pieper 6R and non-SRS 7R geometries.

Simple kinematics calculation toolkit for robotics

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.

A lightweight toolkit for quantitatively scoring LeRobot episodes.