Robotics

Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz

Optimal Reciprocal Collision Avoidance in Three Dimensions (C++)

NVIDIA Alpamayo 2 Super is an open 34B multi-task foundation model designed to supercharge autonomous vehicle development.

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

Object picking and stowing with a 6-DOF KUKA Robot using ROS

ros2_medkit - diagnostics gateway for ROS 2 robots. Faults, live data, operations, scripts, locking, triggers, and OTA updates via REST API. No SSH, no custom tooling.

UMI-3D SLAM and Data Processing Pipeline: https://umi-3d.github.io/

Web-based MuJoCo viewer powered by Viser

a Lightweight Motion Planning Package

NVIDIA-accelerated packages for arm motion planning and control

Python SDK for LuckyEngine robotics simulation

A fruit fly connectome as a drone pilot. Camera -> fly eyes -> spiking brain -> descending neurons -> drone. Live 3D demo in your browser.

Browser teleoperation data for embodied AI — elizaOS-ready episodes, trajectory_db converter, onchain provenance. The fuel station for agent robot stacks.

ROS2 control package for Mujoco simulation physics simulator, including plugins for various sensors, RGB-D cameras, and lidar.

ROS package used to create an endpoint to accept ROS messages sent from a Unity scene using the ROS TCP Connector scripts

Python wrapper over OpenRave's IKFast inverse kinematics solver for a UR5 robot arm.

100+ robotics algorithms in Rust: planning, localization, SLAM, control, and benchmarks.

The LLVM for Robot Descriptions. A programmable IR engine to compose, validate, and compile URDF/XACRO/SRDF models from Python or Blender.

Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models

Open-source 7DoF 3D-printable robotic arm with LeRobot integration.

Cross-Cluster Embodied Intelligence Cloud-Native Platform. Manage cross-cluster embodied AI workloads with Kubernetes-native CRDs, unified job scheduling, cross-cluster Pod networking, and multi-runtime support.

A simulation framework for Robotic Mobile Fulfillment Systems

Evidence-first runtime for a wheeled mobile household robot with bounded actions, replayable events, and fail-closed verification.

What's the simplest possible AI robot that learns everything from scratch?

A C and Python library for physically accurate, real-time, sensor simulation and visualization using NVIDIA Omniverse RTX

A unified inference runtime for VLA models.

[ICRA 2024] Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning

Open Source Java Framework for Robotics and Creative Machine Control

76 audit-ready Claude skills automating the industrial robot, cobot, AMR, ROS2, V&V, AI/ML, and IEC 62443 lifecycle. 38 builder + reviewer pairs anchored to ISO 10218, 13849, 62061, 12100, 9283, 15066, 3691-4, and IEC 62443.

Cross-Platform, Multi-Use Motion Profiling and Trajectory Generation

Motion Planning Networks

Code for "PHUMA: Physically Reliable Humanoid Locomotion Dataset" (CoRL 2026)

FurnitureBench: Real-World Furniture Assembly Benchmark (RSS 2023)

A selection of state-of-the-art research materials on decision making and motion planning.

Official code for "OpenWAM: An Open Framework for Composable World-Action Models" (Stanford University)

🤖🐑 It's a sheep, it's a dolly, it's a following robot. Dolly was born to be cloned.

Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution.

Artificial Intelligence for Kinematics, Dynamics, and Optimization

An end-to-end, GPU-accelerated, and modular platform for building generalized Embodied Intelligence.

Model Predictive Path Integral Control (MPPI) with PyTorch

The 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.

Experimental Drosophila-inspired camera-to-robot bridge. Working mock neural backend, optical flow, IMU feedback and UDP motor control. MaleCNS integration planned.

Flex-π: A multi-stream world-action model with compute flexibility: one checkpoint that deploys as a VLA, a full world model, or anything in between.

Agent skill for production-grade ROS 2 development. Progressive-disclosure SKILL.md covering workspace, nodes, executors, QoS, ros2_control, Nav2, MoveIt 2, real-time, and deployment. Works with Claude Code, Codex, Cursor, Gemini CLI.

STM32F446RE+ROS1 racing robot: RPLIDAR C1 + IMU, Bluetooth comms, hector_slam mapping, PID motor control, and a custom move_base local planner optimized for high-speed go-and-return navigation via referee node.

A desk lamp that's learning to be more than a lamp

Camera calibration library with spline and parametric distortion models. Maximally powerful, minimally complex.

Memory-Dependent Manipulation Benchmark based on RoboTwin

adam implements a collection of algorithms for calculating rigid-body dynamics in Jax, CasADi, PyTorch, and Numpy.

Companion repository for “In-Context Learning for Robots: Methods and Applications” — methods, datasets, and benchmarks organized by taxonomy and release date.