Trending Robotics Repos

🦀 Jumper — an crab robot.

A robotic harness that gives LLM agents a visual-geometric control panel so that they can directly understand and invoke embodied tasks.

Animated 3D robot heads for React: TV-headed bots with LED faces that show what your agent is doing.

Build your own robot duck. XGO-Duck is a 3D-printable biped powered by Arduino UNO Q and 15 servos, adapted from Pollen Robotics' Microduck. Includes mechanical models, PCB designs, a BOM, and an assembly guide. Build it, explore its motion, and make it your own.

Eyes are All JEV Needs - real time visual devisions from RGB, video and RGB-D cameras.

A controllable benchmark for robotic manipulation

Official codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It

Embodied In-Context Learning for GPT-6 Astra

EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs

LLM-first, 3D-native robotics and simulation workspace.

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

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

ROS 2 and NVIDIA Isaac Sim based air-ground cooperative delivery system with robotic grasping and UAV visual alignment.

An embodied neural experiment connecting a simulated ant to a synthetic neural controller

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

FLUX 3 Action: open weights 7B world action model from Black Forest Labs. Train, fine-tune and run action prediction for robots (DROID, SO-101), simulators and games.

A library of experiments using frontier LLMs/VLMs for robotics tasks, currently focusing on GPT-6 Astra.

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

HOI-Retarget: Contact-Centric Retargeting for Human-Object Interaction

Robô de bancada com ESP32: rosto animado no OLED, conversa por voz em pt-BR, jogos e controle do Mac

Argus is an open source dataset-and-format-agnostic harness for the densest annotation of robot learning data.

Official reinforcement learning training framework for Asimov humanoid robots, built on Isaac Lab.

A small desk robot with a face, a voice, and a camera. ESP32 body, Python brain, Rocky from Project Hail Mary.

🦀 Appearance and scene design for Jumper, an open-source crab robot.

SONIC adpation for new full size humanoid agibot A3！

Machines you can take apart in your browser: fusion reactor, Raptor 3, Cybertruck, humanoid, black hole, fighter jet engine, F1 car, drone. Three.js, procedural, real physics.

A harness for embodied intelligence — connecting agents, robot skills and the physical world through execution, feedback and recovery.

A Qualifying Exam for Coding Agent as Robot Learning Engineers

[IROS 2026] ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation

EmbodiedUE is an open-source reinforcement learning framework for Unreal Engine with robot training and in-game policy deployment.