Video-Action Models for Generalizable Robot Control Beyond VLAs

Official code and data from DexWM ("World Models Can Leverage Human Videos for Dexterous Manipulation").

A minimalist mobile bimanual robot tutorial - hardware, data, model training and inference.

LeflexiTac: Giving robots a sense of touch.

[RSS'26] HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

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

OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

IronClaw is an Agent OS focused on privacy, security and extensibility

EgoVerse: Egocentric Data for Robot Learning from Around the World

Official implementation of Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data

AI agents running research on single-GPU nanochat training automatically

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

[CVPR 2026 Highlight] XL-VLA: Cross-Hand Latent Representation for Vision-Language-Action Models

A community collection of OpenClaw use cases for making life easier.

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

[ICLR'26] This repository is the implementation of "3D Aware Region Prompted Vision Language Model"

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…

Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr0…

LAP: Language-Action Pre-Training Enables Zero-Shot Cross Embodiment Transfer

A general physic-based retargeting framework.

Flow Policy Gradients for Robot Control

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

Masked Depth Modeling for Spatial Perception