EgoVerse: Egocentric Data for Robot Learning from Around the World

Lets make video diffusion practical!

Memory-Dependent Manipulation Benchmark based on RoboTwin

Enjoy the magic of Diffusion models!

HaMeR: Reconstructing Hands in 3D with Transformers

AI agents running research on single-GPU nanochat training automatically

GigaWorld-Policy: An Efficient Action-Centered World–Action Model

Official code of Motus: A Unified Latent Action World Model

Distributed, scalable benchmarking of generalist robot policies.

A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

[CVPR 2026] UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos

Wan: Open and Advanced Large-Scale Video Generative Models

CLI-Anything: Making ALL Software Agent-Native

[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Unified Codebase for Advanced World Models.

[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

Official repository of Utonia: Toward One Encoder for All Point Clouds

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos"

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…

Code for kai0, including training, inference and data collection.

RynnBrain: Open Embodied Foundation Models

[ICRA 2026 🥳] GarmentPile++: Affordance-Driven Cluttered Garments Retrieval with Vision-Language Reasoning

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

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

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