AutoClaw is a hyper-lightweight AI agent designed to live inside Docker containers. Unlike heavy, GUI-dependent agents, AutoClaw is built for headless, massive-scale concurrency.

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

Planning Algorithm for All-Wheel-Steering Platforms

Library for logging of numeric data to HDF5 MAT-files, which is RT-safe and multithreaded.

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Robust Convex Model Predictive Control with collision avoidance guarantees for robot manipulators

An open-source library for GPU-accelerated robot learning and sim-to-real transfer.

[RSS 2025] "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills"

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

Open Source Visual Servoing Platform

Action Chunking Transformer implementation for low cost robot

Official implementation of OpenWBT.

MoveIt kinematics_base plugin based on particle optimization & GA

Public Repository for the Wrappers for ROS1 for RelaxedIK

CUDA Accelerated Robot Library

[RSS 2025] Learning Getting-Up Policies for Real-World Humanoid Robots

A C++ library for interacting with JSON.

The official instructions of HOI4D dataset.

RelaxedIK Solver

[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

HumanML3D: A large and diverse 3d human motion-language dataset.

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.