Editable scientific figures in PowerPoint and draw.io via Codex/MCP with Designer-Drawer-Reviewer-Corrector quality gates.

ROS 2 Jazzy autonomy stack for a mecanum-wheeled platform, extended as a bridge between Habitat and the real robot. Converts panoramic images and lidar scans into RGB-D with matching config, runs p…

Self-evolving runtime infrastructure for Physical AI and embodied agents. Ground AI agents into robot bodies with e-URDF, sandbox safety, capability routing, praxis capture, physical memory, runtim…

A feed-forward 3D foundation model for reconstructing scenes from streaming data

A unified, agentic system for general-purpose robots, enabling multi-modal perception, mapping and localization, and autonomous mobility and manipulation, with intelligent interaction with users.

Describe Anything, Anywhere, at Any Moment (DAAAM), a novel approach to real-time, large-scale, spatio-temporal memory

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"

The fastest repo in history to surpass 50K stars ⭐, reaching the milestone in just 2 hours after publication. Better Harness Tools, not merely storing the archive of leaked Claude Code but also mak…

Use Garry Tan's exact Claude Code setup: 10 opinionated tools that serve as CEO, Eng Manager, Release Manager, Doc Engineer, and QA

Dynamic MBTI Personality Simulation for LLM Agents via Carl Jung's Theory. A framework that enables LLM agents' MBTI personalities to naturally evolve and grow through interaction.

Dimensional is the agentic operating system for physical space. Vibecode humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seam…

AI agents running research on single-GPU nanochat training automatically

High-performance control stack for Embodied AI powered by the OpenClaw ecosystem. Designed for high-dynamic platforms including Humanoids and Quadrupeds, this repo provides unified whole-body contr…

Ngine is a modular, environment-agnostic engine for embodied AI research, unifying diverse robot embodiments (like Unitree and Franka) across multiple simulators. Built on Isaac Lab–Arena, it offer…

[RA-L'25] An Reliable and Efficient Framework for Zero-Shot Object Navigation

SpatialLM: Training Large Language Models for Structured Indoor Modeling

[RSS'25] This repository is the implementation of "NaVILA: Legged Robot Vision-Language-Action Model for Navigation"

Official implementation of OpenWBT.

Adaptive Runtime AUTOSAR Linux Simulator

Low-level locomotion policy training in Isaac Lab

[ECCV 2024 Oral] Code for RPBG: Towards Robust Neural Point-based Graphics in the Wild.

[ICRA2023] Implementation of Visual Language Maps for Robot Navigation

杭州电子科技大学硕士学位论文LaTeX模版

旨在帮助杭州电子科技大学硕博生使用 Latex完成学位论文撰写，非官方模板，如若使用，后果自负！

V2X Hub is a message handler that acts as a translator and data aggregator/disseminator for infrastructure components of a connected vehicle deployment.