Kubernetes-native IoT gateway

Copper is an operating system for robots - build, run, and replay your entire robot deterministically.

Mosaico - The data platform for Physical AI

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

Collection of best practices, reference architectures, model training examples and utilities to train large models on AWS.

🦾 Runtime for Physical AI. Connect streams. Detect events. Control your world.

Open-source MAVLink fleet operations platform for PX4 drones, SITL, drone shows, SAR, and cooperative autonomy.

CLI for Robot Training and Deployment

A curated list of academic papers and resources on Physical AI — focusing on Vision-Language-Action (VLA) models, world models, embodied ai, and robotic foundation models.

Curated embodied AI list: surveys, VLA models, datasets, simulators, humanoids, robot learning, and safety resources.

A C and Python library for physically accurate, real-time, sensor simulation and visualization using NVIDIA Omniverse RTX

ROBOTIS Physical AI Tools: Physical AI Development Interface with LeRobot and ROS 2

Robotics Data Toolkit | Convert between robotics dataset formats (RLDS, LeRobot v2/v3, Zarr, HDF5, Rosbag). Inspect, visualize, and analyze datasets. Works with HuggingFace Hub. Built for OpenVLA, Octo, LeRobot, and Diffusion Policy workflows.

A curated list of research and projects on world models

Visual Asset Management System (VAMS) is a purpose-built, AWS native solution for the management and distribution of traditional to specialized visual assets used in physical AI and spatial computing.

Harness framework to build world model based workflows for physical AI systems.

The open infrastructure for Physical Intelligence. ROSClaw grounds AI agents into the physical world through e-URDF, sandbox safety, capability providers, praxis capture, memory, runtime intervention, and self-evolving skills.

A curated list of Robotics + AI resources to learn, build, deploy, and stay current in Physical AI / Embodied AI. 🌟 Star if you like it!

🔥PhysInOne in Python (CVPR 2026)

Pelican-VL 1.0 is a new family of open-source embodied brain models with parameter scales ranging from 7B to 72B developed by WFM System Group, Beijing Innovation Center of Humanoid Robotics (X-Humanoid).