Robots Tools

Aero Hand Open is a lightweight, open-source tendon-driven robotic hand. Fully 3D-printable and modular, it offers smooth, human-like motion with ESP32 and ROS2 support — an accessible platform for research, education, and prototyping.

We're taking Aloha to the next level with our new AI line of machine-learning hardware. Built from the ground up for even faster data collection and model evaluation.

Meet AIBI Pocket, a tiny AI companion that fits in your hand or attaches to your shirt. It recognizes you, chats with ChatGPT, rotates like a gimbal, shows weather with fun animations, provides reminders, and even plays with other AIBIs.

Unitree R1 is an ultra-lightweight, fully customizable humanoid robot for education, research, and industry. Features advanced power systems, flexible joints, modular design, and secondary development support.

Reachy Mini is an expressive, open-source robot kit by Pollen Robotics & Hugging Face. Designed for AI experimentation and creative coding, it's fully programmable in Python and deeply integrated with the HF ecosystem.

Gemini Robotics On-Device is Google's powerful VLA model, optimized to run locally on robots. It offers strong dexterity and fast task adaptation with minimal fine-tuning.

AI-powered robots for companionship, entertainment and customer service. Realbotix offers human-like robots for superior social interactions in a variety of settings that improve human experiences through connection, learning and play.

V-JEPA 2 is Meta's new world model, trained on video to understand and predict the physical world. It enables zero-shot robot planning and sets SOTA benchmarks in visual understanding. Model, code, and new benchmarks are now open.

SmolVLA is a compact (450M) open-source Vision-Language-Action model for robotics. Trained on community data, it runs on consumer hardware & outperforms larger models. Released with code & recipes.

An AI-driven robotic packing system using LLaMA and Hello Robot Stretch leverages vision and language planning to dynamically sequence items for optimal bag utilization—adapting in real time to any object to maximize packing efficiency and safety.