Memo
Memo is a wheeled home humanoid robot by Sunday Robotics that performs household chores including dishwashing, laundry folding, tidying, and bed-making. Standing 1.7 meters tall on a wheeled base, it uses Sunday's ACT-1 AI model trained on 10M+ household data episodes via the Skill Capture Glove. Beta program launched 2026.
Primary use case: Autonomous household chore assistance, including clearing tables, loading and running the dishwasher, making espresso, and folding socks.
Height
213.36 cm
Specifications
Physical
Height
213.36 cm
Locomotion
wheeled
Balance
static
Manipulation
Hand Type
unknown
Power & Autonomy
Autonomy Level
fully_autonomous
AI & Compute
AI Capabilities
manipulation, navigation, learning
Onboard Compute
not publicly disclosed; cloud-assisted AI with onboard real-time control stack
Commercial
Availability
not_available
Primary Use Case
Autonomous household chore assistance, including clearing tables, loading and running the dishwasher, making espresso, and folding socks.
Related news
Meta built a humanoid robot with Fourier Trump declared that a security risk three days earlier ...
Tesla will open Optimus reservations in December. Here's the fine print.
Inside Neura Robotics' massive physical AI strategy: more than humanoids
Physical Intelligence wants a $20 billion valuation. Here's the bull and bear case.
NVIDIA's massive robotics strategy: how all the puzzle pieces fit together
Matic Teases a Humanoid as It Looks Beyond Floor Cleaning
Matic, a home robotics company best known for its floor cleaning robot, released a teaser video showing a cap-wearing humanoid and a smaller robot with an arm, signaling its next phase focused on manipulation. Co-founder Mehul Nariyawala framed floor cleaning as the foundation for broader household robotics, but no specifications, pricing, or launch dates were disclosed. The article also notes a design connection: Sunday's founding designer Seungho Yang previously worked at Matic from 2018 to 2024.
The UMI Effect: Why Robotics Companies Are Building the Data Collector First
Robotics companies including Sunday Robotics, X Square Robot, and Reward AI are developing specialized data collection devices—gloves and wearable interfaces—that allow humans to demonstrate manipulation tasks without requiring a physical robot present. Sunday achieved 99.1% folding success using its Skill Capture Glove, while X Square reports 5.3x collection throughput improvement with TwinDEX, and Reward AI traces its Omnibody Hand to the DexCap research lineage. These approaches build on the 2024 UMI framework, treating data collection hardware as a core engineering decision that shapes the entire robot learning system.
Isomorphism Over Imitation: X Square Unveils TwinDEX to Bridge the Robot-Free Data Gap
X Square Robot unveiled TwinDEX, an isomorphic hardware-software platform that pairs a wearable exoskeleton with a matched three-finger robotic end effector, allowing policies to be trained on robot-free human demonstrations without complex retargeting. The system achieved up to 5.3x data collection throughput compared to conventional on-robot teleoperation and completed a 24-step autonomous chemistry experiment using only hundreds of exoskeleton demonstrations with zero on-robot training data.