Sunday Robotics' ACT-1 is a robot foundation model trained on zero robot data, learning from humans via the Skill Capture Glove.

Product passport

Key facts are transcribed from official pages or public documentation. Access and pricing can change, so confirm them before acting.

Category: Robot Development
Maturityi: Available
Deploymenti: Not specified
Purchase access: Public purchase / signup
Official source: Official website
Verifiedi: Not yet verified

Reality check

The useful boundary is what works repeatedly in a real environment—not what looks impressive in a demo.

Works well when

Simulation, control, perception and repeatable experiments
Teams that can manage dependencies and hardware interfaces
Prototyping before committing to a physical deployment

Verify before buying

Supported hardware, GPU requirements and version compatibility
Documentation, examples and community response
How simulation results transfer to the real robot

Not a magic solution

A guarantee that simulation equals a production cell
A replacement for safety validation on hardware
A low-maintenance toolchain without version ownership

About

ACT-1 is a 2025 robot foundation model from Sunday Robotics, trained on zero robot data. Instead of scaling teleoperation data collected from the robot itself, it learns directly from humans wearing the company's Skill Capture Glove. Sunday Robotics states it owns the entire stack, including software, hardware, data, training, and model evaluation.