rabbit os
The Large Action Model is the cornerstone of rabbit OS. LAM is a new type of foundation model that understands human intentions on computers. With LAM, rabbit OS understands what you say and gets things done.
how LAM + rabbit OS work:
01 intention
    rabbit OS will first understand what you mean by what you said. Human intentions are deeply personal, have layers, may be incomplete, and could change on a whim. rabbit OS uses its long-term memory of you to translate your requests into actionable steps and responses that LAM could leverage in real-time.
02 interface
    LAM then comprehends how applications and services you use daily instead of relying on application programming interfaces (APIs). LAM can learn to see and act in the world like humans do. LAM has seen most interfaces of consumer applications on the internet and is more capable as we feed it with more data of actions taken on them.
03 interaction
    LAM completes these tasks for you on virtual environments in our cloud, from basic tasks such as booking a flight or reservation to complex ones like editing images on Photoshop or streaming music and movies. There is no need for a complex local setup, such as installing an app, a Chrome plugin, or typing code into a command line. Simply talk to rabbit OS, and it will carry out the tasks for you.
the rabbithole
The rabbithole is an all-in-one web portal to manage your relationship with rabbit OS, and your companion device.

rabbit OS operates apps on our secured cloud, so you don’t have to. Log into the apps you’d like rabbit to use on your system through the rabbithole to relay control. You only need to do this once per app.

Manage your preferences and r1 devices, from initial linking, personal information & clearing data, to factory reset.

View your past interactions with r1: conversations, reports, images taken by the eye, app receipts, and more.

connect your accounts
We support the best apps you’ve always liked to use, with no need for additional subscriptions or siloed experiences with limited features.

map research
generative AI
experimental teach mode
We envision a truly personalized, accessible rabbit OS. To do so, we want everyone to train their LAM. Introducing teach mode, where anyone can create their LAM-powered rabbits without any programming experience. Record your actions, explain them with your voice, and play them to rabbit OS. LAM will learn the nuances and create a rabbit that can be applied to various scenarios.
What if you create a rabbit that could be useful to others? You can monetize and distribute it on our upcoming rabbit store.

rabbit r1