Why Are OpenAI, Meta and xAI Giving AI Agents Their Own Computers?

Ask people to picture an AI agent taking over their tasks and many will imagine a cursor moving around their laptop, opening a browser and typing into their apps. OpenAI, Meta and xAI are taking a different route: give the agent a computer of its own.

OpenAI introduced Dots at DevDay on Sept. 29, following Meta’s Muse on Sept. 8 and xAI’s Grok Bot, which entered beta on Aug. 11. The implementations differ, but each gives an agent a remote environment where it can continue working after you close your laptop.

The appeal is obvious. The agent gets a place to work without taking over the machine sitting in front of you. The harder question is what happens when that remote computer becomes connected to everything the agent needs to do its job.

Why Put An Agent On A Separate Computer?

A dedicated cloud machine lets an agent keep working in the background without tying up your laptop or automatically exposing the files and browser sessions already open on it.

Meta’s Muse runs inside what the company calls a Secure VM, with a separate approval layer called Sentinel controlling what the agent can access outside the environment. “Dots are persistent agents with connected apps and their own cloud computer,” OpenAI says.

Proactive research starts with read-only access, while actions such as sending messages, editing files or controlling a user’s computer require additional permission. The separation creates a boundary around the agent’s computing environment.

“Muse runs on its own dedicated computer in the cloud, contained so no one else’s agent can reach it,” Meta says in its Muse launch announcement. It does not, by itself, create a boundary around everything the agent is allowed to access.

Isolated Hardware, Shared Keys: The Agent Security Trap

An agent becomes useful when it can reach the services where your work actually happens: email, files, calendars, messaging platforms and other connected applications. Those connections move authority into the agent’s environment even when the underlying computer is isolated.

OpenAI’s Dots can use existing plugin and data permissions granted through ChatGPT. “Muse has no visibility into people’s passwords or payment methods. Any credentials a person shares go into secure storage, so Muse can use them without seeing them,” Meta says.

“Every Bot on your account uses one persistent cloud computer. They share its files, browser sessions, and logins so they can hand work off. The computer is assigned per user, not per Bot. Do not use separate Bots as a security boundary,” xAI says in its Grok Bot FAQ.

xAI’s documentation says every bot created under an account uses the same persistent computer, including its files, browser sessions and logged-in application credentials. The company specifically warns users not to treat separate bots as a security boundary. So creating one bot for work and another for a different purpose does not, by itself, create two isolated environments on Grok.

Meta has encountered a different kind of data-flow problem. The company disclosed an incident involving its Marketplace integration in which addresses were shared in ways users did not expect. That does not show that Muse’s virtual-machine isolation failed. It shows something narrower: keeping an agent’s compute environment separate does not guarantee that information moving through connected services will stay inside the boundaries a user expects.

What Happens To The Agent’s Files And History?

Persistence creates another question as these systems move from short tasks to long-running work: what remains in the agent’s environment after the task ends?

xAI’s documentation provides the clearest answer among the three. Terminating a computer ends the current session but preserves its durable disk, including synced bots, files and saved logins. Starting another computer restores that material. Deleting a bot removes its profile and conversation history, but files and logins stored on the shared computer can remain.

“Deleting a Bot does not remove shared-computer files or browser sessions,” xAI says in its security documentation. The supplied OpenAI and Meta material does not provide comparably detailed answers about exporting everything an agent has accumulated, what persists after a plan is cancelled or how completely a user can move that working context to another provider.

Those questions become more consequential as agents spend weeks or months inside these environments rather than minutes answering a prompt. It is about whether the remote computer becomes a long-term store of your files, authenticated sessions and working history.

The unanswered question is what happens when you want to leave: what can you take with you, what remains behind, and how much of the agent’s accumulated working context can actually be separated from the platform that hosted it?