What does Meta's Muse agent actually do for you?

Meta has introduced Muse, a personal AI agent that runs on its own secure virtual machine and can take actions across the apps you use daily. It handles tasks like booking travel or selling a car, keeps working after you close the app, and remembers details you mentioned once to make unprompted suggestions.

How the Agent Gets Things Done

Muse runs on Muse Spark, Meta's most capable model to date, built for real-world agentic work. You tell it what needs doing in the Muse app or directly in WhatsApp. The agent then opens a browser, fills out forms, and negotiates on your behalf. It can send an email, book travel, or sell a car for more money than you might get alone. It can lower a bill or adjust a training plan as the rest of your life shifts.

It keeps working after you close the app. The agent returns when something changes or when it needs approval before sending an email or making a purchase. It remembers what matters. A recipe reel saved on Instagram becomes a grocery list. A dinner party menu appears with friends' dietary restrictions already noted. Suggestions arrive unprompted, built on details mentioned once.

The Secure Computer Behind the Agent

Personal agents need a new kind of secure computer, so Meta built one for everyone. Muse runs on Muse Secure VM, a dedicated virtual machine that houses both the agent and your data. This VM lives in the cloud on its own dedicated computer, contained so no one else's agent can reach it. That is where the data and credentials for any service you connect are securely stored.

A separate Sentinel agent runs on that same machine, kept apart from Muse at the system level. Nothing Muse does reaches the internet unless the Sentinel approves it, and it asks you for permission when needed. Muse has no visibility into your passwords or payment methods. Any credentials you share go into secure storage, so Muse can use them without seeing them, including passwords you type into the browser yourself.

What You Control

You choose which apps Muse connects to and exactly how much access it gets. For email, you decide whether Muse reads mail or can also send on your behalf. Access can be changed or a service disconnected at any time. You can also opt out of your interactions being used to train Meta's AI models.

A complete audit trail shows everything the agent has done and plans to do. Conversations and VM data never reach Meta's ad systems. You can always tell Muse to forget specific things it has learned. Control stays with you.

Payments and Purchase Protections

When it comes time to pay, Muse can checkout with Link built by Stripe. It is the first AI agent covered by Link's purchase protections. Those include free coverage for damaged or lost items and price drops. They also include no-fee returns and a return guarantee on eligible purchases. Link's wallet for agents generates a one-time-use card so your real card details stay hidden, allowing safe purchases across the internet.

Shop Pay is coming soon, along with 1Password support so Muse can use logins you already have.

What Comes Later This Year

Later this year, Meta will introduce Muse Confidential VM, where the whole VM, including your data and conversations with Muse, is encrypted with a key only you hold, so not even Meta can access it. Muse is rolling out in the US on iOS, Android, and muse.ai, and coming soon to AI glasses. It's free for most of what people need, with subscription plans for people who want to do more.