Continue your Atlas path← Agents and computer use
Initial research 2026-09-21MetaReleased 2026-09-08

Meta Muse

Inspect the documented capabilities, access conditions and sources for your task.

Initial research: 2026-09-21. Check current terms before choosing.

Automated fact checks · 4 fields

AI extraction with a second evidence validation pass. These dates apply to the listed fields.

  • Operate a web browser · 2026-09-28 · Source
  • Complete a multi-step workflow · 2026-09-28 · Source
  • Run in an isolated environment · 2026-09-28 · Source
  • Operate a computer interface · 2026-09-28 · Source

Updated

The facts

Version
1 (Muse Spark 1.3 model, 2026-09-02)
Price
From $20 per month. Subscription. Included usage and billing terms vary by plan.
API
✕Not supported
Open weights
✕Not supported
Commercial use
yes
Computer use
✓Supported

Muse runs on Muse Secure VM, a dedicated secure computer with its own browser, and works on a person's behalf across apps they use daily.

Source for Computer use (opens in a new tab)
Browser control
✓Supported

Muse runs on Muse Secure VM with its own dedicated browser and can open a browser, fill out forms, and negotiate on a person's behalf.

Source for Browser control (opens in a new tab)
Multi-step autonomy
✓Supported

Muse keeps working after people close the app, advances work on its own, and returns when something changes or needs approval.

Source for Multi-step autonomy (opens in a new tab)
Sandboxed execution
✓Supported

Muse runs on a dedicated virtual machine (Muse Secure VM) contained so no other agent can reach it, with a separate Sentinel agent approving all internet actions.

Source for Sandboxed execution (opens in a new tab)

From the publisher

Automatic source checks. These do not change the verification date of the facts above.

Sources

Beyond feature support

Quality evidence.

How well a model performs depends on the task, version, and settings.

We have not published a reviewed quality evaluation for these versions yet. Feature support and price do not establish output quality.

Try the same small task with each option. Check accuracy, consistency, and how much editing you need to get a usable result.

Start a conversation.