I tried this myself - my conclusion was the overhead of parsing a screenshot, generating an action, and being limited to headful mode is much less efficient than reading accessibility trees & generating CDP commands.
basically, browser automation is a closer-to-the-metal abstraction than computer use, allows more flexibility, and ends up being much cheaper at scale!
If agents need to run on the desktop or logged into a user's real browser, the alternative would be Ui.Vision MCP. But stagehand is designed for backend use, so apples and oranges.
I tried this myself - my conclusion was the overhead of parsing a screenshot, generating an action, and being limited to headful mode is much less efficient than reading accessibility trees & generating CDP commands.
basically, browser automation is a closer-to-the-metal abstraction than computer use, allows more flexibility, and ends up being much cheaper at scale!
Astra with computer use seems to burn a ton of tokens though. Stagehand seems more token efficient.
If agents need to run on the desktop or logged into a user's real browser, the alternative would be Ui.Vision MCP. But stagehand is designed for backend use, so apples and oranges.
Money?