Claude SDKs now ship built-in computer and browser use loops
- Source
- x.com
- Date
Building a computer-use agent used to mean writing the loop yourself: read Claude's requested action, translate each click or keystroke into a driver command, capture the result and send it back. The SDKs now ship that loop as built-in toolsets for both computer use and browser use, so developers plug in a driver instead of maintaining the glue code. That removes a common source of bugs in early agents, where action schemas drift from the driver's API. The timing lines up with Haiku 5.5, which Anthropic markets for computer use at a much lower price, so the cost and the boilerplate of running a screen-driving agent both dropped in the same week. Teams with hand-written loops should compare them against the SDK version before adding features.
Computer use and browser use toolsets are now built into the Python and TypeScript SDKs for Claude. The API tells you what Claude wants to click or type. Previously, you had to write your own loop and map clicks and keystrokes to commands, but the SDKs now run the loop and send actions to drivers.
Use a compatible driver from @browser_use, @browserbase, @e2b, @daytonaio, or write your own based on the example drivers in the quickstarts. Quickstart: https://t.co/R3lr1EV75I Docs: https://t.co/i6dmcD7kJP
Context
Anthropic's developer account ClaudeDevs says the Python and TypeScript SDKs (developer toolkits) for Claude now include built-in computer use and browser use toolsets. In its October 7 thread, the account explains that the API only tells a developer what Claude wants to click or type, and previously developers had to write their own loop and map those clicks and keystrokes to commands.
Now the SDKs run that loop and send actions to a driver, the component that actually controls a browser or machine. Compatible drivers are named from Browser Use, Browserbase, E2B and Daytona, or developers can write one from the quickstart examples. Anthropic's Haiku 5.5 page separately describes the SDK support as beta. The thread does not report reliability results; it describes removing a piece of boilerplate code.
Checking sign-in…
Loading comments…