Skip to main content
Once you have a browser session, you can control it in several ways. Pick the approach that matches how much logic you want Anchor to handle.

Natural language

Send a plain-English instruction and let an AI agent navigate, click, and extract for you. Same capability via the SDK (agent.task) or the Perform Web Task REST endpoint.

Your own code

Connect with Playwright or Puppeteer over CDP and write the automation yourself. Full control over every step.

REST API

Call HTTP endpoints for screenshots, page content, PDFs, and perform-web-task — no SDK required.

OS-level control

Drive the session with mouse, keyboard, and screen coordinates. Used by computer-use agents and vision models.

​
REST API

Anchor exposes browser actions as REST endpoints you can call from any language or agent framework. Pass an optional sessionId query parameter to run on an existing session; omit it and Anchor provisions a browser for the request.

​
AI endpoints

See Perform Web Task for SDK usage, agent options, and Async execution for the async flow.

​
Page endpoints

The Screenshot Webpage endpoint does not support PDF URLs. Use Get Webpage Content to extract text from PDFs.

​
Session-less fetch

See API Quick Start for authentication and your first REST call. To expose Anchor from Cursor, Claude, or other agent tools, see MCP integration.

​
Compiled workflows

For repeatable, versioned flows — not one-off session control — see Automation Tasks. Use Which task type? to compare Perform Web Task with Automation Tasks.