Claude Computer Use enables AI to control browsers through vision and reasoning in a continuous action loop.

Overview Copied

The Claude Computer Use integration connects Claude 3.5 Sonnet (and newer models) with Steel's browser infrastructure. This enables:

• Control Steel browser sessions via Claude's Computer Use API

• Execute browser actions like clicking, typing, and scrolling

• Automate complex web tasks and multi-step workflows

• Process visual feedback from screenshots

• Implement human verification for sensitive operations

Combining Claude's Computer Use with Steel gives you reliable automation with anti-bot capabilities, proxy support, and sandboxed environments.

Requirements & Limitations Copied

• Anthropic API Key: Access to Claude 3.5 Sonnet or newer models

• Steel API Key: Active subscription to Steel

• Python or Node.js Environment: Support for API clients for both services

• Supported Environments: Works best with Steel's browser environment

• Beta Status: Computer Use is currently in beta with some limitations

Documentation Copied

Quickstart Guide (Python) → Step-by-step guide to building Claude Computer Use agents with Steel sessions in Python.

Quickstart Guide (Node.js) → Step-by-step guide to building Claude Computer Use agents with Steel sessions in TypeScript & Node.js.

Additional Resources Copied

Anthropic Computer Use Documentation - Official documentation from Anthropic

Steel Sessions API Reference - Technical details for managing Steel browser sessions

Cookbook Recipe (Python) - Working, forkable examples of the integration in Python

Cookbook Recipe (Node.js) - Working, forkable examples of the integration in Node.js

Community Discord - Get help and share your implementations