​

Browser-act

• Agent CLI is for AI agents that need to operate browsers through a safe command-line runtime.
• Workflow is for users and teams that want hosted visual browser automation.

​

Start with the Agent CLI

​

Shortest path

browser-act get-skills core --skill-version <version>
browser-act browser list
browser-act --session my-task browser open <browser-id> https://example.com
browser-act --session my-task state
browser-act --session my-task click 2

​

Where to start

• Introduction: Learn what Browser-act gives AI agents.
• Installation: Install the CLI, add the entry Skill, and verify the runtime.
• Quick Start: Get the first extraction or browser interaction running in 60 seconds.
• First workflow guide: Open the existing Workflow learning material.