Use Case
Agent Browser is a powerful AI agent skill that extends your assistant with new capabilities. Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: we... This guide walks you through installing Agent Browser, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Agent Browser: npx clawhub@latest --dir ~/.claude/skills install agentic-browser
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to design & creative to trigger Agent Browser
Review the output and refine your prompt for better results
Combine Agent Browser with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Agent Browser
Help me get started with Agent Browser
What can Agent Browser do for my design & creative workflow?
Show me an example of using Agent Browser
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install agentic-browserOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install agentic-browserβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/agentic-browser/π‘Extract and place the folder at the path above, then restart your agent.