agent-browser

agent-browser enables you to script browser automation through an AI-powered agent that operates in isolated containers for security and reliability. Control web interactions—clicks, text input, form handling—programmatically without manual intervention. Built for customization and ease of understanding, it's designed as a lightweight foundation for browser-based automation workflows.

agent-browser is an AI-powered browser automation tool that enables you to script web interactions programmatically. It lets you automate clicking, typing, form submission, and other browser actions without manual intervention. The tool operates in isolated containers for security and reliability, making it a lightweight foundation for browser-based automation workflows that you can customize and extend.

AI-generated summary based on this skill's SKILL.md

★ 30,388 ⁮ 12,873 MIT updated 2026-07-27 by nanocoai

Install

nanocoai/nanoclaw/agent-browser · repository language: TypeScript

Manual (git clone) CLI (skillfed)coming soon

git clone https://github.com/nanocoai/nanoclaw
cp -r nanoclaw/container/skills/agent-browser ~/.claude/skills/agent-browser

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

What is agent-browser and what can it do?

How do I automate clicking and filling forms with agent-browser?

agent-browser allows you to automate clicking and filling forms by scripting browser interactions through its AI-powered agent. You can programmatically control text input, form handling, and submission without needing to manually interact with the web page. The tool is designed for ease of understanding and customization, so you can build automation workflows tailored to your specific form-filling needs.

Can agent-browser extract data and content from web pages?

Yes, agent-browser supports data extraction and content scraping from web pages programmatically. You can use it to retrieve information from websites automatically as part of your automation workflows. Combined with its ability to navigate and interact with pages, agent-browser provides a complete solution for extracting data alongside automating web interactions.

Is agent-browser suitable for automated web testing?

agent-browser is well-suited for testing web applications and pages through automated workflows. You can script interactions like clicking, typing, and form submission to validate web app behavior, and the tool's operation in isolated containers ensures security and reliability during test execution. This makes it effective for building repeatable, automated test scenarios.

What are the security features of agent-browser?

agent-browser operates in isolated containers, which provides security and reliability for your automation tasks. This containerized approach protects your system and data while running browser automation workflows. The tool is built with security in mind as a foundation for safe, repeatable browser-based automation.

Can agent-browser take screenshots and capture PDFs of websites?

agent-browser supports capturing screenshots and PDFs of web pages automatically as part of your navigation and automation workflows. You can navigate websites and generate visual snapshots or document captures programmatically, making it useful for documentation, testing, or monitoring purposes alongside your other automation tasks.

SKILL.md

rendered from the published skill — quoted content, verbatim

Browser Automation with agent-browser

Quick start

agent-browser open &lt;url&gt;        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

Navigate: agent-browser open <url>
Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
Interact using refs from the snapshot
Re-snapshot after navigation or significant DOM changes

Commands

Navigation

agent-browser open &lt;url&gt;      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser

Snapshot (page

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 1 file

container/skills/agent-browser/SKILL.md

All skills by nanocoai → Best browser automation skills for AI agents - SkillFed →