Agent Browser Automation

This is a Rust-based headless browser CLI that wraps Chrome DevTools Protocol for AI agents. Instead of dealing with Playwright or Puppeteer runtimes, you get a single binary with commands like `agent-browser snapshot` to grab accessibility trees with `@ref` IDs, then `agent-browser click @e2` to act on them. It's optimized for AI workflows with semantic locators, batch command execution via JSON, and network interception. The snapshot output is genuinely clean for LLM consumption, and being native Rust means it's fast and doesn't require a Node environment. Good pick if you're building agents that need reliable web interaction without the usual JavaScript toolchain overhead.

skills.sh installs: 1.9K
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill agent-browser-automation --agent claude-code

Installs into .claude/skills of the current project.

Files

agent-browser

Skill by ara.so — Daily 2026 Skills collection.

agent-browser is a headless browser automation CLI built in Rust, designed for AI agents. It wraps Chrome via the Chrome DevTools Protocol (CDP) and exposes a fast, ergonomic command-line interface for navigation, interaction, accessibility snapshots, screenshots, network interception, and more — with no Node.js or Playwright runtime required.

Installation

Recommended (npm global)

npm install -g agent-browser
agent-browser install  # Download Chrome for Testing (first time only)

macOS (Homebrew)

brew install agent-browser
agent-browser install

Rust / Cargo

cargo install agent-browser
agent-browser install

Local project dependency

npm install agent-browser
# Add to package.json scripts or invoke via npx

Linux (with system dependencies)

agent-browser install --with-deps

Quick Start

SKILL.md on GitHub

Details

Repository: github.com/aradotso/trending-skills
Categories: AI & Agent Building, Automation & Workflows
First seen: Apr 16, 2026