agent-browser

Automates browser interactions via a CLI using Chrome DevTools Protocol and accessibility-tree snapshots.

1|Updated Aug 11, 2026
One-click install
npx skills add https://github.com/Chia1104/agent-air --skill agent-browser-chia1104
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Chia1104/agent-air/tree/main/skills/shared/agent-browser
Command: npx skills add https://github.com/Chia1104/agent-air --skill agent-browser-chia1104

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser.

What problem does it solve? AI agents need a reliable way to interact with websites and desktop apps programmatically, but built-in browser tools are often slow, brittle, or unavailable. This Skill provides a fast browser automation CLI that lets agents navigate pages, fill forms, click elements, take screenshots, and extract data through Chrome/Chromium via CDP. ## Core Features & Use Cases - Browser Automation: Navigate pages, fill forms, click buttons, take screenshots, and scrape data using accessibility-tree snapshots with compact element refs. - Specialized Skills: Load dedicated workflows for Electron desktop apps (VS Code, Slack, Discord, Figma), Slack workspace automation, exploratory testing/QA, Vercel Sandbox microVMs, and AWS Bedrock AgentCore cloud browsers. - Sessions & Observability: Persistent sessions, authentication vault, state persistence, video recording, and an observability dashboard on port 4848. - Use Case: Ask your agent to log into a web app, fill out a multi-step form, and capture a screenshot of the confirmation page, all driven by the agent-browser CLI. ## Quick Start Ask your agent to open a website and take a screenshot using agent-browser, after installing it with npm i -g agent-browser and running agent-browser install.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser actions with an AI agent?▼

Install agent-browser globally with npm i -g agent-browser, run agent-browser install, then load workflows with agent-browser skills get core. The CLI controls Chrome/Chromium via CDP using accessibility-tree snapshots with element refs for reliable interaction.

What browser automation tool works without Playwright or Puppeteer?▼

agent-browser is a native Rust CLI that drives Chrome/Chromium directly through the Chrome DevTools Protocol, with no Playwright or Puppeteer dependency. It provides accessibility-tree snapshots and compact @eN element refs for agents.

Can agent-browser automate Electron desktop apps like VS Code or Slack?▼

Yes, load the electron specialized skill with agent-browser skills get electron to automate Electron apps such as VS Code, Slack, Discord, Figma, Notion, and Spotify. A separate slack skill covers Slack workspace automation.

Does agent-browser work with cloud browsers or sandboxed environments?▼

Yes, specialized skills support running agent-browser inside Vercel Sandbox microVMs and using AWS Bedrock AgentCore cloud browsers. Load them with agent-browser skills get vercel-sandbox or agentcore.

How do I monitor agent-browser sessions?▼

The observability dashboard runs independently of browser sessions on port 4848 and can be opened through a proxied URL. Session tabs, status, and stream traffic are proxied internally, so session ports do not need to be exposed.