mcpField
A
agent-browser

agent-browser

github.com/arize-aiAgent workflows12.1k77 installsUpdated today
Repository

About agent-browser

agent-browser is a browser automation CLI skill for AI agents, using Chrome or Chromium through CDP. It provides version-matched workflow instructions and specialized guidance for web pages, Electron apps, Slack, and testing tasks.

Key features

  1. 01Chrome and Chromium automation via CDP
  2. 02Accessibility snapshots with element references
  3. 03Session, authentication, and state management
  4. 04Video recording
  5. 05Specialized skills for Electron, Slack, and QA
  6. 06Version-matched guidance served by the CLI

Use cases

  1. 01Automating interactions with browser pages
  2. 02Operating Electron desktop applications
  3. 03Automating tasks in Slack workspaces
  4. 04Exploratory testing and bug hunting

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/arize-ai/phoenix --skill agent-browser

After installing, type/agent-browserin Claude Code to confirm it loaded.

Details

From the project README

agent-browser

Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact @eN element refs.

Install: npm i -g agent-browser && agent-browser install

Start here

This file is a discovery stub, not the usage guide. Before running any agent-browser command, load the actual workflow content from the CLI:

agent-browser skills get core             # start here — workflows, common patterns, troubleshooting
agent-browser skills get core --full      # include full command reference and templates

The CLI serves skill content that always matches the installed version, so instructions never go stale. The content in this stub cannot change between releases, which is why it just points at skills get core.

Specialized skills

Load a specialized skill when the task falls outside browser web pages:

agent-browser skills get electron          # Electron desktop apps (VS Code, Slack, Discord, Figma, ...)
agent-browser skills get slack             # Slack workspace automation
agent-browser skills get dogfood           # Exploratory testing / QA / bug hunts
agent-browser skills get vercel-sandbox    # agent-browser inside Vercel Sandbox microVMs
agent-browser skills get agentcore         # AWS Bedrock AgentCore cloud browsers

Run agent-browser skills list to see everything available on the installed version.

Why agent-browser

  • Fast native Rust CLI, not a Node.js wrapper
  • Works with any AI agent (Cursor, Claude Code, Codex, Continue, Windsurf, etc.)
  • Chrome/Chromium via CDP with no Playwright or Puppeteer dependency
  • Accessibility-tree snapshots with element refs for reliable interaction
  • Sessions, authentication vault, state persistence, video recording
  • Specialized skills for Electron apps, Slack, exploratory testing, cloud providers

Observability Dashboard

The dashboard runs independently of browser sessions on port 4848 and can also be opened through a proxied or forwarded URL such as https://dashboard.agent-browser.localhost. Agents should stay on the dashboard origin: session tabs, status, and stream traffic are proxied internally, so session ports do not need to be exposed.

Comments

Markdown supported