Agent Browser

Name: Agent Browser
Author: arize-ai

arize-ai/phoenix

77 installs
10.9k repo stars
Updated August 3, 2026
arize-ai/phoenix

This is a copy of agent-browser by vercel-labs - installs and ranking accrue to the original listing.

agent-browser is a Claude Code skill wrapping a Rust browser-automation CLI that lets AI agents control Chrome/Chromium over CDP to navigate, fill forms, screenshot, and test web and Electron apps.

About

agent-browser is a browser-automation CLI for AI agents that drives Chrome or Chromium over CDP. Developers use it to navigate pages, fill forms, click buttons, take screenshots, extract data, and run exploratory QA or dogfooding without a Playwright or Puppeteer dependency. It exposes accessibility-tree snapshots with element refs so agents can interact reliably, and ships specialized modes for Electron apps, Slack, and cloud browsers.

Rust browser-automation CLI that drives Chrome/Chromium over CDP for AI agents
Accessibility-tree snapshots with compact @eN element refs for reliable interaction
Also automates Electron apps (VS Code, Slack, Discord, Figma) and cloud browsers

Agent Browser by the numbers

77 all-time installs (skills.sh)
Data as of Aug 3, 2026 (Skillselion catalog sync)

At a glance

agent-browser capabilities & compatibility

Capabilities: browser automation · web testing · web scraping · screenshot capture · form filling · exploratory qa
Use cases: testing · web scraping · debugging
Runs: Runs locally
Pricing: Free

From the docs

What agent-browser says it does

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

SKILL.md

Chrome/Chromium via CDP with no Playwright or Puppeteer dependency

SKILL.md

Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality.

SKILL.md

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

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/arize-ai/phoenix/agent-browser.svg)](https://skillselion.com/skills/arize-ai/phoenix/agent-browser)

Installs	77
repo stars	★ 10.9k
Last updated	August 3, 2026
Repository	arize-ai/phoenix ↗

What it does

Let an AI agent open a website, fill forms, click, screenshot, extract data, or run exploratory QA on a web or Electron app.

Who is it for?

AI agents that need to drive a real browser to test web apps, fill forms, or scrape pages

Skip if: Teams that already standardize on Playwright or Puppeteer test suites and don't want a separate CLI

When should I use this skill?

You need an agent to open a website, fill a form, click a button, screenshot, scrape a page, or run exploratory QA

What you get

The agent can navigate, interact with, screenshot, and extract data from web and Electron apps via a single CLI

browser session automation
page screenshots
extracted page data

By the numbers

Observability dashboard runs on port 4848
6 specialized skills: electron, slack, dogfood, vercel-sandbox, agentcore, core

Files

SKILL.mdMarkdownGitHub ↗

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.