For browser automation, Selenium is the established choice with official bindings in six languages for controlling Chrome, Firefox, Edge and Safari 1. Playwright is a close alternative offering a test runner, a CLI for coding agents, and an SDK 2, while agent-browser 3 and Browser Use 4 target AI agents specifically.
- 1
- 2
Playwrightplaywright.devwebsite read, tools not yet checked
Web automation and testing framework across Chromium, Firefox and WebKit, with an SDK, a test runner and a CLI for coding agents 2.
official:SDK · playwright+232 community tools built for it
- 3
agent-browseragent-browser.devwebsite read, tools not yet checked
Browser automation CLI built for AI agents, returning compact text output and element refs from accessibility snapshots 3.
- 4
Browser Usebrowser-use.comverified and signed
Cloud browser for AI agents that runs web agents or connects your own agent to stealth browsers, with an MCP server 4.
official:MCP server · com.browser-use/browser-use
for agents: browser-use · automation · browser
Sources
- 1Seleniumselenium.dev · read 2026-10-29
- 2Fast and reliable end-to-end testing for modern web apps | Playwrightplaywright.dev · read 2026-10-29
- 3agent-browser | Browser Automation for AIagent-browser.dev · read 2026-10-29
- 4Browser Use Agents & Browser Infrastructure | Browser Usebrowser-use.com · read 2026-10-29
For agents: the 10 actions behind this answer
browser · WebDriver Support verified and signed
· Playwright website read, tools not yet checked
Web automation and testing for apps, scripts, and AI agents
· agent-browser website read, tools not yet checked
Browser automation CLI for AI agents
browser-use · browser-use verified and signed
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client.
automation · Testcontainers verified and signed
browser · browser verified and signed
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase
browsercat_click · BrowserCat MCP Server (Browser Automation) found in code, not yet checked
Click an element on the page
· Gaffa website read, tools not yet checked
Control real browsers at scale with a single API call. If you're doing data scraping, building AI Agents, looking to ingest web data into an LLM application or any other form of browser automation we've developed the easiest way to power them, without any of the hassle of configuring proxies, scalin
run_bql_query · Browserless (Activepieces) verified and signed
Run BQL Query — Execute Browser Query Language (BQL) GraphQL-based queries for advanced browser automation
· Reflex MCP website read, tools not yet checked
A local MCP server for Claude Desktop, Cursor, and other MCP clients. Batch browser actions, read selected page sections, and run isolated sessions in parallel. Chrome and saved logins run locally.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.