agent-browser is a browser automation CLI built for AI agents, using compact text output and ref-based element selection 1. The alternatives below also run browsers for agents or automation, drawing on the same sources.
- 1
agent-browseragent-browser.devwebsite read, tools not yet checked
A browser automation CLI for AI agents with compact text output, accessibility-tree snapshots with refs, and 50+ commands for navigation, forms, screenshots and debugging 1.
- 2
Playwrightplaywright.devwebsite read, tools not yet checked
Browser automation and testing across Chromium, Firefox and WebKit, with a Playwright CLI aimed at coding agents such as Claude Code and GitHub Copilot 4.
official:SDK · playwright+232 community tools built for it
- 3
Browserbasebrowserbase.comverified and signed
A cloud browser platform for agents that operate on the web, with an MCP server (@browserbasehq/mcp) and a Stagehand repository 2.
official:MCP server · @browserbasehq/mcprepository · stagehandskill · browserskill · agent-experienceskill · autobrowse+9 community tools built for it
for agents: safe-browser · autobrowse · browser
- 4
Browser Usebrowser-use.comverified and signed
A cloud browser for AI agents that runs web agents or connects your own agent to stealth browsers, with an MCP server 3.
official:MCP server · com.browser-use/browser-use
for agents: browser-use · agent · automation
- 5
Sources
- 1agent-browser | Browser Automation for AIagent-browser.dev · read 2026-10-29
- 2Browserbasebrowserbase.com · read 2026-10-29
- 3Browser Use Agents & Browser Infrastructure | Browser Usebrowser-use.com · read 2026-10-29
- 4Fast and reliable end-to-end testing for modern web apps | Playwrightplaywright.dev · read 2026-10-29
- 5Seleniumselenium.dev · read 2026-10-29
For agents: the 10 actions behind this answer
· agent-browser website read, tools not yet checked
Browser automation CLI for AI agents
safe-browser · safe-browser verified and signed
Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while
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.
· Playwright website read, tools not yet checked
Web automation and testing for apps, scripts, and AI agents
browser · WebDriver Support verified and signed
· Obscura website read, tools not yet checked
Obscura is an open source, headless browser engine for AI agents and web scraping. Spin up a clean, isolated session in milliseconds.
control-ui · control-ui verified and signed
Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs.
· Browser MCP website read, tools not yet checked
Let Claude, Cursor, Codex and other AI apps use your real browser, with your logins, in tabs you can watch and stop.
browserless_agent · browserless-mcp found in code, not yet checked
· Hyperbrowser website read, tools not yet checked
Cloud browsers, isolated sandboxes, and web data APIs for AI agents. Spin up Chrome sessions and microVMs in one call, and connect Playwright, Puppeteer, or any agent.
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.