

Firecrawl
Open source web data API for agents: search, scrape, crawl and interact, with an official MCP server
Persistent cloud Chrome for AI agents, with saved logins, forks and live view

About
Install the CLI with `curl -fsSL https://cloudbrowser.tv/install.sh | sh`, sign in with `cloudbrowser auth login`, then run `cloudbrowser create --name research --wait` and `cloudbrowser links create <browser-id> --audience cdp --output url`. Attach Playwright, playwright-cli, agent-browser, Puppeteer or any CDP client to that URL from Claude Code, Codex, Cursor or OpenClaw. A human can sign in to a site once in the live view and then hand the browser to the agent. Things to know: the service is still labeled preview, website logins can still expire, and usage is counted in browser-hours across running browsers.
Features
Install
I compare five ways to give an AI agent a browser, from local Chrome over MCP to hosted cloud browsers, with real install commands and pricing.
The APIs and cloud browsers that let an agent search, read and use the live web, compared on what they return, how they bill and how to plug them in.
Give Claude Code hands in the iOS Simulator or an Android emulator so it checks its own UI changes. Five MCP tools, real setup commands, honest tradeoffs.



Free. I review every submission.
is in the review queue. I'll install it, test it and list it if it passes.