Skip to main content
This page walks you from a fresh download to your first AI-driven session. Six steps. About five minutes.
1

Install BrowserClaw

Head over to browseros.com/agents and download BrowserClaw for your operating system. Install it the way you’d install any other browser.Once it’s open, it works like Chrome or any other browser you’ve used. Bookmarks, extensions, keyboard shortcuts, all in the same places.
2

Sign in like you normally would

Use BrowserClaw as your browser for a bit. Sign in to Gmail. Sign in to your calendar. Sign in to Notion, Linear, your CRM, your accounting tool, whatever you use for actual work.There is nothing special about this step. You are just using a browser. But it matters, because every account you sign in to here becomes something your AI can use later.
Your AI cannot see your personal tabs unless you ask it to. It works in its own tabs, side by side with yours. Signing in to Gmail here means your AI can use Gmail when you ask it to. It does not mean your AI is reading your inbox while you’re not looking.
3

Connect BrowserClaw to your AI

Open a new tab in BrowserClaw and click MCP in the sidebar. You’ll see a list of AI tools you can connect with one click.
BrowserClaw connect page showing an endpoint URL at the top and six AI tools listed underneath: Claude Code, Codex, Cursor, Antigravity, VS Code, and Zed. Each has a Connect button on the right.

The connect page: one endpoint, one click per AI tool.

Find the AI tool you use: Claude Code, Cursor, Codex, Antigravity, VS Code, Zed, or another. Click Connect on its row. BrowserClaw sets everything up for you.Restart your AI tool once, and it now has a browser.
Using an AI tool that isn’t listed? Copy the endpoint URL at the top of the page and paste it into your AI’s own settings. See the Connect page for the manual setup.
4

Give your AI a task

Open your AI tool and give it a real task. Something you’d actually want done. To start, try this:
Or something closer to your own work:
Whichever you pick, hit send.
5

Watch it work

Open a new tab in BrowserClaw. Your AI’s session shows up on the dashboard.
BrowserClaw new-tab dashboard with a large italic headline reading 'What are your agents working on right now?' A row of Running now cards shows a live agent session with a live browser preview. Below it, a grid of Recent activity tiles shows five completed sessions with the sites they visited.

Every running AI and every finished session, at a glance.

Two things to look at:
  • Running now: the AI working on your task right now. You’ll see the site it’s on, how long it’s been at it, and a live preview of what it’s looking at.
  • Recent activity: sessions that already finished. Click any tile to open the full story of what happened.
You don’t have to sit and stare. Come back whenever you want; the dashboard shows you what’s been going on.
6

Replay what your AI did

When a session finishes, click its tile. Then click View Session Replay.
BrowserClaw replay screen showing a full-fidelity playback of a page the AI browsed. A play/pause scrubber sits at the bottom. On the right, an action timeline lists every step the AI took, synced to the current moment in the video.

Replay any session like a video. Scrub through, see exactly what your AI saw at every moment.

The replay plays back like a video. Hit rewind to see the exact moment things went off, or the exact moment something went well. On the right, every step your AI took is listed in order, and you can click any one to jump the replay to that moment.Now you know what worked. Tell your AI, and it’ll do the next task better.

Where to next

Your dashboard

Every part of the new-tab dashboard and what it tells you.

Your stuff stays yours

What BrowserClaw records, what it doesn’t, and where everything lives.