TheGitAI

Control your browser with TheGitAI. It works in the browser you already have open, on the tools a script can't reach.

Control your browser with TheGitAI. It works in the browser you already have open, on the tools a script can't reach. Most of what a coding agent does needs no browser at all. This is for the part that does — the cloud console, the dashboard, the admin panel, and everything else that has no API to call and no way in from the outside. It is not mainly a front-end debugger. Checking a page you just built is the one thing an ordinary headless script already does well. What a script cannot do is work in a browser that is already yours. WHAT IT IS FOR • Standing up infrastructure through a provider's console, where the portal is the interface and working out the API would take longer than the task. • Getting data out of a site that offers no download and no API. • Working through an admin UI — a CMS, a page builder, a dashboard, an internal tool — where the job is clicking through screens rather than writing files. • Being shown how something works. Ask where a setting lives in a panel you do not know, and have it walked through on your own screen, one step at a time. • Filling in the long form on the internal tool, the one you have already filled in twice today. • Reading a professional profile, a feed, or a job posting you are looking at, and doing something useful with what is there. • Front-end work too, when you want it: how a page renders, what breaks at phone width, the console error behind a failure. HOW IT WORKS No second browser to set up, and no API key standing in for you. It uses the browser you already have open, exactly as you left it. The extension connects to the TheGitAI command-line tool running on the same computer, and does nothing at all until you ask for something in your terminal. Its clicks and keystrokes are the same kind the browser gets from you, rather than scripted events — which is why pages that ignore automated input still work normally. WHERE THE LIMITS ARE • Each terminal session owns a Chrome tab group. A tab joins when you ask the agent to use it, and dragging it out of the group takes it back out of reach. • Your other tabs are never read. The agent is told how many you have open — never their titles, never their addresses. • Default mode asks before the agent uses a website. Plan mode lets it read pages without clicking, typing or navigating. • Downloads pause the moment they start. Nothing reaches your disk until you say so. • Stop, Resume and Disable are in the toolbar popup, and Chrome shows its own banner for as long as the agent is attached to a tab. • It never types your passwords. Logins and CAPTCHAs are handed back to you. PRIVACY The extension makes no network requests of its own. Everything it reads goes to the TheGitAI tool on your own computer, over a local channel between two programs on the same machine. Nothing it reads is stored by us — not the pages, not the screenshots, not a record of the sites you visit. On your own machine it keeps exactly two things: a random identifier so that two Chrome profiles can be told apart, and whether you have switched it off. Uninstalling removes both. Full policy: https://thegit.ai/privacy GETTING STARTED This extension is the browser half of TheGitAI. Install the terminal app first: npm install -g @thegitai/cli Then run it in any project directory: ai Ask it about a page, and the extension connects on its own. There is no pairing step, no port to configure, and nothing to set up twice. Homepage and docs: https://thegit.ai Browser guide: https://thegit.ai/docs/core-features/browser-control Package: https://www.npmjs.com/package/@thegitai/cli WHAT YOU NEED • macOS, Windows or Linux • Node.js 22 or later, to install the terminal app • Chrome 116 or later REQUIRES THE TERMINAL APP This extension does nothing by itself. Until TheGitAI is installed and running, the popup will tell you it is waiting.