Auto Browser

AI agent that actually uses your browser. WebMCP-native, privacy-first, works with any AI providers.

Auto Browser is an AI agent that uses your browser for you. It sits in your Chrome side panel. You tell it what you want in plain English ("find me a flight from NYC to Tokyo next Thursday", "compare these soccer boots and pick one", "pull the top 5 rows from this table"), and it goes and does it, in your own tabs with your own logins. There are no scripts to write, no servers to set up, no per-site integrations. It works on most websites, it lets you pick which AI runs it, and with a model running on your own machine, nothing goes to a cloud provider. HOW IT WORKS You type a task. The agent reads an outline of the page (its buttons, links, fields and text), takes a screenshot when it needs to check something visually, and figures out what to do. Then it clicks, types, scrolls, opens pages and tabs, or calls the page's own WebMCP tools. It keeps going until the job is done, it needs you to step in, or it reaches its step limit (50 by default). By default, every action that changes something on the page asks for your approval first. Reading the page and scrolling never do. You can switch to auto-approve for one task, or for everything until you turn it off. BRING YOUR OWN AI Most agent tools lock you into one model. Auto Browser doesn't. You pick a provider in Settings, and three of them can run tasks on a page. You can switch between those three mid-conversation without losing context. 1. OpenRouter. One key gets you every model in the OpenRouter catalog. The default is DeepSeek V4.1 Flash, and Claude, GPT and Llama are a dropdown away. Image and audio support is detected per model. 2. Google Gemini. Direct API access to Google's Gemini models. The default is Gemini 3.8 Flash. Your key, your quota. 3. Local LLM. Point it at Ollama, LM Studio, or any OpenAI-compatible endpoint running on your machine. Good for air-gapped setups and custom fine-tunes. 4. Chrome Built-in AI (Gemini Nano). Free and on-device, with no API key and no account. Use it for chat and for questions about images or audio. Its context window is too small to drive web pages, so tasks on a page need one of the other three. Start a task on DeepSeek, hit something hard, flip to Claude, finish, flip back. Your conversation comes with you. WEBMCP NATIVE Auto Browser speaks WebMCP, an open web spec that lets pages describe themselves to AI agents. When a site exposes WebMCP tools, the agent uses those tools directly instead of clicking around the page, with the same permission checks as a click. That is faster and less likely to break when the site changes. WebMCP is an open spec, not something we own. We just think it is the right way to build the web for agents. PRIVACY AND SAFETY An agent that can click anything is dangerous if you do not put guardrails on it. We put guardrails on it. There are no analytics in this extension. No telemetry. No usage tracking. Your API keys live in Chrome's storage on your machine. What you type into form fields, passwords included, stays out of the page outline the model reads. The agent can tell that a field has a value in it, but the outline never shows the value. About 30 banking, payment, crypto, government, healthcare and password-manager sites are on a built-in block list. On those sites the agent can't click, type, run scripts or open tabs, whatever approval mode you're in. If a page moves to another site mid-task (a login loop, a phishing hop), approvals you gave on the first site stop applying, and the agent has to ask again. Running JavaScript on a page is the most powerful thing the agent can do, so it is the most gated. Auto-approve never covers it. Scripts need their own approval, which you can give for one site for the rest of a task, or turn off in Settings. The agent only works in the tab you started from and the tabs it opens, all kept in one Chrome tab group. It can't see or touch your other tabs. If you want nothing to leave your machine, run a local model through Ollama or LM Studio. WHAT YOU CAN USE IT FOR Comparing products across a store and getting a recommendation. Pulling structured data out of nasty HTML tables. Summarising long articles, papers, and release notes. Reading what someone is posting on X without scrolling for twenty minutes. Booking restaurant reservations and movie tickets. Filling out tedious multi-step forms. Anything you keep putting off because it is boring. WHO IT IS FOR People who live in their browser. Researchers, analysts, founders, builders, operators, anyone who treats "lots of open tabs" as a permanent condition. If you spend hours a day inside Chrome, this is for you. GETTING STARTED Install the extension. Open the side panel on any site. Add an OpenRouter or Gemini key, or point it at a local model. Type what you want done. That is the whole onboarding. Auto Browser is an experimental project by Vin Lim. It is closed-source. Privacy policy and terms are linked from the listing.