AgentBrowser vs Auto Browser

AgentBrowser has no write-up on Specifiction yet; its figures are above.

Auto Browser is a free Chrome extension that uses an AI agent in the browser’s side panel. It reads a webpage’s accessibility tree and can click, type, scroll, navigate, fill forms, and handle research tasks described in plain English. Pages exposing WebMCP tools can let it use those tools instead of the page DOM. Supported providers include Chrome Built-in AI (Gemini Nano), Google Gemini, OpenRouter, and local OpenAI-compatible endpoints such as Ollama and LM Studio. You can change providers during a conversation without losing its history. Write actions require approval, arbitrary JavaScript prompts for approval, and banking, government, and healthcare origins are blocked by default. The extension is free to install at free; Google Gemini and OpenRouter charge per request using your API key. Chrome 126 or newer is required for basic use. Attachments can be images or audio up to 10 MB each.