Auto Browser
autobrowser.dev
- Free plan
- Browser extension
What Auto Browser is
Auto Browser is a free Chrome side-panel AI agent that reads webpages and performs tasks described in plain English. It can inspect a page’s accessibility tree, click, type, scroll, navigate, and fill forms. Pages exposing WebMCP tools can let the extension use those tools instead of interacting through the DOM. Supported providers include Chrome Built-in AI (Gemini Nano), Google Gemini, OpenRouter, and local OpenAI-compatible endpoints such as Ollama and LM Studio. Providers can be switched during a conversation while keeping its history. Write actions require approval, arbitrary JavaScript prompts for approval, and banking, government, and healthcare origins are blocked by default. The maker says there is no extension backend storing prompts, browsing activity, conversation history, or API keys. Cloud-provider prompts and page context go directly to that provider; the maker says Gemini Nano and local options send no device data through the extension. Chrome 126 or newer is required.
Who it suits
It suits Chrome users who want browser tasks, form filling, or research handled through natural-language instructions. People choosing cloud providers should consider their direct prompt and page-context handling.
Good to know, and what to watch
- Free extension installation
- Supports multiple cloud and local AI providers
- Can use WebMCP page tools
- Provider switching keeps conversation history
- Approval prompts protect write actions
- Requires Chrome 126 or newer
- Gemini Nano needs substantial hardware and storage
- Cloud providers receive prompts and page context
- Restricted from automated commercial pipelines
Plans
Every plan and priceFree
Free plan
The verdict
Auto Browser combines browser control with several AI-provider choices and explicit approval checks. Its privacy model differs between local and cloud providers, and Chrome and usage restrictions apply.
What the maker publishes
- AI providers
- It supports Chrome Built-in AI (Gemini Nano), Google Gemini, OpenRouter, and local OpenAI-compatible endpoints such as Ollama and LM Studio. source
- Attachments
- Users can attach images and audio files of up to 10 MB each in the side panel. source
- Cloud data handling
- When a cloud AI provider is selected, prompts and relevant page context are sent directly from the browser to that provider. source
- Integrations
- Pages that expose tools using WebMCP can let Auto Browser use those tools instead of interacting through the DOM. source
- Local AI
- The maker says Gemini Nano and local LLM options send no data from the device through the extension. source
- Notable restrictions
- The terms prohibit using the service to operate an automated pipeline, bot, crawler, or commercial service beyond ordinary individual use. source
- On-device requirements
- Gemini Nano requires Chrome 138 or newer, macOS 13 or newer, Windows 10 or newer, Linux or ChromeOS, 16 GB RAM, and 22 GB free disk. source
- Page interaction
- It reads the page accessibility tree and can click, type, scroll, navigate, and use page-provided WebMCP tools. source
- Privacy
- The maker says it operates no extension backend and does not receive or store prompts, browsing activity, conversation history, or API keys. source
- Provider switching
- Users can switch AI providers mid-conversation while retaining conversation history. source
- Safety controls
- Write actions require approval, arbitrary JavaScript always prompts, and banking, government, and healthcare origins are blocked by default. source
- Support
- The maker directs users to the Chrome Web Store listing’s support channel for help with blocked sites or other issues. source
- Supported browser
- Auto Browser requires Chrome 126 or newer for basic use. source
- What it does
- Auto Browser is a Chrome side-panel AI agent that reads webpages and carries out tasks described in plain English. source
Checked against the maker's pages on 3 Oct 2026.