WebBrain

WebBrain is a free, open-source browser extension that functions as an AI agent within the browser. It reads and comprehends web pages, including articles, dashboards, forms, and PDFs, and can answer questions about their content. The tool can interact with pages by clicking, typing, scrolling, and navigating, automating repetitive tasks through natural language instructions.

WebBrain is designed for users who need to automate browser tasks, extract structured data from web pages, or interact with online forms and documents. It suits developers, researchers, analysts, and general users looking for a privacy-focused, open-source alternative to proprietary browser AI tools.

WebBrain prioritizes privacy by operating in a read-only mode by default, avoiding telemetry, accounts, or data tracking. It asks for permission before taking consequential actions and defends against hidden prompt injections. Users can run it with local LLMs for zero data leakage or connect to cloud providers.

Yes, WebBrain supports offline operation by allowing users to choose local LLMs. This enables fully private, on-device processing without relying on cloud services. It also supports cloud providers like OpenAI or Claude for users who prefer cloud-based models.

WebBrain supports multiple LLM providers, including local llama.cpp, OpenAI, Claude, and OpenRouter. It also offers optional integrations like CAPTCHA solving via CapSolver API and cookie banner dismissal for common consent management tools.

To get started, install the WebBrain browser extension from the Chrome Web Store, Firefox Add-ons, or Edge Add-ons. Once installed, open the extension sidebar, choose your preferred LLM provider, and begin interacting with web pages by asking questions or issuing natural language instructions.