Multimodal AI Browser Agent

About

Unlock the Power of Multimodal AI in Your Browser

Transform your browsing experience with the Multimodal AI Browser Agent. This powerful extension integrates the world's leading AI models—Google Gemini, OpenAI (GPT-4o), Anthropic Claude 3.5 Sonnet, and Perplexity—directly into your browser's side panel.

Why Install? Stop switching tabs to access your favorite AI tools. whether you need to summarize a long article, debug code, draft emails, or research complex topics, your AI assistant is just one click away, fully aware of what you are looking at.

Key Features:

🤖 Multi-Model Support: Access the best AI models in one place. Switch seamlessly between Gemini, GPT-4o, Claude 3.5 Sonnet, and Perplexity to get the best answer for any task.
👁️ Context Awareness: The AI "sees" what you see. It can read the current tab's content, URL, and title to provide relevant, context-aware assistance without you needing to copy-paste text.
⚡ Browser Automation: Go beyond chat. Command the agent to navigate websites, perform searches, click elements, and type text to automate repetitive web tasks.
🧠 Smart Memory: Your assistant remembers key details and preferences across sessions, making every interaction more personalized and efficient.
🔒 Privacy First: Your API keys are stored securely and locally within your browser. You maintain full control over your data and access.
💬 Modern Chat Interface: Enjoy a clean, responsive, and user-friendly chat experience with full history support.
How to Use:

Install the extension.
Click the icon in your toolbar to open the side panel.
Go to Settings (gear icon) and enter your API keys for the models you wish to use (Gemini, OpenAI, Anthropic, or Perplexity).
Start chatting! Ask questions about the current page or give automation commands.
Open Source: This project is open source. View the code, contribute, or report issues on our GitHub repository.