Gemini Nexus is a Chrome extension deeply integrating Google Gemini AI into web browsing. It targets power users and developers seeking enhanced productivity via intelligent web interaction control, advanced image processing, and seamless AI assistance. The extension makes AI an active participant in user workflows.

How It Works

The project uses a multi-component architecture: content scripts inject interactive elements like a floating selection toolbar and browser control capabilities. A secure sandbox isolates rendering. Background scripts manage AI logic, API communication, session state, and an account polling system to circumvent rate limits. This enables Gemini AI to converse and manipulate web content/browser functions via a Browser Control Protocol (MCP).

Quick Start & Requirements

Installation: Download latest release ZIP, unzip, load unpacked extension in Chrome (or Chromium) via chrome://extensions/ with developer mode enabled. No specific hardware/software prerequisites beyond a compatible browser are detailed.

Highlighted Details

• Floating Toolbar: Context-aware AI actions (translate, summarize, explain, correct) on selected text, insertable into web forms.
• Image AI: OCR extraction, screenshot translation, AI image analysis.
• Browser Control (MCP): AI programmatically controls browser actions (new tabs, forms, JS execution).
• Account Polling: Mitigates API rate limits by rotating Google accounts.
• Secure Sandbox: Isolates UI rendering.

Maintenance & Community

User support sought via "afdian.com" (crowdfunding). No specific community channels or notable contributors mentioned.

Licensing & Compatibility

MIT License: Permissive, generally allows commercial use and integration into closed-source projects (with attribution/terms).

Limitations & Caveats

README lacks details on limitations, alpha/beta status, or bugs. Reliance on Google Gemini implies dependency on API availability/terms. Account polling may be subject to Google's policies.