Ken Qian bb2eda2b29 feat: Introduce Voice Mode feature with real-time speech recognition and particle visualization
- Added Voice Mode component for immersive voice interaction.
- Implemented audio management for speech recognition and synthesis.
- Integrated Three.js for dynamic particle visualizations responding to audio input.
- Updated README to include Voice Mode usage instructions and technical details.
- Enhanced UI with microphone controls and visual feedback for different voice states.
2025-11-01 17:24:03 +08:00
2025-09-04 12:44:38 +08:00
2025-09-12 00:02:21 +08:00
2025-07-13 13:52:32 +08:00
2025-07-12 09:59:19 +08:00
2025-07-12 09:59:19 +08:00
2025-08-30 01:00:39 +08:00
2025-08-30 01:04:57 +08:00

🤖 AIPex - AI-Powered Browser Automation Extension

The Open Source ChatGPT Atlas - Automate your browser with natural language commands

Chrome Web Store GitHub stars GitHub forks GitHub issues GitHub pull requests License: MIT TypeScript React

Twitter YouTube Discord

** The Open Source ChatGPT Atlas Alternative **

Chrome Web Store

🤖 What is AIPex?

AIPex is the open source alternative to ChatGPT Atlas - a revolutionary Chrome extension that transforms your browser into an intelligent automation platform. Using natural language commands and AI-powered intelligence, AIPex can automate virtually any browser task - from complex multi-step workflows to simple repetitive actions.

🎯 Why choose AIPex over ChatGPT Atlas?

  • Free & Open Source - No subscription fees, full transparency
  • No Browser Migration - Use your existing browser directly
  • All Atlas Features - Complete feature parity with additional capabilities
  • Better Performance - Optimized for speed and efficiency

📊 Comparison with Similar Projects

AIPex vs ChatGPT Atlas vs Dia/Comet vs Playwright-based Solutions

Feature AIPex ChatGPT Atlas Comet (Dia) Playwright-based
Pricing & Open Source Free and open source Paid and closed source Free and open source Free and open source
Browser Migration Cost No migration needed, use existing browser Requires browser migration ⚠️ Install separate Dia browser Launch browser + install dependencies
Setup & Resources One-click extension install, uses current browser Requires browser migration ⚠️ Install separate Dia browser Launch browser + install dependencies
Session Reuse Auto-uses existing logins & settings Preserves user environment Preserves user environment Clean environment, requires re-login
Ease of Use No technical knowledge needed ⚠️ Adapt to new browser ⚠️ Adapt to new browser ⚠️ Requires technical setup
Performance Fast, low LLM token cost Fast, low token cost Fast, low token cost ⚠️ Slower (IPC overhead, higher token cost)
Capabilities Full browser API, multi-tab support ⚠️ Limited features ⚠️ Limited API, tab selection only ⚠️ Limited to Playwright API
Feature Coverage All Atlas features available ⚠️ Multiple features implemented ⚠️ Limited features ⚠️ Limited features
BYOK Yes No No Yes

🚀 Do Amazing with AIPex

1. "Organize my tabs by topic"

https://github.com/user-attachments/assets/4a4f2a64-691c-4783-965e-043b329a8035

2. "Use google to research MCP"

https://github.com/user-attachments/assets/71ec4efd-d80e-4e8f-8e39-88baee3ec38e

3. "write a twitter to say hello"

https://github.com/user-attachments/assets/81f6b482-84d0-4fd9-924b-dca634b208ec

4. "please help me pass the exam"

https://github.com/user-attachments/assets/ba454715-c759-41df-bf87-e835f76be365

🎤 Voice Mode (NEW!)

  • Hands-Free Control: Control your browser using voice commands
  • Real-Time Speech Recognition: Natural voice interaction with AI
  • Text-to-Speech Output: AI responses are spoken back to you
  • GPU-Accelerated Visuals: Beautiful particle animations powered by Three.js + GLSL shaders
  • Audio Visualization: Dynamic particles that react to voice frequency and amplitude

Quick Start:

  1. Click the microphone icon in the chat input toolbar
  2. Allow microphone permissions
  3. Click the red microphone button to start speaking
  4. Watch the stunning particle animations respond to your voice!

📖 Voice Mode Quick Start Guide | 📚 Detailed Guide

🚀 Getting Started

Quick Start

  1. Install from Chrome Web Store (Recommended)

  2. Open AIPex

    • Press ⌘+M (Mac) or Ctrl+M (Windows/Linux)
    • Or click the AIPex icon in your toolbar

🛠️ Development & Contributing

We love contributions! Here's how you can help make AIPex even better:

📖 For detailed development setup, build instructions, and contribution guidelines, please see DEVELOPMENT.md

📊 Tool Categories Overview

🗂️ Tab Management - 8 tools

Complete tab control and navigation:

  • get_all_tabs - Get all open tabs across all windows
  • get_current_tab - Get information about the currently active tab
  • switch_to_tab - Switch to a specific tab by ID
  • create_new_tab - Create a new tab with the specified URL
  • get_tab_info - Get detailed information about a specific tab
  • duplicate_tab - Duplicate an existing tab
  • close_tab - Close a specific tab
  • get_current_tab_content - Get the visible text content of the current tab
📄 Page Content & Interaction - 14 tools

Content extraction, analysis, and page interaction:

  • get_page_metadata - Get page metadata including title, description, keywords
  • extract_page_text - Extract text content with word count and reading time
  • get_page_links - Get all links from the current page
  • search_page_text - Search for text on the current page
  • get_interactive_elements - Get all interactive elements (links, buttons, inputs) with optimized performance
  • click_element - Click an element using CSS selector
  • summarize_page - Summarize page content with key points
  • fill_input - Fill an input field with text
  • clear_input - Clear the content of an input field
  • get_input_value - Get the current value of an input field
  • submit_form - Submit a form using CSS selector
  • get_form_elements - Get all form elements and input fields
  • scroll_to_element - Scroll to a DOM element and center it
  • highlight_element - Permanently highlight DOM elements
  • highlight_text_inline - Highlight specific words or phrases within text
⬇️ Downloads & Files - 4 tools

Download control and file management:

  • download_text_as_markdown - Download text content as markdown file
  • download_image - Download an image from base64 data
  • download_chat_images - Download multiple images from chat messages
  • download_current_chat_images - Download all images from current AI chat
📸 Screenshots - 3 tools

Visual capture and screenshot management:

  • capture_screenshot - Capture screenshot of current visible tab
  • capture_tab_screenshot - Capture screenshot of a specific tab by ID
  • capture_screenshot_to_clipboard - Capture screenshot and save to clipboard
🔧 Advanced Features - 3+ tools

Advanced browser automation and utilities:

  • Additional specialized tools for enhanced browser control
  • AI-powered content analysis and processing
  • Custom automation workflows

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Support & Community

🏆 Contributors

Thank you to all the amazing contributors who help make AIPex better:

Contributors are automatically updated from GitHub. Click to see detailed contribution statistics.


Want to contribute? Check out our Contributing Guide and help make AIPex even better!

🌟 Star History

Star History Chart


Made with ❤️ by the AIPex Team

GitHub Chrome Web Store

📱 Follow us on social media:

Twitter YouTube Discord

Description
No description provided
Readme MIT 90 MiB
Languages
TypeScript 94.9%
JavaScript 4.3%
HTML 0.4%
CSS 0.4%