Math AI Agent Chrome Extension

A sophisticated Chrome extension that leverages a cognitive AI architecture to solve mathematical problems. The agent uses a layered cognitive approach inspired by human cognitive processes to understand, analyze, and solve mathematical queries.

Features

• Cognitive Architecture: Implements a multi-layer cognitive system:

  • Perception Layer: Analyzes and structures user input
  • Memory Layer: Maintains context and conversation history
  • Decision Layer: Determines next actions based on current state
  • Action Layer: Executes decided actions and generates responses

• Chrome Extension Integration: Easy-to-use browser interface for quick access to the math solving capabilities

• Asynchronous Processing: Built with async/await for efficient request handling

• Robust Error Handling: Graceful fallbacks and error management throughout the system

Architecture

The system is built with a modular architecture consisting of:

1. Core Cognitive Components:

   • main.py: Orchestrates the cognitive workflow
   • perception.py: Handles input analysis
   • memory.py: Manages conversation state
   • decision.py: Implements decision-making logic
   • action.py: Executes actions based on decisions

2. Support Systems:

   • llm.py: Language model integration
   • models.py: Data models and structures
   • helpers.py: Utility functions
   • prompts.py: System prompts and templates

3. API Layer:

   • fastapi_server.py: REST API endpoints
   • mcp_server.py: Message control protocol server

Installation

1. Clone the repository:

git clone [repository-url]

2. Install dependencies:

uv sync

3. Set up environment variables: Create a .env file with necessary configurations

4. Install the Chrome Extension:

   • Open Chrome and navigate to chrome://extensions/
   • Enable "Developer mode"
   • Click "Load unpacked" and select the extension directory

Usage

1. Click the Math Agent icon in your Chrome browser
2. Enter your mathematical query in the popup window
3. The agent will process your query through its cognitive layers
4. View the solution and explanation in the response

Technical Requirements

• Python 3.11+
• Chrome Browser
• Required Python packages (specified in uv.lock)
• Local server running on port 8000 for API communication

Development

To run the development server:

python main.py

The extension communicates with a local FastAPI server that needs to be running:

uvicorn fastapi_server:app --reload

Architecture Diagram

User Query (Chrome Extension)
         ↓
    Perception Layer
         ↓
    Memory Layer
         ↓
    Decision Layer
         ↓
    Action Layer
         ↓
      Response

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License