AI Student Assistant Agent 🎓

A multi-agent AI system designed to help students manage schedules, track emotional well-being, and plan study sessions. The system utilizes Google's Gemini models and the Agent Development Kit (ADK).

📂 Project Structure

• uninav_agent/: The main orchestrator agent that routes user requests.
• emotion_checker_agent/: Analyzes user sentiment and logs burnout scores.
• calendar_agent/: Retrieves schedule and events.
• planner_agent/: Creates study plans based on context.
• tools/: Custom Python tools (Mood logger, Calendar fetcher).
• uni-navigator-ui/: A Flask-based web interface for the agents.
• main.py: CLI entry point.

✅ Prerequisites

1. Python 3.10+ installed.
2. A Google Gemini API Key. Get one at aistudio.google.com.

🛠️ Installation

1. Clone the repository

   git clone https://github.com/MdMujahith/UniNavigator.git
   cd UniNavigator

2. Create a Virtual Environment (Recommended):

   python -m venv venv

   Activate the Virtual Environment

   # Windows:
   venv\Scripts\activate
   
   # Mac/Linux:
   source venv/bin/activate

3. Install Dependencies:

   pip install -r requirements.txt

4. Set up Environment Variables: Create a .env file in the root directory:

   GEMINI_API_KEY=your_actual_api_key_here

🚀 How to Run

1. Option 1: Terminal Mode (CLI)

   Run the interactive chat directly in your command line.

   python main.py

   Type exit to quit the chat.

2. Option 2: Custom Web UI (Flask)

   Launch the custom-styled chat interface included in this project.

   Navigate to the root directory.

   Run the Flask app as a module (ensures imports work correctly):

     python -m uni-navigator-ui.app

   (Note: Ensure you have __init__.py files in your folders, or simply run python uni-navigator-ui/app.py if your PYTHONPATH is set).

   Open your browser to: http://127.0.0.1:5000

3. Option 3: Google ADK Web UI

   To run this using the standard Agent Development Kit visualizer:

   Ensure you have the ADK installed:

   pip install google-adk
   

   Run the ADK server pointing to your main agent:

   adk run uninav_agent/agent.py:uni_navigator_agent
   

   OR

   adk web
   

   on root_directory

   Follow the URL provided in the terminal (usually http://localhost:3000).

🧠 Memory & Storage

The emotion_checker_agent stores mood data in a user_memory.json file at the project root, which serves as a local User_Emotion database for development. The calendar tool reads from the sample_calendar.json file as mock calendar data, which can later be replaced with the Google Calendar API for real-time calendar integration.

APP UI