HOSTED HERE : http://www.neuracore.tech/

██╗███╗   ██╗████████╗███████╗██╗     ██╗     ██╗███╗   ███╗ █████╗ ██████╗ ██╗  ██╗███████╗████████╗
██║████╗  ██║╚══██╔══╝██╔════╝██║     ██║     ██║████╗ ████║██╔══██╗██╔══██╗██║ ██╔╝██╔════╝╚══██╔══╝
██║██╔██╗ ██║   ██║   █████╗  ██║     ██║     ██║██╔████╔██║███████║██████╔╝█████╔╝ █████╗     ██║   
██║██║╚██╗██║   ██║   ██╔══╝  ██║     ██║     ██║██║╚██╔╝██║██╔══██║██╔══██╗██╔═██╗ ██╔══╝     ██║   
██║██║ ╚████║   ██║   ███████╗███████╗███████╗██║██║ ╚═╝ ██║██║  ██║██║  ██║██║  ██╗███████╗   ██║   
╚═╝╚═╝  ╚═══╝   ╚═╝   ╚══════╝╚══════╝╚══════╝╚═╝╚═╝     ╚═╝╚═╝  ╚═╝╚═╝  ╚═╝╚═╝  ╚═╝╚══════╝   ╚═╝   

IntelliMarket is an enterprise-grade investment research platform that leverages multiple AI agents to provide comprehensive financial analysis. Built with the AGNO framework and powered by Google's Gemini AI, it delivers institutional-quality research reports comparable to Goldman Sachs and Morgan Stanley.

• 🤖 Multi-Agent Architecture: 5 specialized AI agents working in coordination
• 📈 Real-Time Data: Live market data via YFinance and web research via DuckDuckGo
• 💼 Institutional Quality: CFA/CMT-level analysis with professional report formatting
• ⚡ High Performance: ~10,000x faster than LangGraph with minimal memory footprint
• 🌐 Full-Stack Solution: REST API backend with professional web frontend
• 📊 Beautiful UI: Investment-grade interface with interactive charts and tables
• 📄 PDF Reports: Professional PDF generation with financial styling and institutional formatting

• Comprehensive financial metrics analysis (P/E, ROE, debt ratios)
• Technical analysis with RSI, MACD, moving averages
• Real-time news sentiment analysis
• Competitive landscape assessment
• Investment recommendations with price targets

• Side-by-side analysis of multiple stocks
• Relative valuation and performance metrics
• Competitive positioning analysis
• Investment ranking with rationale

• Topic-based market sentiment analysis
• Industry trend identification
• Related stock discovery and analysis
• News impact assessment

• Natural language investment questions
• Intelligent agent routing based on query content
• Contextual analysis with multiple perspectives

• Institutional-grade report generation
• Interactive data tables and visualizations
• Professional PDF Reports: High-quality PDF downloads with financial styling, proper typography, and institutional formatting
• Real-time progress tracking

graph TB
    subgraph "Frontend Layer"
        UI[Web Interface<br/>HTML/CSS/JS]
        API_CLIENT[API Client<br/>JavaScript]
    end
  
    subgraph "Backend Layer"
        FLASK[Flask API Server<br/>REST Endpoints]
        WORKFLOWS[Workflow Engine<br/>Agent Coordination]
        PDF[PDF Generator<br/>ReportLab Engine]
    end
  
    subgraph "AI Agent Layer"
        FA[Financial Agent<br/>CFA-Level Analysis]
        TA[Technical Agent<br/>CMT Analysis]
        RA[Research Agent<br/>News & Sentiment]
        CA[Competitive Agent<br/>Strategic Analysis]
        REP[Report Agent<br/>Synthesis & Formatting]
    end
  
    subgraph "Data Layer"
        YF[YFinance<br/>Market Data]
        DDG[DuckDuckGo<br/>Web Research]
        GEMINI[Gemini AI<br/>LLM Processing]
    end
  
    UI --> API_CLIENT
    API_CLIENT --> FLASK
    FLASK --> WORKFLOWS
    FLASK --> PDF
    WORKFLOWS --> FA
    WORKFLOWS --> TA
    WORKFLOWS --> RA
    WORKFLOWS --> CA
    WORKFLOWS --> REP
    FA --> YF
    TA --> YF
    RA --> DDG
    CA --> YF
    REP --> GEMINI
    FA --> GEMINI
    TA --> GEMINI
    RA --> GEMINI
    CA --> GEMINI

sequenceDiagram
    participant User
    participant API
    participant Workflow
    participant FA as Financial Agent
    participant TA as Technical Agent
    participant RA as Research Agent
    participant CA as Competitive Agent
    participant REP as Report Agent
  
    User->>API: Request Stock Analysis
    API->>Workflow: Initialize Analysis
  
    par Parallel Analysis
        Workflow->>FA: Analyze Financials
        Workflow->>TA: Technical Analysis
        Workflow->>RA: News Research
        Workflow->>CA: Competitive Analysis
    end
  
    FA-->>Workflow: Financial Metrics
    TA-->>Workflow: Technical Indicators
    RA-->>Workflow: Market Sentiment
    CA-->>Workflow: Competitive Position
  
    Workflow->>REP: Synthesize Report
    REP-->>Workflow: Final Report
    Workflow-->>API: Complete Analysis
    API-->>User: Investment Report

• Python 3.8+
• Google Gemini API Key (Get it here)
• Internet connection for real-time data

1. Clone the repository

   git clone https://github.com/fenil210/intelligmarket.git
   cd intelligmarket

2. Set up virtual environment

   python -m venv venv
   
   # Windows
   venv\Scripts\activate
   
   # macOS/Linux
   source venv/bin/activate

3. Install dependencies

   pip install -r backend/requirements.txt

4. Configure environment

   # Copy environment template
   cp .env.example .env
   
   # Edit .env file and add your Gemini API key
   GOOGLE_API_KEY=your_gemini_api_key_here

1. Start the backend server

   python run.py

   Backend will be available at http://127.0.0.1:5000

2. Start the frontend server (in a new terminal)

   cd frontend
   python -m http.server 8080

   Frontend will be available at http://localhost:8080

3. Access the application

   Open your browser and navigate to http://localhost:8080

curl -X POST http://127.0.0.1:5000/api/analyze/stock \
  -H "Content-Type: application/json" \
  -d '{
    "symbol": "AAPL",
    "type": "comprehensive"
  }'

curl -X POST http://127.0.0.1:5000/api/analyze/comparison \
  -H "Content-Type: application/json" \
  -d '{
    "symbols": ["AAPL", "MSFT", "GOOGL"]
  }'

curl -X POST http://127.0.0.1:5000/api/analyze/research \
  -H "Content-Type: application/json" \
  -d '{
    "topic": "AI stocks 2024"
  }'

curl -X POST http://127.0.0.1:5000/api/download/pdf \
  -H "Content-Type: application/json" \
  -d '{
    "content": {...},
    "title": "AAPL Analysis Report"
  }' \
  --output report.pdf

Agents can be customized by modifying their instructions in backend/agents.py:

• Financial Agent: CFA-level financial analysis
• Technical Agent: CMT-level technical analysis
• Research Agent: Market research and sentiment analysis
• Competitive Agent: Strategic competitive analysis
• Report Agent: Professional report synthesis

intelligmarket/
├── backend/                 # Backend API server
│   ├── app.py              # Flask application factory
│   ├── config.py           # Configuration management
│   ├── agents.py           # AI agent definitions
│   ├── tools.py            # Agent tools and utilities
│   ├── workflows.py        # Multi-agent workflows
│   ├── requirements.txt    # Python dependencies
│   └── api/
│       ├── __init__.py
│       └── routes.py       # REST API endpoints
├── frontend/               # Frontend web application
│   ├── index.html         # Main HTML file
│   ├── css/
│   │   └── styles.css     # Professional styling
│   └── js/
│       ├── api.js         # API communication
│       └── main.js        # Application logic
├── .env                   # Environment variables
├── run.py                 # Application runner
└── README.md              # This file

1. Create tool class in backend/tools.py:

   class CustomTool(Toolkit):
       def custom_function(self, parameter: str) -> Dict[str, Any]:
           # Your tool logic here
           return {"result": "data"}

2. Add tool to relevant agent in backend/agents.py:

   tools=[FinancialDataTool(), CustomTool()]

1. Create agent class in backend/agents.py:

   class CustomAgent:
       def __init__(self):
           self.agent = Agent(
               name="Custom Agent",
               model=Gemini(id=Config.GEMINI_MODEL),
               tools=[CustomTool()],
               instructions=["Custom instructions"]
           )

2. Add to AgentFactory.create_all_agents() method

# Backend health check
curl http://127.0.0.1:5000/health

# Test single stock analysis
curl -X POST http://127.0.0.1:5000/api/analyze/stock \
  -H "Content-Type: application/json" \
  -d '{"symbol": "AAPL", "type": "quick"}'

1. Environment Variables

   FLASK_DEBUG=false
   SECRET_KEY=your-secure-secret-key
   CORS_ORIGINS=https://yourdomain.com
   LOG_LEVEL=WARNING

2. Backend Deployment

   # Using Gunicorn
   pip install gunicorn
   gunicorn -w 4 -b 0.0.0.0:5000 "backend.app:create_app()"

3. Frontend Deployment

   • Serve frontend/ directory via nginx, Apache, or static hosting
   • Update API base URL in frontend/js/api.js

# Dockerfile
FROM python:3.9-slim

WORKDIR /app
COPY backend/requirements.txt .
RUN pip install -r requirements.txt

COPY . .
EXPOSE 5000

CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:5000", "backend.app:create_app()"]

# Build and run
docker build -t intelligmarket .
docker run -p 5000:5000 -e GOOGLE_API_KEY=your_key intelligmarket

• Use "Quick Analysis" for faster results (30-60 seconds)
• Comprehensive analysis provides detailed insights (2-5 minutes)
• Cache results for repeated queries
• Monitor API usage to optimize costs
• PDF Generation: Optimized for institutional-quality reports with professional formatting

We welcome contributions! Please see our Contributing Guidelines for details.

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Make your changes
4. Add tests if applicable
5. Commit your changes: git commit -m 'Add amazing feature'
6. Push to the branch: git push origin feature/amazing-feature
7. Open a Pull Request

• Follow PEP 8 for Python code
• Use type hints where applicable
• Add docstrings for public methods
• Keep functions focused and small
• Use meaningful variable names

This project is licensed under the MIT License.

• AGNO Framework: High-performance multi-agent system foundation
• Google Gemini: Advanced AI capabilities for analysis
• YFinance: Real-time financial data access
• DuckDuckGo: Privacy-focused web search capabilities
• ReportLab: Professional PDF generation for institutional reports

• Email: [email protected]