Democratizing hedge fund-level analysis for retail traders
Titan is a multi-agent AI system that solves the "Retail Synthesis Gap" - the inability of individual traders to simultaneously analyze technical indicators, news sentiment, and risk factors like institutional firms do.
Before Titan:
- ❌ Retail traders must manually calculate RSI, MACD, and Bollinger Bands
- ❌ Cannot process 50+ news headlines while analyzing charts
- ❌ No systematic approach to synthesizing conflicting signals
- ❌ Hedge funds have teams of analysts; you have Google Finance
With Titan:
- ✅ Instant technical analysis with 10+ indicators
- ✅ Parallel processing of price action + news + sentiment
- ✅ AI-powered conflict detection and resolution
- ✅ Professional-grade analysis in seconds
- Real-time Technical Analysis: RSI, MACD, Bollinger Bands, Moving Averages
- Price Action Detection: Trend identification, support/resistance levels
- Pattern Recognition: Golden Cross, Death Cross detection
- Volume Analysis: Institutional activity tracking
- Signal Generation: Clear BUY/SELL/HOLD with confidence scores
- Market Data Tool - Live OHLCV data fetching
- Technical Indicators Tool - 10+ indicator calculations
- Price Action Tool - Trend and pattern analysis
- Python 3.11 or higher
- pip package manager
- Virtual environment (recommended)
- Clone the repository
git clone https://github.com/Vyom-2007/market-analyst-project.git
cd market-analyst-project- Create and activate virtual environment
# Windows
python -m venv venv
venv\Scripts\activate
# Linux/Mac
python -m venv venv
source venv/bin/activate- Install dependencies
pip install -r requirements.txt- Set up environment variables
# Create .env file
echo "GOOGLE_API_KEY=your_api_key_here" > .envGet your Google AI API key from: https://makersuite.google.com/app/apikey
Run the main CLI for interactive queries:
python main.pyExample Queries:
💬 Your query: How does NVDA look technically?
💬 Your query: Analyze AAPL technical indicators
💬 Your query: What's the RSI for TSLA?
💬 Your query: Give me a technical analysis of Microsoft
Run the demo to see all tools in action:
python examples/phase1_demo.pyThis will analyze NVDA, AAPL, and TSLA with live market data.
# Install pytest if not already installed
pip install pytest
# Run all tests
pytest tests/test_quant_agent.py -v**Technical Analysis for NVDA**
Current Price: $495.50
**Indicators:**
- RSI (14): 58.3 → Neutral
- MACD: 2.15 (Signal: 1.87) → Bullish (MACD above signal)
- Bollinger Bands: $465.80 (Lower) | $475.50 (Middle) | $485.20 (Upper) → Middle range (neutral)
- 50-day MA: $470.30 | 200-day MA: $445.80 → Golden Cross territory (Bullish long-term)
- Volume: Normal volume (Ratio: 1.1x)
**Price Action:**
- Trend: Uptrend (Strength: 0.82)
- Support: $465.80 | Resistance: $495.00
- Pattern: Golden Cross (Bullish signal)
**Signal:** BUY
**Confidence:** 75%
**Reasoning:** RSI neutral with room to run. MACD showing bullish momentum.
Golden Cross formation indicates strong long-term trend. Price consolidating
before potential breakout above resistance.
Titan Investment Committee
│
├── 🧠 Root Agent (Committee Lead)
│ └── Orchestrates specialist agents
│
├── 📊 Quant Agent (Phase 1 - LIVE)
│ ├── Market Data Tool
│ ├── Technical Indicators Tool
│ └── Price Action Tool
│
├── 📰 Data Scout Agent (Basic)
│ └── News gathering capability
│
└── ⚠️ Risk Assessor Agent (Basic)
│ └── Risk evaluation
market-analyst-project/
├── market_analyst/ # Main package
│ ├── __init__.py
│ ├── agent.py # Root agent (Committee Lead)
│ ├── quant_agent.py # Quant analyst agent
│ ├── quant_tools.py # Technical analysis tools
│ ├── supporting_agents.py # Data Scout & Risk Assessor
│ └── tools.py # Basic tools
│
├── examples/
│ └── phase1_demo.py # Interactive demo
│
├── tests/
│ └── test_quant_agent.py # Test suite
│
├── main.py # CLI entry point
├── requirements.txt # Dependencies
├── .env # API keys (create this)
└── README.md # This file
- ✅ Market data fetching
- ✅ Technical indicators (RSI, MACD, Bollinger Bands)
- ✅ Price action analysis
- ✅ Trend detection
- ✅ Signal generation
- News scraper with Google Search integration
- Sentiment analysis (FinBERT)
- Source grounding and citation
- Parallel execution (Quant + Journalist simultaneously)
- Conflict detection and synthesis
- Portfolio correlation analysis
- Position sizing calculator
- Black swan risk detection
- Earnings calendar integration
- User preference learning
- Trade history tracking
- ChromaDB vector storage
- Context compaction
- Continuous market monitoring
- Price alert system
- Adaptive check intervals
- Structured logging
- A2A protocol for external integrations
- Paper trading validation
- Docker containerization
- Kubernetes deployment
- AI Framework: Google ADK (Agent Development Kit)
- LLM: Gemini 2.0 Flash Exp
- Market Data: yfinance (Yahoo Finance API)
- Technical Analysis: pandas-ta (130+ indicators)
- Data Processing: pandas, numpy
- Testing: pytest
- Search: DuckDuckGo Search API
- Titan Concept Analysis - Deep dive into the framework
- Implementation Plan - Phase 1 technical plan
- Phase 1 Walkthrough - Complete implementation guide
- Improvement Suggestions - Future enhancements
Contributions are welcome! Here's how you can help:
- Phase 2 Implementation: Build the Journalist Agent
- Tool Improvements: Add more technical indicators
- Testing: Expand test coverage
- Documentation: Improve examples and guides
Please read CONTRIBUTING.md for details.
This project is licensed under the MIT License - see the LICENSE file for details.
- Google ADK Team - For the powerful Agent Development Kit
- pandas-ta - For comprehensive technical analysis library
- yfinance - For reliable market data access
- Retail Traders Worldwide - For inspiring this project
- GitHub Issues: Report bugs or request features
- Discussions: Join the conversation
This is educational software. NOT financial advice.
- Titan is a proof-of-concept AI system for learning purposes
- Do NOT make real investment decisions based solely on AI analysis
- Always conduct your own research and consult financial professionals
- Past performance does not guarantee future results
- Trading involves substantial risk of loss
If you find Titan useful, please star the repository! ⭐
Built with ❤️ to democratize financial analysis