FinFlow AI Agents 🤖💰

A comprehensive Multi-Agent Financial Analysis Platform built with LangGraph, CrewAI, and FastAPI.

🚀 Features

• Multi-Agent System: Research, Analysis, Risk, Report, and Compliance agents
• RAG Pipeline: SEC filings and earnings calls knowledge base
• Real-time Data: Integration with Yahoo Finance, Alpha Vantage, FRED APIs
• Observability: MLflow and OpenTelemetry logging
• Security: API key management and audit trails
• Governance: Bias monitoring and decision explainability

🏗️ Architecture

FinFlow AI Agents/
├── agents/           # Agent implementations
├── api/             # FastAPI endpoints
├── core/            # Core utilities and models
├── data/            # Data processing and storage
├── tools/           # External API integrations
├── config/          # Configuration management
└── tests/           # Test suite

🛠️ Tech Stack

• LangGraph: Agent orchestration and workflow management
• CrewAI: Multi-agent collaboration framework
• FastAPI: High-performance API framework
• Chroma: Vector database for RAG
• AWS: Cloud infrastructure and services
• MLflow: Experiment tracking and model management
• OpenTelemetry: Observability and monitoring

📦 Installation

# Clone the repository
git clone https://github.com/yourusername/finance-gpt-agents.git
cd finance-gpt-agents

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Set up environment variables
cp .env.example .env
# Edit .env with your API keys

🔧 Configuration

Create a .env file with your API keys:

# OpenAI API
OPENAI_API_KEY=your_openai_key

# Financial APIs
YAHOO_FINANCE_API_KEY=your_yahoo_key
ALPHA_VANTAGE_API_KEY=your_alpha_vantage_key
FRED_API_KEY=your_fred_key

# AWS Configuration
AWS_ACCESS_KEY_ID=your_aws_key
AWS_SECRET_ACCESS_KEY=your_aws_secret
AWS_REGION=us-east-1

# Database
CHROMA_PERSIST_DIRECTORY=./data/chroma

🚀 Quick Start

# Start the FastAPI server
uvicorn api.main:app --reload

# Run agent workflow
python -m core.workflow --symbol AAPL --analysis_type comprehensive

📊 API Endpoints

• POST /api/v1/analyze: Comprehensive financial analysis
• GET /api/v1/agents/status: Agent status and health
• POST /api/v1/research: Financial research request
• GET /api/v1/reports/{report_id}: Retrieve analysis reports

🤖 Agents Overview

ResearchAgent

• Gathers financial data from multiple APIs
• Processes SEC filings and earnings calls
• Maintains knowledge base with Chroma

AnalysisAgent

• Performs quantitative analysis
• Generates financial ratios and metrics
• Creates technical analysis charts

RiskAgent

• Assesses portfolio risks
• Calculates VaR and stress tests
• Monitors market volatility

ReportAgent

• Generates executive summaries
• Creates comprehensive reports
• Formats data for stakeholders

ComplianceAgent

• Ensures regulatory compliance
• Monitors for bias and fairness
• Maintains audit trails

📈 Usage Examples

from core.workflow import FinancialAnalysisWorkflow

# Initialize workflow
workflow = FinancialAnalysisWorkflow()

# Run comprehensive analysis
result = workflow.analyze(
    symbol="AAPL",
    analysis_type="comprehensive",
    include_risk_assessment=True
)

print(result.report)

🧪 Testing

# Run all tests
pytest

# Run specific test categories
pytest tests/test_agents/
pytest tests/test_api/
pytest tests/test_tools/

📚 Documentation

• Agent Architecture
• API Reference
• Deployment Guide
• Contributing Guidelines

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request

📄 License

MIT License - see LICENSE for details.

🙏 Acknowledgments

• LangGraph team for the excellent agent orchestration framework
• CrewAI for multi-agent collaboration patterns
• FastAPI for the high-performance API framework

---

Built with ❤️ for the open-source community