This project provides an AI-powered agent for automating sophisticated financial options analysis. It targets traders, analysts, and developers seeking intelligent processing of real-time options data, offering features like smart caching, persistent memory, and professional-grade analysis tools. The agent aims to streamline data retrieval, analysis, and export, reducing manual effort and enhancing decision-making.

How It Works

The agent is orchestrated using LangGraph, managing workflows between a chatbot interface, various tools, and an LLM (GPT-4o). It employs a microservice architecture with FastAPI for scalability. Core components include a tool suite for searching options data (Polygon.io), analysis, and export; persistent memory via SQLite; and a Retrieval-Augmented Generation (RAG) knowledge base using ChromaDB for semantic search and anomaly detection. This layered approach enables complex, stateful interactions with financial data.

Quick Start & Requirements

• Prerequisites: Python 3.9+, pip, OpenAI API Key, Polygon.io API Key, Tavily API Key (optional).
• Installation: Clone the repository, create a virtual environment, install dependencies via pip install -r requirements.txt, and configure API keys in a .env file.
• Run: Execute python agent_main.py for the CLI or cd microservice && python app.py for the FastAPI microservice.
• Links: No direct links to official quick-start guides or demos are provided within the README.

Highlighted Details

• Intelligent Data Caching: Utilizes ChromaDB and SQLite for smart hybrid storage, reducing API calls and improving response times.
• Persistent Memory: SQLite stores conversation history, enabling multi-session continuity and state retention across program restarts.
• Professional Analysis Tools: Includes options chain analysis with Greeks, sentiment detection, anomaly detection via vector similarity, and comparative analysis.
• Flexible Export Options: Supports standard CSV, custom CSV generation, PNG chart visualization, and professional reports.
• RAG Integration: Enables semantic search on historical data and automatic watchlist updates.
• Microservice Architecture: Exposes functionality via FastAPI endpoints, supporting Docker deployment for easy scalability.
• Performance Monitoring: Tracks token usage, tool execution metrics, and query performance, with built-in A/B testing evaluators.

Maintenance & Community

The project is marked as "Production Ready" with a last update in December 2025. No specific community channels (e.g., Discord, Slack) or notable contributors/sponsorships are mentioned in the README.

Licensing & Compatibility

The license type is not specified in the README. This omission requires further investigation for commercial use or integration into closed-source projects.

Limitations & Caveats

The primary adoption blocker is the absence of explicit licensing information, making it difficult to ascertain usage rights. The project relies heavily on external API keys (OpenAI, Polygon.io, Tavily), which may incur costs and are subject to rate limits. While described as "Production Ready," specific performance benchmarks are provided, but detailed known issues or unsupported platforms are not listed.