StockScreener
Performs detailed stock analysis utilizing a local AI assistant and web scraping for financial data.
About
This project offers a fully local AI assistant designed for in-depth stock analysis. It leverages the Model Context Protocol (MCP) for structured tool usage, Ollama to run local large language models (specifically Qwen3), and LangChain to orchestrate the AI application. By integrating BeautifulSoup, the assistant scrapes real-time financial data from Screener.in, providing comprehensive insights into company details, profit trends, and shareholding patterns.
Key Features
- Retrieve comprehensive company details including market cap, PE ratio, ROE, and ROCE
- Extract and analyze quarterly and yearly net profit data for financial performance
- Examine shareholding patterns from promoters, DIIs, FIIs, and the public
- Seamless integration with MCP tools for enhanced functionality
- Utilizes local LLMs (Ollama Qwen3) for privacy-focused analysis
- 0 GitHub stars
Use Cases
- Quickly obtain detailed financial information for specific companies.
- Analyze profitability trends and shareholding patterns for investment research.
- Develop and test local AI agents for financial data processing and analysis.
Sponsored