Stock Research AI (Free-Stack Architecture)

Build a stock research AI system using free APIs and LLMs.

Updated Apr 26, 2026

Search Tags:#investment #LLM #stock analysis #AI trading #free APIs

Ready to run

npx skills add https://github.com/prafulkumar17/Stock-Analyser --skill stock-research-ai-free-stack-architecture

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Stock Research AI (Free-Stack Architecture)
Source: https://github.com/prafulkumar17/Stock-Analyser/tree/main/.agents/skills/ai_skill
Command: npx skills add https://github.com/prafulkumar17/Stock-Analyser --skill stock-research-ai-free-stack-architecture

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fastapi, uvicorn, langchain, langgraph, yfinance, pandas, pandas-ta, plotly, sqlalchemy, psycopg2, chromadb, sentence-transformers, newsapi-python, python-dotenv, apscheduler, google-generativeai, groq, ollama, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill guides the creation of a Stock Research AI application that analyzes stocks and mutual funds using free APIs and LLMs, providing fundamental analysis, technical indicators, trend visualization, news analysis, and AI-generated buy/sell insights.

Core Features & Use Cases

Free API and LLM Usage: Utilizes free APIs and LLMs for market analysis.
Stock Analysis: Offers fundamental and technical analysis.
News Analysis: Incorporates real-time financial news into analysis.
AI Decision Making: Provides AI-generated buy/sell recommendations.
Use Case: A user can input a stock ticker or company name to receive an analysis report including fundamental analysis, technical indicators, trend visualization, relevant news, and AI-generated buy/sell insights.

Quick Start

Use the Stock Research AI skill to analyze the stock of 'AAPL' and receive a comprehensive analysis report including buy/sell recommendations.

Frequently Asked Questions about Stock Research AI (Free-Stack Architecture)

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a stock analysis AI using free APIs and LLMs?▼

You can build a stock analysis AI by combining yfinance for market data, newsapi-python for real-time news, and LLMs via LangChain to generate fundamental analysis, technical indicators, and buy/sell recommendations.

Can I use LangChain and FastAPI to create an AI trading recommendation system?▼

Yes, you can use LangChain to orchestrate LLM analysis and FastAPI with Uvicorn to serve the stock research AI application, handling real-time data retrieval and AI-generated trading insights efficiently.

What is the best way to perform technical and fundamental stock analysis with Python?▼

The best way to perform technical and fundamental stock analysis in Python is using yfinance for historical data, pandas-ta for technical indicators, and Plotly for trend visualization to inform investment decisions.

Does this stock research AI approach support real-time financial news integration?▼

Yes, the stock research AI integrates real-time financial news using the newsapi-python library, allowing the LLM to factor current market events into its AI-generated buy/sell insights.

Do I need a paid API key to use LLMs for stock analysis?▼

No, you do not need a paid API key; the architecture utilizes free LLM access through Groq, Google Generative AI, and local Ollama models, alongside free APIs like yfinance for market data.

How does vector storage work with ChromaDB in an AI stock analysis workflow?▼

Vector storage with ChromaDB and sentence-transformers embeds financial news and stock data, enabling the LLM to retrieve relevant context for generating accurate trading recommendations.