AI agent that researches stocks like a team of analysts — runs Bull vs Bear debates, challenges its own reasoning, and delivers probability-weighted verdicts. Built with LangGraph, FastAPI, and React.
# StockSense Agent **AI-Powered Autonomous Stock Market Research (ReAct Pattern)** StockSense is an autonomous stock analysis system implementing the **ReAct (Reasoning + Action)** pattern: iterative reasoning, selective tool invocation, and adaptive summarization. The agent collects real market data (news + historical prices), performs LLM-based sentiment analysis, and produces a structured summary. [](https://www.python.org/downloads/) [](https://fastapi.tiangolo.com/) [](https://react.dev/) [](https://langchain-ai.github.io/langgraph/) [](https://python.langchain.com/) [](LICENSE) --- ## Table of Contents - [Overview](#overview) - [Architecture](#architecture) - [Features](#features) - [Quick Start](#quick-start) - [API Reference](#api-reference) - [Testing](#testing) - [Deployment](#deployment) - [Contributing](#contributing) - [License](#license) - [Acknowledgments](#acknowledgments) - [Technical Highlights](#technical-highlights) - [Author](#author) --- ## Overview StockSense is not a simple chatbot wrapper — it's a **production-grade agentic AI system** that demonstrates advanced patterns in autonomous reasoning, multi-agent coordination, and real-time streaming. ### What Makes This Different Most AI stock analysis tools send a single prompt and return a response. StockSense takes a fundamentally different approach: | Traditional Approach | StockSense Approach | |---------------------|---------------------| | Single prompt → single response | Iterative reasoning loop with multiple tool calls | | One perspective | Multiple agents with opposing viewpoints |
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.