dragon1086/prism-insight

AI-based stock analysis and trading system

What it solves

PRISM-INSIGHT is an AI-powered system designed to automate the complex process of stock market analysis and trading. It solves the problem of manually tracking surge stocks, analyzing financial data, and managing portfolios across both Korean (KOSPI/KOSDAQ) and US (NYSE/NASDAQ) markets.

How it works

The system employs a multi-agent architecture consisting of over 13 specialized AI agents organized into teams (Macro, Analysis, Strategy, Communication, and Trading). These agents collaborate to detect stocks with unusual price/volume movements, generate professional-grade analysis reports, and execute trades via APIs. It integrates with various MCP servers for real-time data from Yahoo Finance, SEC filings, and KRX stock data, and includes a self-improving feedback loop where past trading journal entries inform future buy decisions.

Who it’s for

It is intended for investors who want AI-driven market insights, automated trading strategies, and professional-grade stock reports without needing to perform manual technical and fundamental analysis.

Highlights

  • Multi-Agent Orchestration: Uses 13+ specialized agents for macro intelligence, technical/financial analysis, and trade execution.
  • US and Korean Market Support: Full analysis and trading capabilities for both US and Korean stock exchanges.
  • Self-Improving Trading: A trading journal feedback loop that automatically improves future decisions based on historical win rates.
  • Flexible AI Access: Supports OpenAI API keys or direct integration via ChatGPT Plus/Pro subscriptions through an OAuth proxy.
  • Comprehensive Ecosystem: Includes a real-time performance dashboard, Telegram alerts, and a dedicated mobile app for iOS and Android.

Related

  • Project
    oficcejo/aiagents-stock

    An AI-powered multi-agent stock analysis system that simulates a professional analyst team to provide stock screening, macro-economic mapping, and automated trading for A-shares, Hong Kong, and US markets.

  • Project
    KylinMountain/TradingAgents-AShare

    A multi-agent AI system that simulates a professional investment research institution to provide deep analysis and trading suggestions for the A-share market.

  • Project
    hsliuping/TradingAgents-CN

    A multi-agent AI platform for stock analysis and research, specifically enhanced for Chinese users with support for A-shares and multiple LLM providers.

  • Project
    ArvinLovegood/go-stock

    go‑stock is a Windows/macOS desktop app that combines real‑time stock data with LLM‑driven analysis, offering chart tools, AI agents, back‑testing, alerts, and a skill‑sharing system. It works with many LLM providers (OpenAI, local models, Chinese cloud models) and is GPL‑v3 licensed.

  • Project
    rollingSirius/equity-research-skill

    An AI-powered equity research framework that transforms AI agents into institutional-grade analysts by enforcing rigorous valuation, forensic accounting, and industry-specific research protocols.