AI-Powered Stock Market Analysis & Trading System
13+ specialized AI agents collaborate to detect surge stocks, generate analyst-grade reports, and execute trades automatically.
English | νκ΅μ΄ | ζ₯ζ¬θͺ | δΈζ | EspaΓ±ol
AI3, creator of WrksAI - the AI assistant for professionals,
proudly sponsors PRISM-INSIGHT - the AI assistant for investors.
See AI trading performance in real-time: π analysis.stocksimulation.kr
Get daily surge stock alerts and AI analysis reports:
- πΊπΈ English Channel
- π°π· Korean Channel
- π―π΅ Japanese Channel
- π¨π³ Chinese Channel
- πͺπΈ Spanish Channel
Watch an AI-generated Apple Inc. analysis report:
The fastest way to try PRISM-INSIGHT. Only requires an OpenAI API key.
# Clone and run the quickstart script
git clone https://github.com/dragon1086/prism-insight.git
cd prism-insight
./quickstart.sh YOUR_OPENAI_API_KEYThis generates an AI analysis report for Apple (AAPL). Try other stocks:
python3 demo.py MSFT # Microsoft
python3 demo.py NVDA # NVIDIA
python3 demo.py TSLA --language ko # Tesla (Korean report)π‘ Get your OpenAI API key from OpenAI Platform
π° Optional: Add a Perplexity API key to
mcp_agent.config.yamlfor news analysis
Your AI-generated PDF reports will be saved in prism-us/pdf_reports/.
π³ Or use Docker (no Python setup needed)
# 1. Set your OpenAI API key
export OPENAI_API_KEY=sk-your-key-here
# 2. Start container
docker-compose -f docker-compose.quickstart.yml up -d
# 3. Run analysis
docker exec -it prism-quickstart python3 demo.py NVDAReports will be saved to ./quickstart-output/.
- Python 3.10+ or Docker
- OpenAI API Key (get one here)
# 1. Clone & Install
git clone https://github.com/dragon1086/prism-insight.git
cd prism-insight
pip install -r requirements.txt
# 2. Install Playwright for PDF generation
python3 -m playwright install chromium
# 3. Install perplexity-ask MCP server
cd perplexity-ask && npm install && npm run build && cd ..
# 4. Setup config
cp mcp_agent.config.yaml.example mcp_agent.config.yaml
cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml
# Edit mcp_agent.secrets.yaml with your OpenAI API key
# Edit mcp_agent.config.yaml with KRX credentials (Kakao account)
# 5. Run analysis (no Telegram required!)
python stock_analysis_orchestrator.py --mode morning --no-telegram# 1. Clone & Configure
git clone https://github.com/dragon1086/prism-insight.git
cd prism-insight
cp mcp_agent.config.yaml.example mcp_agent.config.yaml
cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml
# Edit config files with your API keys
# 2. Build & Run
docker-compose up -d
# 3. Run analysis manually (optional)
docker exec prism-insight-container python3 stock_analysis_orchestrator.py --mode morning --no-telegramπ Full Setup Guide: docs/SETUP.md
PRISM-INSIGHT is a completely open-source, free AI-powered stock analysis system for Korean (KOSPI/KOSDAQ) and US (NYSE/NASDAQ) markets.
- Surge Stock Detection - Automatic detection of stocks with unusual volume/price movements
- AI Analysis Reports - Professional analyst-grade reports generated by 13 specialized AI agents
- Trading Simulation - AI-driven buy/sell decisions with portfolio management
- Automated Trading - Real execution via Korea Investment & Securities API
- Telegram Integration - Real-time alerts and multi-language broadcasting
- Analysis & Trading: OpenAI GPT-5
- Telegram Bot: Anthropic Claude Sonnet 4.5
- Translation: OpenAI GPT-5 (EN, JA, ZH support)
13+ specialized agents collaborate in teams:
| Team | Agents | Purpose |
|---|---|---|
| Analysis | 6 agents | Technical, Financial, Industry, News, Market analysis |
| Strategy | 1 agent | Investment strategy synthesis |
| Communication | 3 agents | Summary, Quality evaluation, Translation |
| Trading | 3 agents | Buy/Sell decisions, Journal |
| Consultation | 2 agents | User interaction via Telegram |
π Detailed Agent Documentation: docs/CLAUDE_AGENTS.md
| Feature | Description |
|---|---|
| π€ AI Analysis | Expert-level stock analysis through GPT-5 multi-agent system |
| π Surge Detection | Automatic watchlist via morning/afternoon market trend analysis |
| π± Telegram | Real-time analysis distribution to channels |
| π Trading Sim | AI-driven investment strategy simulation |
| π± Auto Trading | Execution via Korea Investment & Securities API |
| π¨ Dashboard | Transparent portfolio, trades, and performance tracking |
| π§ Self-Improving | Trading journal feedback loop β past trigger win rates automatically inform future buy decisions (details) |
| πΊπΈ US Markets | Full support for NYSE/NASDAQ analysis |
| Metric | Value |
|---|---|
| Start Date | 2025.09.29 |
| Total Trades | 50 |
| Win Rate | 42.00% |
| Cumulative Return | 127.34% |
| Real Account Return | +8.50% |
π Live Dashboard
Same AI-powered workflow for US markets:
# Run US analysis
python prism-us/us_stock_analysis_orchestrator.py --mode morning --no-telegram
# With English reports
python prism-us/us_stock_analysis_orchestrator.py --mode morning --language enData Sources: yahoo-finance-mcp, sec-edgar-mcp (SEC filings, insider trading)
| Document | Description |
|---|---|
| docs/SETUP.md | Complete installation guide |
| docs/CLAUDE_AGENTS.md | AI agent system details |
| docs/TRIGGER_BATCH_ALGORITHMS.md | Surge detection algorithms |
| docs/TRADING_JOURNAL.md | Trading memory system |
A modern, responsive landing page built with Next.js and Tailwind CSS.
π Live Demo
cd examples/landing
npm install
npm run dev
# Visit http://localhost:3000Features: Matrix rain animation, typewriter effects, GitHub star counter, responsive design
Real-time portfolio tracking and performance dashboard.
cd examples/dashboard
npm install
npm run dev
# Visit http://localhost:3000Features: Portfolio overview, trading history, performance metrics, market selector (KR/US)
π Dashboard Setup Guide: examples/dashboard/DASHBOARD_README.md
- kospi_kosdaq - KRX stock data
- firecrawl - Web crawling
- perplexity - Web search
- sqlite - Trading simulation DB
- yahoo-finance-mcp - OHLCV, financials
- sec-edgar-mcp - SEC filings, insider trading
- Fork the project
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Create a Pull Request
Dual Licensed:
Free under AGPL-3.0 for personal use, non-commercial projects, and open-source development.
Separate commercial license required for SaaS companies.
π§ Contact: dragon1086@naver.com π Details: LICENSE-COMMERCIAL.md
Analysis information is for reference only, not investment advice. All investment decisions and resulting profits/losses are the investor's responsibility.
Monthly operating costs (~$310/month):
- OpenAI API: ~$235/month
- Anthropic API: ~$11/month
- Firecrawl + Perplexity: ~$35/month
- Server infrastructure: ~$30/month
Currently serving 450+ users for free.
- @jk5745 π
Achieved 250+ Stars in 10 weeks since launch!
β If this project helped you, please give us a Star!
π Contact: GitHub Issues | Telegram | Discussions





