QuantDinger

AI-Native Quantitative Trading Platform

Vibe Coding Meets Algo Trading

🇨🇳 中文  ·  🇺🇸 English

🌐 Live Demo  ·  📺 Video  ·  💬 Community  ·  🚀 Quick Start

7 AI Agents · Python Strategies · 10+ Exchanges · Prediction Markets · Your Server, Your Keys

Describe your trading idea in natural language → AI writes the Python strategy → Backtest → Live trade.
Zero coding required. Self-hosted — your API keys and strategies never leave your machine.

_{🇺🇸 English · 🇨🇳 简体中文 · 🇹🇼 繁體中文 · 🇯🇵 日本語 · 🇰🇷 한국어 · 🇩🇪 Deutsch · 🇫🇷 Français · 🇹🇭 ไทย · 🇻🇳 Tiếng Việt · 🇸🇦 العربية}

---

📑 Table of Contents

• 🚀 Quick Start (2 Minutes)
• 🎯 Why QuantDinger?
• 📸 Visual Tour
• ✨ Key Features
• 🔌 Supported Exchanges & Brokers
• 🏗️ Architecture & Configuration
• 📚 Documentation Index
• 💼 License & Commercial
• 🤝 Community & Support

---

🚀 Quick Start (2 Minutes)

Only need: Docker installed. Nothing else.

# 1. Clone
git clone https://github.com/brokermr810/QuantDinger.git
cd QuantDinger

# 2. Copy backend config
cp backend_api_python/env.example backend_api_python/.env

# 3. Generate and write a secure SECRET_KEY
./scripts/generate-secret-key.sh

# 4. Launch!
docker-compose up -d --build

Linux/macOS:

• Copy backend config: cp backend_api_python/env.example backend_api_python/.env
• Need more knobs? Scroll to the lower "Advanced / rarely changed" section inside: backend_api_python/env.example
• Optional: if Docker Hub is slow/unreachable in your network, copy root Docker config: cp .env.example .env
• Generate and write SECRET_KEY: ./scripts/generate-secret-key.sh
• Launch: docker-compose up -d --build

Windows PowerShell:

• Copy backend config: Copy-Item backend_api_python\env.example -Destination backend_api_python\.env
• Need more knobs? Scroll to the lower "Advanced / rarely changed" section inside: backend_api_python\env.example
• Optional: if Docker Hub is slow/unreachable in your network, copy root Docker config: Copy-Item .env.example -Destination .env
• Generate and write SECRET_KEY: $key = py -c "import secrets; print(secrets.token_hex(32))" (Get-Content backend_api_python\.env) -replace '^SECRET_KEY=.*$', "SECRET_KEY=$key" | Set-Content backend_api_python\.env -Encoding UTF8
• Launch: docker-compose up -d --build

⚠️ Security Note: The container will NOT start if SECRET_KEY is using the default value. This prevents insecure deployments.

🎉 Done! Open http://localhost:8888 | Login: quantdinger / 123456

📝 Key settings in backend_api_python/.env

# Required — Change for production!
ADMIN_USER=quantdinger
ADMIN_PASSWORD=your_secure_password
SECRET_KEY=your_random_secret_key  # ⚠️ MUST change! Generate with: python3 -c "import secrets; print(secrets.token_hex(32))"

# Optional — Enable AI features (pick one)
OPENROUTER_API_KEY=your_key        # Recommended: 100+ models
OPENAI_API_KEY=your_key            # GPT-4o
DEEPSEEK_API_KEY=your_key          # Cost-effective
GOOGLE_GEMINI_API_KEY=your_key     # Gemini

🔐 Generate SECRET_KEY (Required for Docker)

Before starting Docker, you MUST set a secure SECRET_KEY:

# Option 1: Use helper script (Linux/Mac)
./scripts/generate-secret-key.sh

# Option 2: Use helper script (Windows PowerShell)
.\scripts\generate-secret-key.ps1

# Option 3: Manual generation
python3 -c "import secrets; print(secrets.token_hex(32))"
# Then edit backend_api_python/.env and replace SECRET_KEY value

⚠️ The container will NOT start if SECRET_KEY is using the default value!

🔧 Common Docker Commands

docker-compose ps                  # View service status
docker-compose logs -f backend     # View backend logs (real-time)
docker-compose restart backend     # Restart backend only
docker-compose up -d --build       # Rebuild & restart all
docker-compose down                # Stop all services

Update to latest version:

git pull && docker-compose up -d --build

Backup & Restore database:

docker exec quantdinger-db pg_dump -U quantdinger quantdinger > backup.sql
cat backup.sql | docker exec -i quantdinger-db psql -U quantdinger quantdinger

Custom port — create .env in project root:

FRONTEND_PORT=3000          # Default: 8888
BACKEND_PORT=127.0.0.1:5001 # Default: 5000

Alternative image sources — Default uses Docker Hub. If pulling base images fails in your region/network, copy .env.example to .env and change one line:

IMAGE_PREFIX=docker.m.daocloud.io/library/

Other common choices:

IMAGE_PREFIX=
IMAGE_PREFIX=docker.xuanyuan.me/library/

Docker troubleshooting

1. Image source switching is controlled by the project-root `.env`, not `backend_api_python/.env`.
2. The open-source repo ships prebuilt frontend files in `frontend/dist`, so frontend deployment does not require Node.js.
3. On Windows, if backend logs show:
   exec /usr/local/bin/docker-entrypoint.sh: no such file or directory
   it is usually caused by shell/line-ending compatibility in the image layer. Rebuild the backend image with:
   docker-compose build --no-cache backend
4. If frontend logs show:
   host not found in upstream "backend"
   it usually means the backend container failed first. Fix backend, then restart frontend:
   docker-compose restart frontend
5. If frontend build fails with:
   COPY frontend/dist ... not found
   check `.dockerignore` and make sure `frontend/dist` is NOT excluded from the Docker build context.
6. If saving settings from the admin panel fails with:
   Read-only file system: '/app/.env'
   make sure `backend_api_python/.env` is mounted read-write in `docker-compose.yml`.
7. For Docker deployments, a local proxy must use `host.docker.internal`, not `127.0.0.1`.
   Example:
   PROXY_URL=socks5h://host.docker.internal:10808
8. If exchange logs say a symbol is "not found" after proxy/network fixes, it may be a market-symbol mapping issue
   on that exchange (for example, renamed tokens), not a general network failure.

---

🎯 Why QuantDinger?

Vibe Coding for Trading — Describe your trading idea in plain English (or any language). AI writes the Python strategy, backtests it, and deploys it to live markets. No manual coding. No SaaS lock-in. Everything runs on your own server.

🎵 Vibe Coding	Describe ideas in natural language → AI generates production-ready Python strategies
🔒 100% Self-Hosted	API keys & strategies never leave your server — privacy by design
🤖 7 AI Agents	Multi-agent research team: parallel analysis → debate → trade decision
🐍 Python-Native	Full ecosystem (Pandas, NumPy, TA-Lib, scikit-learn) — no proprietary language limits
📊 Professional Charts	K-line charts with Python indicators, real-time visualization
🌍 Crypto + Stocks + Forex	10+ exchanges, IBKR, MT5 — all in one platform
📊 Prediction Markets	On-demand AI analysis for Polymarket — probability divergence, opportunity scoring
💰 Monetization-Ready	Membership, credits, USDT on-chain payment — built-in
⚡ 2-Minute Deploy	docker-compose up -d — production-ready, zero build

---

📸 Visual Tour  |  📺 Watch Video Demo

📊 Professional Quant Dashboard
🤖 AI Deep Research	💬 Smart Trading Assistant
📈 Indicator Analysis	🐍 AI Strategy Coding
📊 Portfolio Monitor

---

✨ Key Features

🎵 Vibe Coding Strategy Workbench

No coding required. Tell AI what you want in natural language — it generates production-ready Python strategies. Or write your own with the full Python ecosystem (Pandas, NumPy, TA-Lib, scikit-learn). Visualize everything on professional K-line charts.

💬 "I want a MACD crossover strategy with RSI filter on BTC 15min"
    ↓ AI generates Python code
    ↓ 📈 Visualize on K-line charts
    ↓ 🔄 Backtest with rich metrics
    ↓ 🤖 AI suggests optimizations
    ↓ 🚀 One-click deploy to live trading

🤖 7-Agent AI Analysis Engine

Not just one AI call. QuantDinger deploys 7 specialized agents that collaborate like a research team — analyze, debate, and reach consensus:

Phase 1 (Parallel):  📊 Technical · 📑 Fundamental · 📰 News · 💭 Sentiment · ⚠️ Risk
Phase 2 (Debate):    🐂 Bull vs 🐻 Bear — structured argumentation
Phase 3 (Decision):  🎯 TraderAgent → BUY / SELL / HOLD (with confidence %)

• 🎵 Natural Language Analysis — Ask "Analyze BTC trend for next week" → 7 agents deliver a full report
• 📡 AI Trading Radar — Auto-scans Crypto/Stocks/Forex hourly, surfaces opportunities
• ⚡ Quick Trade Panel — See a signal? One-click to execute. No page switching.
• 🧠 Memory-Augmented — Agents learn from past analyses (local RAG, not cloud)
• 🔌 5+ LLM Providers: OpenRouter (100+ models), OpenAI, Gemini, DeepSeek, Grok
• 📊 Polymarket Prediction Markets — On-demand AI analysis for prediction markets. Input a market link or title → AI analyzes probability divergence, opportunity score, and trading recommendations. Full history tracking and billing integration.

📈 Full Trading Lifecycle

Step	What Happens
1. 💬 Describe	Tell AI your trading idea in natural language — or write Python directly
2. 🤖 Generate	AI creates the indicator & strategy code for you
3. 📊 Visualize	See signals on professional K-line charts instantly
4. 🔄 Backtest	Rich metrics + AI analyzes results & suggests improvements
5. 🚀 Execute	Live trade on 10+ crypto exchanges, IBKR (stocks), MT5 (forex)
6. 📡 Monitor	Portfolio tracker, alerts via Telegram/Discord/Email/SMS/Webhook

📊 Polymarket Prediction Market Analysis

On-demand AI analysis for prediction markets. Input a Polymarket link or market title → AI analyzes probability divergence, opportunity score, and provides trading recommendations.

Features:

• 🔍 Smart Search — Supports market links, slugs, or natural language titles
• 🤖 AI Probability Prediction — Compares AI-predicted probability vs market probability
• 📈 Opportunity Scoring — Calculates opportunity score based on divergence and confidence
• 💡 Trading Recommendations — YES/NO/HOLD with detailed reasoning and key factors
• 📚 History Tracking — View all your past analyses with full details in a dedicated history tab
• 💰 Billing Integration — Configurable credit consumption per analysis (set via BILLING_COST_POLYMARKET_DEEP_ANALYSIS)
• 🌍 Multi-Language — AI responses match your frontend language (English/Chinese)
• 📊 Admin Statistics — All analyses tracked in user management dashboard

Usage:

1. Navigate to AI Asset Analysis → Prediction Markets tab
2. Input Polymarket link or market title
3. AI analyzes and returns:
   - Market probability vs AI-predicted probability
   - Divergence analysis
   - Opportunity score (0-100)
   - Trading recommendation (YES/NO/HOLD)
   - Detailed reasoning and key factors
4. View analysis history anytime

💰 Built-in Monetization

Most open-source projects need months of custom billing work. QuantDinger ships with a complete monetization system out of the box:

• 💳 Membership Plans — Monthly / Yearly / Lifetime tiers with configurable pricing & credits
• ₿ USDT On-Chain Payment — TRC20 scan-to-pay, HD Wallet (xpub) per-order addresses, auto-reconciliation via TronGrid
• 🏪 Indicator Marketplace — Users publish & sell Python indicators, you take commission
• ⚙️ Admin Dashboard — Order management, AI usage stats, user analytics

🔐 Enterprise-Grade Security

• Multi-User — PostgreSQL-backed accounts with role-based permissions
• OAuth — Google & GitHub one-click login
• Protection — Cloudflare Turnstile, IP/account rate limiting, email verification
• Demo Mode — Read-only mode for public showcases

🧠 AI Agent Architecture Diagram (Click to expand)

flowchart TB
    subgraph Entry["🌐 API Entry"]
        A["📡 POST /api/analysis/multi"]
        A2["🔄 POST /api/analysis/reflect"]
    end
    subgraph Service["⚙️ Service Orchestration"]
        B[AnalysisService]
        C[AgentCoordinator]
        D["📊 Build Context<br/>price · kline · news · indicators"]
    end
    subgraph Agents["🤖 7-Agent Workflow"]
        subgraph P1["📈 Phase 1 · Parallel Analysis"]
            E1["🔍 MarketAnalyst"]
            E2["📑 FundamentalAnalyst"]
            E3["📰 NewsAnalyst"]
            E4["💭 SentimentAnalyst"]
            E5["⚠️ RiskAnalyst"]
        end
        subgraph P2["🎯 Phase 2 · Bull vs Bear Debate"]
            F1["🐂 BullResearcher"]
            F2["🐻 BearResearcher"]
        end
        subgraph P3["💹 Phase 3 · Final Decision"]
            G["🎰 TraderAgent → BUY / SELL / HOLD"]
        end
    end
    subgraph Memory["🧠 Local Memory Store"]
        M1[("Agent Memories (PostgreSQL)")]
    end
    subgraph Reflect["🔄 Reflection Loop"]
        R[ReflectionService]
        W["⏰ ReflectionWorker → verify + learn"]
    end
    A --> B --> C --> D
    D --> P1 --> P2 --> P3
    Agents <-.->|"RAG retrieval"| M1
    C --> R
    W -.->|"update memories"| M1

---

🔌 Supported Exchanges & Brokers

Cryptocurrency (Direct API Trading)

Exchange	Markets
Binance	Spot, Futures, Margin
OKX	Spot, Perpetual, Options
Bitget	Spot, Futures, Copy Trading
Bybit	Spot, Linear Futures
Coinbase	Spot
Kraken	Spot, Futures
KuCoin	Spot, Futures
Gate.io	Spot, Futures
Bitfinex	Spot, Derivatives

Traditional Brokers & Markets

Market	Broker/Source	Trading
US Stocks	Interactive Brokers (IBKR), Yahoo Finance, Finnhub	✅ Via IBKR
Forex	MetaTrader 5 (MT5), OANDA	✅ Via MT5
Futures	Exchange APIs	⚡ Data + Notify

Exchange Rebate Links

If you are opening a new exchange account, use a rebate link from the start. Many traders actively look for fee-rebate links anyway, and these links give you a straightforward 20% trading fee discount at no extra cost.

• OKX: Open account with 20% fee rebate
• Bitget: Open account with 20% fee rebate
• Bitget (backup link): Alternate 20% fee rebate signup link

---

🏗️ Architecture & Configuration

Tech Stack

Layer	Technology
AI Engine	7-Agent Multi-Agent System · RAG Memory · 5+ LLM Providers · Vibe Coding (NL→Python)
Backend	Python 3.10+ · Flask · PostgreSQL 16 · Redis (optional)
Frontend	Vue.js · Ant Design · KlineCharts · ECharts
Payment	USDT TRC20 On-Chain · HD Wallet (BIP-32/44) · TronGrid API
Mobile	Vue 3 + Capacitor (Android / iOS)
Deploy	Docker Compose · Nginx · Zero-build one-click

┌─────────────────────────────────────┐
│         Docker Compose              │
│                                     │
│  ┌───────────────────────────────┐  │
│  │  frontend (Nginx)  → :8888   │  │
│  └──────────────┬────────────────┘  │
│                 │ /api/* proxy       │
│  ┌──────────────▼────────────────┐  │
│  │  backend (Flask)   → :5000   │  │
│  └──────────────┬────────────────┘  │
│  ┌──────────────▼────────────────┐  │
│  │  postgres (PG 16)  → :5432   │  │
│  └───────────────────────────────┘  │
│                                     │
│  External: LLM APIs · Exchanges ·   │
│  TronGrid · Data providers          │
└─────────────────────────────────────┘

Repository Layout

QuantDinger/
├── backend_api_python/          # 🐍 Backend (Open Source, Apache 2.0)
│   ├── app/routes/              #   API endpoints
│   ├── app/services/            #   Business logic (AI, trading, payment)
│   ├── migrations/init.sql      #   Database schema
│   ├── env.example              #   ⚙️ Config template → copy to .env
│   └── Dockerfile
├── frontend/                    # 🎨 Frontend (Pre-built)
│   ├── dist/                    #   Static files (HTML/JS/CSS)
│   ├── Dockerfile               #   Nginx image
│   └── nginx.conf               #   SPA routing + API proxy
├── docs/                        # 📚 Guides & tutorials
├── docker-compose.yml           # 🐳 One-click deployment
└── LICENSE                      # Apache 2.0

⚙️ Configuration Reference (.env)

Use backend_api_python/env.example as the simplified template. The upper part is for first-time deployment, and the lower "Advanced / rarely changed" section contains optional tuning.

Category	Key Variables
Auth	SECRET_KEY, ADMIN_USER, ADMIN_PASSWORD
Database	DATABASE_URL (PostgreSQL connection string)
AI / LLM	LLM_PROVIDER, OPENROUTER_API_KEY, OPENAI_API_KEY
OAuth	GOOGLE_CLIENT_ID, GITHUB_CLIENT_ID
Security	TURNSTILE_SITE_KEY, ENABLE_REGISTRATION
Membership	MEMBERSHIP_MONTHLY_PRICE_USD, MEMBERSHIP_MONTHLY_CREDITS
USDT Payment	USDT_PAY_ENABLED, USDT_TRC20_XPUB, TRONGRID_API_KEY
Proxy	PROXY_URL
Workers	ENABLE_PENDING_ORDER_WORKER, ENABLE_PORTFOLIO_MONITOR

🔌 API Endpoints

Endpoint	Description
GET /api/health	Health check
POST /api/user/login	User authentication
GET /api/user/info	Current user info
GET /api/billing/plans	Membership plans
POST /api/billing/usdt/create-order	Create USDT payment order

For the full route list, see backend_api_python/app/routes/.

---

📚 Documentation Index

All detailed guides are in the docs/ folder:

Getting Started

Document	Description
Changelog	Version history & migration notes
Multi-User Setup	PostgreSQL multi-user deployment
Cloud Deployment	Cloud server deployment with domain, HTTPS, and reverse proxy

Strategy Development

Guide	🇺🇸 EN	🇨🇳 CN	🇹🇼 TW	🇯🇵 JA	🇰🇷 KO
Strategy Dev	EN	CN	TW	JA	KO
Cross-Sectional	EN	CN
Code Examples	examples/

Broker & Integration

Guide	English	中文
IBKR (US Stocks)	Guide	—
MT5 (Forex)	Guide	指南
OAuth (Google/GitHub)	Guide	指南

Notifications

Channel	English	中文
Telegram	Setup	配置
Email (SMTP)	Setup	配置
SMS (Twilio)	Setup	配置

---

💼 License & Commercial

Open Source License

Backend source code is licensed under Apache License 2.0. See LICENSE.

The frontend UI is provided as pre-built files. Trademark rights (name/logo/branding) are governed separately — see TRADEMARKS.md.

🎓 Free Source Code for Non-Profit & Education

If you are a university, research institution, non-profit, community group, or educational program, you can apply for free authorization and full frontend source code:

• 🏫 Universities & academic research
• 🌍 Open-source communities & developer groups
• 🤝 Non-profit & public welfare organizations
• 📚 Educational programs & student hackathons

💼 Commercial License

For commercial use, purchase a license to get:

• Full frontend source code + future updates
• Branding authorization — modify name/logo/copyright as agreed
• Operations support — deployment, upgrades, incident response
• Consulting — architecture review, performance tuning

📬 Contact

Channel	Link
Telegram	t.me/worldinbroker
Email	brokermr810@gmail.com

---

🤝 Community & Support

• Contributing Guide · Contributors
• Report Bugs / Request Features
• Email: brokermr810@gmail.com

---

💝 Support the Project

Crypto Donations (ERC-20 / BEP-20 / Polygon / Arbitrum)

0x96fa4962181bea077f8c7240efe46afbe73641a7

---

🎓 Supporting Partners

Quantitative Finance Society (QFS) Indiana University Bloomington

💡 Want to become a partner? Contact brokermr810@gmail.com or Telegram.

---

Acknowledgements

Built with ❤️ on the shoulders of: Flask · Pandas · CCXT · yfinance · Vue.js · Ant Design Vue · KlineCharts · ECharts · Capacitor · bip-utils

_{If QuantDinger helps you, consider ⭐ starring the repo — it means a lot!}