QuantDinger

Your Private AI Quant Operating System

Research markets, generate Python strategies, backtest ideas, and run live trading workflows on infrastructure you control.

Self-hosted AI trading platform for quant research, backtesting, execution, and operator-ready growth.

English · 简体中文 · Live Demo · Video Demo · Website · Telegram · Discord · YouTube

QuantDinger is a self-hosted, local-first quantitative trading and algorithmic trading platform for AI research, Python strategy generation, backtesting, and live execution.

Try in 2 Minutes

Fastest way to try QuantDinger locally:

git clone https://github.com/brokermr810/QuantDinger.git && cd QuantDinger && cp backend_api_python/env.example backend_api_python/.env && ./scripts/generate-secret-key.sh && docker-compose up -d --build

Then open:

http://localhost:8888
login with quantdinger / 123456
read backend_api_python/.env before production use

What Is QuantDinger?

QuantDinger is a self-hosted AI trading platform and quant research workspace for teams and operators who want one system for:

AI market analysis
Python indicator and strategy development
backtesting and strategy persistence
live trading execution
portfolio monitoring and alerts
multi-user operations, billing, and commercialization

If you are searching for an open source quant platform, AI trading research stack, self-hosted backtesting system, or natural-language-to-Python strategy workflow, this is what QuantDinger is built for.

Why QuantDinger? AI-Powered Quantitative Trading and Backtesting

Self-hosted by design: your credentials, strategy code, market workflows, and operational data stay under your control.
Research to execution in one product: AI analysis, charting, strategy logic, backtests, quick trade, and live operations are connected.
Python-native and AI-assisted: write indicators and strategies directly in Python, or use AI to accelerate drafting and iteration.
Built for operators, not just demos: Docker Compose, PostgreSQL, Redis, Nginx, health checks, worker toggles, and environment-based configuration.
Commercialization-ready: memberships, credits, admin management, and USDT payment flows are already part of the stack.

The Core Promise

QuantDinger gives you something most trading tools do not:

one stack instead of five for research, strategy code, backtests, execution, alerts, and operations
AI that sits inside the workflow, not beside it
Python flexibility without losing product UX
private deployment without giving up growth features

QuantDinger vs Patchwork Setups

Typical Setup	QuantDinger
AI chat tool disconnected from real strategy workflows	AI analysis, AI code generation, backtest feedback, and execution workflows live in one product
Separate charting app, Python scripts, bot runner, and notification stack	One deployable platform for charting, strategy logic, runtime services, and alerts
Hosted SaaS with limited control over credentials and alpha	Self-hosted architecture with your own infra, keys, and operational data
Research tools with no operator layer	Multi-user roles, billing, credits, admin controls, and deployment-ready configuration

Who It Is For

Traders and quants who want AI-assisted market research without giving up control of infrastructure and data.
Python strategy developers who want charting, backtests, and live execution in one environment.
Small teams and studios building internal trading tools or private research platforms.
Operators and founders who need a deployable product with user management, billing, and admin controls.

Use Cases

AI-assisted market research for crypto, stocks, forex, and cross-market workflows
Python-native strategy development for quantitative trading and algorithmic trading teams
Backtesting and iteration for signal strategies, saved strategies, and execution assumptions
Private trading infrastructure for teams that want self-hosted deployment and privacy-first operations
Commercial trading products that need users, billing, credits, and admin controls

Visual Tour


_{Indicator IDE, charting, backtest, and quick trade}	_{AI asset analysis and opportunity radar}
_{Trading bot workspace and automation templates}	_{Strategy live operations, performance, and monitoring}

What You Can Do With QuantDinger

AI Research and Decision Support

Run fast AI-driven market analysis across price action, kline structure, macro/news context, and selected external inputs.
Store analysis history and memory for repeatable review and future calibration.
Configure multiple LLM providers such as OpenRouter, OpenAI, Gemini, DeepSeek, and more.
Optionally enable ensemble and calibration-style flows for more robust AI outputs.

Indicator and Strategy Development

Build IndicatorStrategy workflows for dataframe-based signals, chart overlays, and signal backtests.
Build ScriptStrategy workflows for stateful runtime logic, explicit order control, and live execution alignment.
Generate indicator or strategy code from natural language and refine it in Python.
Visualize indicators, buy/sell signals, and strategy output directly on professional chart interfaces.

Backtesting and Iteration

Run historical backtests with stored trades, metrics, and equity curves.
Backtest both indicator-driven logic and saved strategy records.
Persist strategy snapshots and review historical runs for reproducibility.
Use AI-assisted post-backtest analysis to improve parameters and execution assumptions.

Live Trading and Operations

Connect crypto exchanges through a unified execution layer.
Use quick-trade flows to go from analysis to action faster.
Monitor open positions, review trade history, and close positions from the platform.
Run automated or semi-automated strategy workflows with runtime services and workers.

Multi-Market Coverage

Crypto spot and derivatives
US stocks through IBKR
Forex through MT5
Prediction market research through Polymarket analysis workflows

Multi-User, Alerts, and Billing

PostgreSQL-backed multi-user system with role-based access patterns.
OAuth support for Google and GitHub.
Notification channels including Telegram, Email, SMS, Discord, and Webhooks.
Membership plans, credits, USDT TRC20 payments, and admin-side billing controls.

AI Capabilities

QuantDinger is not just "LLM chat added to a trading app". The current AI layer is integrated into the actual research and strategy workflow.

Fast Analysis

Structured AI market analysis for quick decision support
Lower-latency workflow than older multi-hop orchestration
Useful for daily market review, trade planning, and opportunity screening

AI Strategy and Indicator Generation

Natural language to Python indicator code
Natural language to strategy code and config scaffolding
Better fit for traders who know the idea they want, but want to accelerate implementation

Analysis Memory and Review

Historical analysis storage
Better repeatability and comparison over time
A foundation for future calibration and reflection loops

Ensemble, Calibration, and Reflection

Optional multi-model ensemble configuration
Confidence calibration and reflection-style worker support
Better operational path for teams that want more stable AI-assisted workflows

AI-Assisted Backtest Feedback

Backtest outputs can feed into AI-generated suggestions
Useful for parameter tuning, risk adjustments, and faster iteration

Polymarket and Cross-Market Research

Analyze prediction markets as a research workflow
Compare AI view versus market-implied probabilities
Surface divergence and opportunity scoring

Why It Is Different

Most trading stacks give you one or two of these pieces. QuantDinger aims to give you the full operating system:

Self-hosted infrastructure
AI research workflows
Python strategy development
Backtesting
Live execution
Portfolio and notification operations
Commercialization primitives

That combination is the core difference.

Why It Converts Better Than a Typical Trading Tool

For traders: it shortens the path from idea to execution.
For quants: it keeps Python and strategy control front and center.
For operators: it adds the parts most open-source trading projects skip, including users, billing, roles, and deployability.
For AI-first workflows: it turns analysis into something actionable, reviewable, and eventually automatable.

How It Works

At a practical level, QuantDinger runs as a self-hosted application stack:

a prebuilt Vue frontend served by Nginx
a Flask API backend with Python services
PostgreSQL for state, users, strategies, and history
Redis for worker support and runtime coordination
exchange, broker, AI, payment, and notification integrations through configurable adapters

Architecture Summary

Layer	Technology
Frontend	Prebuilt Vue application served by Nginx
Backend	Flask API, Python services, strategy runtime
Storage	PostgreSQL 16
Cache / worker support	Redis 7
Trading layer	Exchange adapters, IBKR, MT5
AI layer	LLM provider integration, memory, calibration, optional workers
Billing	Membership, credits, USDT TRC20 payment flow
Deployment	Docker Compose with health checks

Execution Model

Market data is pulled through a pluggable data layer.
Backtests run on the server-side strategy engine, including strategy snapshot handling.
Live strategies run through runtime services that generate order intent.
Pending orders are then dispatched through exchange-specific execution adapters.
Crypto live execution is intentionally separated from market-data collection concerns.

System Diagram

flowchart LR
    U[Trader / Operator / Researcher]

    subgraph FE[Frontend Layer]
        WEB[Vue Web App]
        NG[Nginx Delivery]
    end

    subgraph BE[Application Layer]
        API[Flask API Gateway]
        AI[AI Analysis Services]
        STRAT[Strategy and Backtest Engine]
        EXEC[Execution and Quick Trade]
        BILL[Billing and Membership]
    end

    subgraph DATA[State Layer]
        PG[(PostgreSQL 16)]
        REDIS[(Redis 7)]
        FILES[Logs and Runtime Data]
    end

    subgraph EXT[External Integrations]
        LLM[LLM Providers]
        EXCH[Crypto Exchanges]
        BROKER[IBKR / MT5]
        MARKET[Market Data / News]
        PAY[TronGrid / USDT Payment]
        NOTIFY[Telegram / Email / SMS / Webhook]
    end

    U --> WEB
    WEB --> NG --> API
    API --> AI
    API --> STRAT
    API --> EXEC
    API --> BILL

    AI --> PG
    STRAT --> PG
    EXEC --> PG
    BILL --> PG
    API --> REDIS
    API --> FILES

    AI --> LLM
    AI --> MARKET
    EXEC --> EXCH
    EXEC --> BROKER
    BILL --> PAY
    API --> NOTIFY

Quick Start

Requirement: install Docker. Node.js is not required for deployment because this repository already includes the prebuilt frontend in frontend/dist.

Linux / macOS

git clone https://github.com/brokermr810/QuantDinger.git
cd QuantDinger
cp backend_api_python/env.example backend_api_python/.env
./scripts/generate-secret-key.sh
docker-compose up -d --build

Windows PowerShell

git clone https://github.com/brokermr810/QuantDinger.git
cd QuantDinger
Copy-Item backend_api_python\env.example -Destination backend_api_python\.env
$key = py -c "import secrets; print(secrets.token_hex(32))"
(Get-Content backend_api_python\.env) -replace '^SECRET_KEY=.*$', "SECRET_KEY=$key" | Set-Content backend_api_python\.env -Encoding UTF8
docker-compose up -d --build

After startup:

Frontend: http://localhost:8888
Backend health check: http://localhost:5000/api/health
Default login: quantdinger / 123456

Important deployment notes:

The backend container will not start if SECRET_KEY still uses the default value.
The main application config lives in backend_api_python/.env.
Root .env is optional and is mainly used for image mirrors or custom ports.
The default stack includes frontend, backend, postgres, and redis.

Common Docker Commands

docker-compose ps
docker-compose logs -f backend
docker-compose restart backend
docker-compose up -d --build
docker-compose down

Optional Root `.env`

If you need custom ports or image mirrors, create a root .env:

FRONTEND_PORT=3000
BACKEND_PORT=127.0.0.1:5001
IMAGE_PREFIX=docker.m.daocloud.io/library/

Minimal Example: Python Indicator Strategy

This is the kind of Python-native strategy logic QuantDinger is designed for:

# @param sma_short int 14 Short moving average
# @param sma_long int 28 Long moving average

sma_short_period = params.get('sma_short', 14)
sma_long_period = params.get('sma_long', 28)

my_indicator_name = "Dual Moving Average Strategy"
my_indicator_description = f"SMA {sma_short_period}/{sma_long_period} crossover"

df = df.copy()
sma_short = df["close"].rolling(sma_short_period).mean()
sma_long = df["close"].rolling(sma_long_period).mean()

buy = (sma_short > sma_long) & (sma_short.shift(1) <= sma_long.shift(1))
sell = (sma_short < sma_long) & (sma_short.shift(1) >= sma_long.shift(1))

df["buy"] = buy.fillna(False).astype(bool)
df["sell"] = sell.fillna(False).astype(bool)

See full examples:

Supported Markets, Brokers, and Exchanges

Crypto Exchanges

Venue	Coverage
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
Deepcoin	Derivatives integration
HTX	Spot, USDT-margined perpetuals

Traditional Markets

Market	Broker / Source	Execution
US Stocks	IBKR, Yahoo Finance, Finnhub	Via IBKR
Forex	MT5, OANDA	Via MT5
Futures	Exchange and data integrations	Data and workflow support

Prediction Markets

Polymarket is currently supported as a research and analysis workflow, not as direct in-platform live execution. It is useful for market lookup, divergence analysis, opportunity scoring, and AI-assisted review.

Strategy Development Modes

QuantDinger supports two main strategy authoring models:

IndicatorStrategy

dataframe-based Python scripts
buy / sell signal generation
chart rendering and signal-style backtests
best for research, indicator logic, and visual strategy prototyping

ScriptStrategy

event-driven on_init(ctx) / on_bar(ctx, bar) scripts
explicit runtime control with ctx.buy(), ctx.sell(), ctx.close_position()
best for stateful strategies, execution-oriented logic, and live alignment

For the full developer workflow, see:

Repository Layout

QuantDinger/
├── backend_api_python/      # Open backend source code
│   ├── app/routes/          # REST endpoints
│   ├── app/services/        # AI, trading, billing, backtest, integrations
│   ├── migrations/init.sql  # Database initialization
│   ├── env.example          # Main environment template
│   └── Dockerfile
├── frontend/                # Prebuilt frontend delivery package
│   ├── dist/
│   ├── Dockerfile
│   └── nginx.conf
├── docs/                    # Product, strategy, and deployment documentation
├── docker-compose.yml
├── LICENSE
└── TRADEMARKS.md

Configuration Areas

Use backend_api_python/env.example as the primary template. Key areas include:

Area	Examples
Authentication	`SECRET_KEY`, `ADMIN_USER`, `ADMIN_PASSWORD`
Database	`DATABASE_URL`
LLM / AI	`LLM_PROVIDER`, `OPENROUTER_API_KEY`, `OPENAI_API_KEY`
OAuth	`GOOGLE_CLIENT_ID`, `GITHUB_CLIENT_ID`
Security	`TURNSTILE_SITE_KEY`, `ENABLE_REGISTRATION`
Billing	`BILLING_ENABLED`, `BILLING_COST_AI_ANALYSIS`
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`, `ENABLE_REFLECTION_WORKER`
AI tuning	`ENABLE_AI_ENSEMBLE`, `ENABLE_CONFIDENCE_CALIBRATION`, `AI_ENSEMBLE_MODELS`

Documentation

Core Guides

Document	Description
Changelog	Version history and migration notes
Chinese Overview	Chinese product overview
Multi-User Setup	PostgreSQL multi-user deployment
Cloud Deployment	Domain, HTTPS, reverse proxy, and cloud rollout

Strategy Development

Guide	EN	CN	TW	JA	KO
Strategy Development	EN	CN	TW	JA	KO
Cross-Sectional Strategy	EN	CN	-	-	-
Examples	examples	-	-	-	-

Integrations

Topic	English	Chinese
IBKR	Guide	-
MT5	Guide	Guide
OAuth	Guide	Guide

Notifications

Channel	English	Chinese
Telegram	Setup	Config
Email	Setup	Config
SMS	Setup	Config

FAQ

Is QuantDinger really self-hosted?

Yes. The default deployment model is your own Docker Compose stack with your own database, Redis instance, credentials, and environment configuration.

Is QuantDinger only for crypto trading?

No. Crypto is a major focus, but the platform also includes IBKR workflows for US stocks, MT5 workflows for forex, and Polymarket research support.

Can I write strategies directly in Python?

Yes. QuantDinger supports both dataframe-style IndicatorStrategy development and event-driven ScriptStrategy development. You can also use AI to generate a starting point and then edit it yourself.

Is this a research tool or a live trading platform?

It is both. QuantDinger is built to connect AI research, charting, strategy development, backtesting, quick trade flows, and live execution operations in one system.

Can I use QuantDinger commercially?

The backend is licensed under Apache 2.0. The frontend source has a separate source-available license. Commercial use is supported, but you should review the licensing terms in this repository and contact the project for frontend/commercial authorization if needed.

Open Source Repositories

Repository	Purpose
QuantDinger	Main repository: backend, deployment stack, docs, prebuilt frontend delivery
QuantDinger Frontend	Vue frontend source repository for UI development and customization

Exchange Partner Links

The following links are available in-app under Profile -> Open account and may qualify users for trading-fee rebates depending on venue policies.

Exchange	Signup Link
Binance	Register
Bitget	Register
Bybit	Register
OKX	Register
Gate.io	Register
HTX	Register

License and Commercial Terms

Backend source code is licensed under Apache License 2.0. See LICENSE.
This repository distributes the frontend UI here as prebuilt files for integrated deployment.
The frontend source code is available separately at QuantDinger Frontend under the QuantDinger Frontend Source-Available License v1.0.
Under that frontend license, non-commercial use and eligible qualified non-profit use are permitted free of charge, while commercial use requires a separate commercial license from the copyright holder.
Trademark, branding, attribution, and watermark usage are governed separately and may not be removed or altered without permission. See TRADEMARKS.md.

For commercial licensing, frontend source access, branding authorization, or deployment support:

Legal Notice and Compliance

QuantDinger is provided for lawful research, education, system development, and compliant trading or operational use only.
No individual or organization may use this software, any derivative work, or any related service for unlawful, fraudulent, abusive, deceptive, market-manipulative, sanctions-violating, money-laundering, or other prohibited activity.
Any commercial use, deployment, operation, resale, or service offering based on QuantDinger must comply with all applicable laws, regulations, licensing requirements, sanctions rules, tax rules, data-protection rules, consumer-protection rules, and market or exchange rules in the jurisdictions where it is used.
Users are solely responsible for determining whether their use of the software is lawful in their country or region, and for obtaining any approvals, registrations, disclosures, or professional advice required by applicable law.
QuantDinger, its copyright holders, contributors, licensors, maintainers, and affiliated open-source participants do not provide legal, tax, investment, compliance, or regulatory advice.
To the maximum extent permitted by applicable law, QuantDinger and all related contributors and rights holders disclaim responsibility and liability for any unlawful use, regulatory breach, trading loss, service interruption, enforcement action, or other consequence arising from the use or misuse of the software.

Start Here

Want to see the product first? Open the Live Demo or watch the Video Demo.
Want to self-host quickly? Go straight to Quick Start and launch with Docker Compose.
Want to build strategies? Read the Strategy Development Guide.
Want cloud or production deployment? Use the Cloud Deployment Guide.
Want to license or customize it for a business? Contact the team through quantdinger.com.

Community and Support

Support the Project

Crypto donations:

0x96fa4962181bea077f8c7240efe46afbe73641a7

Acknowledgements

QuantDinger stands on top of a strong open-source ecosystem. Special thanks to projects such as:

_{If QuantDinger is useful to you, a GitHub star helps the project a lot.}

Name		Name	Last commit message	Last commit date
Latest commit History 215 Commits
.github		.github
.idea		.idea
backend_api_python		backend_api_python
docs		docs
frontend		frontend
scripts		scripts
.dockerignore		.dockerignore
.env.example		.env.example
.gitignore		.gitignore
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
DEVELOPMENT.md		DEVELOPMENT.md
LICENSE		LICENSE
README.md		README.md
SECURITY.md		SECURITY.md
TRADEMARKS.md		TRADEMARKS.md
docker-compose.yml		docker-compose.yml

Uh oh!

Folders and files

Latest commit

History

Repository files navigation