OpenByteInc/QuantDinger

Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch your own multi-tenant trading SaaS with built-in user management, billing, payments, and settlement.

What it solves

QuantDinger is an open-source AI Trading OS designed for independent traders and small teams to move from AI-driven market research to live execution without relying on black-box signal services. It provides a self-hosted stack that keeps market data, strategy code, and broker credentials under the operator's control.

How it works

The system uses a distributed architecture with a Flask API and a Kafka event backbone to coordinate various specialized workers. It integrates AI providers (like OpenAI, DeepSeek, and Grok) for market analysis and uses a dedicated "Strategy API V2" for developing Python-based indicators and strategies. The platform supports a full lifecycle: AI research, Python strategy coding, server-side backtesting with parameter optimization, paper trading, and live execution across crypto exchanges and traditional brokers.

Who it’s for

It is built for independent traders, Python strategy authors, and small quantitative trading teams who want a professional, self-hosted infrastructure for automating their trading ideas.

Highlights

  • End-to-End Workflow: Covers the entire pipeline from AI research and strategy development to backtesting, paper trading, and live execution.
  • Distributed Runtime: Uses a modular backend with separate workers for trading, strategy evaluation, and scheduling to ensure operational stability.
  • AI Decision Filter: Integrates with TypeSafe Jev to provide a structured, typed AI decision gate for pre-trade validation instead of relying on prose parsing.
  • Self-Hosted Security: Local-first design with encrypted broker credentials and rootless production containers.
  • Multimodal Access: Accessible via web, mobile H5, Human API, Agent Gateway, and MCP.

Related

  • Project
    qusong0627/QuantMind

    QuantMind is an open‑source AI‑first quantitative‑trading platform that combines Microsoft Qlib, RD‑Agent LLM factor mining, and a chat‑bot (QuantBot) reachable from WeChat, QQ, Feishu, etc. It offers end‑to‑end data → factor → model → back‑test → simulated trading pipelines, 13 built‑in model types, autonomous factor evolution, and Docker‑based deployment.

  • Project
    Oft3r/agentic-trading-desk

    An agentic trading desk for stocks and ETFs that combines an AI orchestrator with deterministic Python scripts for technical analysis and strict execution guardrails.

  • Project
    microsoft/qlib

    An AI-oriented quantitative investment platform that provides a full ML pipeline for data processing, model training, and back-testing in quantitative trading.

  • Project
    TraderAlice/OpenAlice

    An AI orchestrator for trading that integrates AI agents, market data, and brokerage accounts into a local workspace for research and execution.

  • Project
    nautechsystems/nautilus_trader

    A production-grade, Rust-native trading engine that enables quantitative traders to use the same code for research, backtesting, and live multi-asset execution.