HomeProjectsArticlesPK BoardAbout
Explore Projects

QuantDinger

Active
GitHub Python Apache-2.0

Description

An open-source AI infrastructure layer for quant trading that turns trading ideas into Python strategies, backtests, paper trading, and live execution across crypto, stocks, and forex.

Key Features

  • End-to-end trading pipeline - from AI research to strategy code, backtest, paper and live execution
  • Multi-market support - connects Binance, Coinbase, Alpaca, MT5, and other major exchanges and brokers
  • Multi-agent research - agents collaborate on strategy research and factor discovery
  • Built-in backtesting engine - historical backtests and performance evaluation
  • MCP integration - exposes trading capabilities over MCP for agent invocation
  • Self-hosted deployment - ships as a Docker image and a hosted SaaS

Use Cases

💡 Turn natural-language trading ideas into backtestable Python strategies fast
💡 Research crypto and forex factors with collaborative multi-agent workflows
💡 Backtest and paper-trade strategies before going live
💡 Self-host a team-grade quant research and execution platform

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (11.3k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Responsive to issues, low backlog

Tags

quant-trading multi-agent backtesting mcp finance

Categories

🧠 Multi-Agent 🔄 Workflow

Quick Start

# Launch the QuantDinger self-hosted platform with Docker
docker run -d -p 8000:8000 --name quantdinger brokermr810/quantdinger
# Open http://localhost:8000 to configure exchanges and strategies
Visit GitHub Visit Website

Related Projects

Mission Control

6.2k · TypeScript
Active A+

Self-hosted AI agent orchestration platform for dispatching tasks, running multi-agent workflows, monitoring spend, and governing operations

orchestrationmulti-agentself-hosted +3
  • · Self-hosted AI agent orchestration dashboard with 32 panels for tasks, agents, logs, security, and more
  • · Real-time updates via WebSocket and SSE with smart polling that pauses when idle
  • · Zero external dependencies: SQLite backend with single `pnpm start` to run
View full details → View on GitHub

Solace Agent Mesh

5.0k · Python
Active A+

Solace Agent Mesh is an event-driven multi-agent AI framework for building and orchestrating multi-agent systems with MCP integration and complex multi-step workflows.

multi-agentevent-drivenmcp +3
  • · Multi-agent event-driven architecture via Solace Event Mesh for true scalability
  • · Automatic agent orchestration with task decomposition and delegation
  • · Flexible gateway interfaces: REST API, web UI, Slack, and custom integrations
View on GitHub

Vibe-Trading

32.4k · Python
Active A+

Vibe-Trading is an open-source personal trading agent stack that combines LLMs, MCP tooling, and multi-agent workflows for algorithmic trading and backtesting.

ai-agentalgorithmic-tradingbacktesting +5
  • · One command empowers your trading agent with full quantitative trading capabilities via LLM + MCP toolchain
  • · Backtesting engine supporting 7 data sources (Tushare, OKX, CCXT, AkShare, etc.) with local caching
  • · Connector-first architecture supporting IBKR, Robinhood, Tiger, Alpaca, OKX, Binance paper trading
View full details → View on GitHub

Cultivation World Simulator

2.1k · Python
Active A

An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world. Showcases multi-agent collaboration in complex scenarios.

multi-agentworkflowagent +1
  • · Every NPC is an independent LLM-driven agent with unique personality, memory, relationships, and decision-making logic
  • · Emergent storytelling with no preset scripts — sect wars, rivalries, and character arcs arise from world rules and AI interactions
  • · Rich cultivation world system including spirit roots, realms, techniques, sects, alchemy, artifacts, and martial tournaments
View on GitHub