MCP servers

OpenByteInc/QuantDinger

The most complete open-source, self-hosted Agentic Trading OS—AI research, Python strategies, factor discovery, backtesting, optimization, paper/live multi-asset execution, risk controls, monitoring, MCP, and multi-tenant SaaS in one auditable stack.

Stars
13,900
+7 days
—
Forks
2,827
Language
Python
License
Apache-2.0
Last push
21 Nov 2026

Summary

Summary written by AI from the README; it may be imprecise.

This open-source, self-hosted quantitative trading operating system connects AI research, Python strategy development, backtesting, and multi-asset execution across crypto exchanges and traditional brokers. It includes an MCP server and Agent Gateway, allowing developer tools like Claude Code to inspect market data, run factor benchmarks, and manage paper or live trades without sharing sensitive broker credentials. The stack runs sandboxed strategy processes with PostgreSQL state management, Celery and Kafka workers, and optional Prometheus and Grafana observability.

Use it when

  • When building, backtesting, or executing Python trading strategies via AI assistants using MCP
  • When hosting a self-contained quant trading platform with paper and live multi-asset execution
  • Connect Claude Code to a local quant backend for factor discovery and automated backtesting

Install

The README has no clear install command. See the instructions on GitHub.

Stars over 90 days

Collecting: 2 of 90 days so far. The chart appears after 7 days.

Type to search the reference, templates and lessons.