Verified project record

OpenByteInc/QuantDinger

quantdinger is a self-hosted AI Trading OS that enables users to develop Python strategies and run multi-provider AI market research, server-side backtesting, paper/live execution, and monitoring within a single stack. Its local-first design keeps market data, strategy code, broker credentials, and deployment under the operator's control.

Project overview

By combining server-side backtesting, multi-provider AI market research, and live execution into one self-hosted stack, quantdinger gives independent traders operational control over their data and credentials while supporting automated workflows through an Agent Gateway and MCP server.

Project type: AI Agent · Workflow
Use cases: Automation
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Independent traders and small teams who want to turn trading ideas into backtested and executed strategies while maintaining local control over their data and credentials.

Key capabilities

Performs multi-provider AI market research and analysis.
Develop Python indicators and Strategy API V2 intents, sizing, risk, backtests, and live runtime.
Executes server-side backtests and experiment workflows.
Provides a scoped Agent Gateway API exposed under /api/agent/v1 for automated clients.
A standalone MCP server that allows clients to call approved tools without receiving broker credentials or administrator JWTs.

Limitations and risks

The project does not provide investment advice.
Desktop and mobile client source code live in separate repositories; this repository consumes their published images.
quantdinger can submit real orders when live trading is explicitly enabled.

Getting started

Run the one-command installer for prebuilt images, provide the initial administrator credentials, and open the web GUI at http://127.0.0.1:8888. Node.js and a local Python environment are not required for prebuilt images.

Evidence and sources

README: This project does not provide > investment advice.
README: Open-source AI Trading OS
README: QuantDinger is an **open-source AI Trading OS** for independent traders, Python strategy authors, and small teams. Its local-first, self-hosted design keeps market data, strategy…
README: PostgreSQL-backed state, durable workers, audit logs, and optional monitoring.
README: the production overlay runs backend processes as a non-root user with a read-only root filesystem, dropped capabilities, and resource limits;

Reviewed at: 2026-07-22T05:17:14Z