GitHub · Trading and markets
OpenByteInc/QuantDinger
A trading stack that ships with the decision layer documented rather than implied.
What it does
A self-hosted "AI trading OS": turn an idea into a Python strategy, backtest it, paper trade, then go live, with monitoring. The README's own line for the pipeline is research → strategy code → backtest → paper/live execution → monitoring, and it lists a Jev System One integration alongside agent and MCP documentation.
The repository's own description: “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.”
How it works
`backend_api_python/` is the server, `mcp_server/` exposes it to agents, `ops/` holds deployment material, and there is a `.cursor/skills/quantdinger-agent-workflow` skill — the agent layer is a first-class part of the repository, not an add-on.
The repository, by the numbers
Read from the GitHub API on 2026-09-22. Stars and the last push move daily — quote them with the date, the way we do.
What we checked
- the tree: backend_api_python, mcp_server, ops, docs, scripts
- Apache-2.0 LICENSE
- README describes the five-stage pipeline and a live app at ai.quantdinger.com
- the description names a Jev System One integration and links separate agent/MCP docs
What we did not check. We did not install it and there is no published performance or P&L figure in the README to check.