If the Jev gate goes down, does it block my exit orders?

No. Exits and protective orders bypass the gate deterministically, so a failed judgment cannot trap you in a position. Only entry orders from strategies and Quick Trade go through the PASS/REJECT decision, with a configurable LLM fallback covering gate errors.

What exactly gets sent to TypeSafe on each gated order?

The prepared decision context for that order, sent to the configured AI provider over the System One HTTP contract at POST /v1/systemone. The README section describing the gate is not present in the copy fetched here, so the precise fields are not documented.

Will a convincing backtest fool me into thinking this predicts returns?

The project says the opposite about its own output. Strategy evolution reports PBO, Deflated Sharpe, block-bootstrap Monte Carlo and transaction-cost stress tests, then states that results compare parameter robustness and do not forecast future returns.

Can this actually place real money trades?

Yes, once live trading is explicitly enabled, and the README warns about exactly that. Its own guidance is to start with paper trading, use restricted API keys, and review the risk and compliance requirements for your jurisdiction.

What stack does QuantDinger run on?

A self-hosted stack of Python 3.12, PostgreSQL 18, Redis 8 and Docker Compose, with a Flask and Gunicorn API, separated trading and scheduler workers, Kafka, and optional Prometheus and Grafana monitoring.

How do signal-only virtual accounts work?

They turn notification-mode signals into internal virtual orders, fills, positions, trade records, PnL and an equity curve, never connecting to a broker. Each fill charges a fixed 0.05% commission on notional and 0.05% adverse slippage.

Can AI agents drive QuantDinger?

Yes. Access is offered through the web UI, mobile H5, a human API, an Agent Gateway and MCP, and the project ships dedicated AI Agents and MCP documentation for integrating agents.

Jev directory

CommunityJev Cookbooks

QuantDinger

A self-hosted AI trading platform that can put Jev in front of strategy and Quick Trade entry orders as an auditable PASS/REJECT gate, with LLM fallback and deterministic bypasses for exits and protective orders.

See highlights Open github.com

Stars: 12.9k
Language: Python
License: APACHE-2.0
Reading time: 3 min
Published by: Community
Author: OpenByteInc
Last verified: Sep 2026

OpenByteInc/QuantDinger

Organization repository on GitHub

View on GitHub

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.

Forks: 2.7k
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

QuantDinger Open-source AI Trading OS Turn trading ideas into Python strategies, backtests, paper trading, live execution, and monitoring — all in one self-hosted stack. QuantDinger is a product of Open Byte Inc. AI research → Strategy code → Backtest → Paper/Live execution → Monitoring. English · 简体中文 · API · AI Agents & MCP. Live App · Website · Video Demo · Official Support Email.

Quoted from the project's README. Read the full README.

Tagscommunity python trading mcp postgres

Works forJev for Tool calling

Used inJev for Finance & Fintech Jev for Data & Analytics

Highlights

Jev gates entry orders only: exits and protective orders bypass it deterministically, and a configurable LLM fallback handles gate errors.
Enabling the filter sends the prepared decision context to the configured AI provider through the System One HTTP contract at POST /v1/systemone.
The v5 backend separates the HTTP API from trading, scheduling, Celery jobs, and migrations, with PostgreSQL state, audit logs, and Prometheus metrics.
Installs with a one-command Docker Compose script; paper trading is the documented starting point before live keys.
Agent tokens are hashed, scoped, rate-limited, and audit-logged; the production overlay runs non-root with a read-only root filesystem.

Quickstart

bash

curl -fsSL https://raw.githubusercontent.com/OpenByteInc/QuantDinger/main/install.sh | bash

Watch out

Apache-2.0-licensed. Needs Docker with Compose v2 and an AI provider key; it can submit real orders once live trading is enabled, so start on paper trading with restricted API keys.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Jev in front of the HeyGen MCP

X: Playwright CLI + Jev vs Playwright MCP

X: A trading loop with Jev and GPT-6 Astra

X: News sentiment in a trading terminal

From the Jev guides

Original write-ups on what this entry is for.

Trading repos put Jev at the decision point, not the price

Oct 16, 2026

Per-tick buy/sell calls on Monad, a five-sleeve Hyperliquid desk, Nifty-50 rankers, and Polymarket confidence gates: how the catalog's trading repos wire Jev in without asking it to predict prices.

Jev Practices & Patterns#trading#markets#gates

Read article

Retrieval with Decisions: Filter, Rerank, and Verify

Oct 12, 2026

Retrieval is a sequence of bounded judgments. How a decision model slots into passage filtering, semantic find, reranking, and citation checks, and what stays in deterministic code.

Jev Cookbooks#retrieval#reranking#rag

Read article

One Request, Many Questions: Batching, Fan-Out, and Composite Scoring

Sep 12, 2026

Jev bills input tokens and gives output away, and questions in one request run in parallel. The design consequence is simple: ask more per call, then decide in code.

Jev Cookbooks#batching#patterns#search

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

QuantDinger

About this project

Highlights

Quickstart

Questions about this entry

If the Jev gate goes down, does it block my exit orders?

What exactly gets sent to TypeSafe on each gated order?

Will a convincing backtest fool me into thinking this predicts returns?

Can this actually place real money trades?

What stack does QuantDinger run on?

How do signal-only virtual accounts work?

Can AI agents drive QuantDinger?

Reactions & coverage

Related terms

More Jev resources like this

From the Jev guides

From the Jev AI model community