Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

jev-quant

Early C++ trading system that uses Jev via OpenRouter for instant decisions, with SimNow futures, Binance and a local simulated venue.

ModelprototypeMIT
View on GitHub ↗

Overview

jev-quant is a C++20 trading system that uses Jev, described as good at instant decisions, for trading decisions. It supports simulated Shanghai Futures Exchange trading through SimNow and the official CTP SDK, Binance, and an optional adapter to a separate local simulated venue that uses the real OpenRouter Jev provider.

It builds with CMake and Ninja, runs tests with ctest in CI, reads an OpenRouter key from .env, and runs as a foreground process. The author describes it as very early and warns to expect bugs. The README does not detail which questions Jev is asked or how risk is controlled, so the decision structure here is inferred.

What the decision model decides

TypeQuestionAnswers
ChoiceShould the strategy buy, sell or hold now?(inferred)buy · sell · hold

How it works

  1. Connect to SimNow, Binance or the local simulated venue
  2. Build market state
  3. Ask Jev for a trading decision
  4. Execute in the simulated or paper environment

Strengths

  • Native C++ implementation
  • Multiple simulated venues
  • CI with tests

Caveats

  • Very early; expect bugs
  • Decision logic not documented in the README
  • Uses simulated or paper trading

Getting started

cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DJEV_ENABLE_SIMEX=OFF && cmake --build build, set the OpenRouter key in .env, then ./build/jev_trading

At a glance

Type
Model
Status
prototype
Language
C++
Runtime
Native process
Has code
yes
Has tests
yes
License
MIT

Use cases and integrations

How curated lists describe it

Frequently asked questions

Does it trade real money?

It targets simulated and paper venues such as SimNow and a local simulator.

How does it reach Jev?

Through OpenRouter with an API key in .env.

Is it production-ready?

No. The author says it is very early and to expect bugs.

Related projects

  • jev-A-share-trader

    Local China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.

    ProjectbetaPython, TypeScript
  • jev-trading

    Local stock decision service that sends market data and news to Jev or a local model and returns a policy-checked buy/sell/hold.

    ProjectbetaTypeScript
  • ml-quant-trading

    PyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.

    ProjectbetaPython
  • QuantStudio

    Chinese open-source research and trading workbench whose JEV monitor watches futures contracts and judges entries and exits.

    ProjectbetaTypeScript
  • traderai

    Self-hosted trading analysis platform pairing Claude briefings with Jev probabilities for signals like thesis-breaking headlines.

    Servicebeta
  • Jev-Trades★ 51

    Next.js crypto dashboard where Jev judges each tick across timeframes and drives a SQLite paper-trading portfolio with automatic TP/SL.

    ServiceprototypeTypeScript