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

jev-trade

Live Hyperliquid trading desk where Jev chooses long or short and open, close or hold each tick for five coins, with dry-run by default.

AppprototypeCustom license
View on GitHub ↗Live demo ↗

Overview

Jev Trade is a trading bot and live dashboard built on Jev and based on Jarrod Watts's jev-trader, moved to Hyperliquid. Each tick the bot reads the order book for one of five isolated sleeves (BTC, ETH, SOL, DOGE, BNB), each with its own wallet and its own Jev call. Jev picks long or short, then open, close or hold; a listing also mentions a leverage Choice. Hold is a valid answer, so a tick can end with no order.

Entries are post-only quotes one tick inside the touch on the maker side; exits are immediate-or-cancel orders that cross the touch; hold pulls any resting quote Jev no longer wants. Position, balance and PnL come from Hyperliquid. The bot runs on Bun with a Next.js dashboard showing candles, fills, the latest Jev call and a tape of every tick. Without a private key it dry-runs with real book data and simulated fills, and the default mock model is a momentum stand-in. Jev can be reached via TypeSafe directly or the Vercel AI Gateway. A live key sends real orders.

What the decision model decides

TypeQuestionAnswers
ChoiceShould this sleeve go long or short?long · short
ChoiceShould the bot open, close or hold the position?open · close · hold

How it works

  1. Read the Hyperliquid book each tick
  2. Jev chooses direction and open/close/hold
  3. Entry: post-only quote inside the touch; exit: IOC crossing the touch
  4. Hold sends no order and pulls stale quotes; dashboard streams results

Strengths

  • Dry-run mode with real data and simulated fills
  • Isolated per-coin sleeves
  • Live public dashboard

Caveats

  • Live keys place real orders; experimental, not advice
  • Custom licence; no reported performance evaluation

Getting started

cp .env.example .env && bun install && bun run start, then `bun run dev:web` and open http://localhost:3001.

At a glance

Type
App
Status
prototype
Language
TypeScript
Runtime
Bun + Next.js
Has code
yes
License
Custom license
Stars
207

Use cases and integrations

How curated lists describe it

  • Crypto trading: asks Jev for a Choice of long or short on a Hyperliquid market each round, places that order, and runs the same loop across many assets.

    yibie/awesome-jev

  • Live Hyperliquid desk: each tick Jev answers Choice questions for long/short, open/close/hold, and leverage; code places or pulls the quote. Dry-run by default; a live key sends real orders. Demo: [jev-trade.com](https://www.jev-trade.com/).

    AnotiaWang/awesome-decision-models

  • An experimental Hyperliquid trading bot using Jev to choose long or short and whether to open, close, or hold.

    logicrw/awesome-jev-projects

  • Live Jev trader on Hyperliquid

    wh000wh000/awesome-jev-live

  • Hyperliquid trading desk where Jev answers Choice questions for long/short, open/close/hold, and leverage; application code quotes or sends no order. Defaults to a dry run; a live key can place real orders.

    cobanov/awesome-jev

  • Live Jev trader on Hyperliquid.

    hellogumbo/awesome-jev

  • Hyperliquid trading bot based on jev-trader, where Jev decides buy, sell, or hold on every tick for five coins. Dry-runs without a private key.

    MrJev/awesome-jev

Frequently asked questions

Will it trade real money?

Only with a live private key; without one it dry-runs with simulated fills.

What does Jev decide each tick?

Long or short, and whether to open, close or hold.

Is it profitable?

The README does not report evaluated performance; treat it as an experiment.

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