User repository on GitHub
Live Jev trader on Hyperliquid
- Forks
- 43
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Cookbooks
Jev Trade — aowang-ai
Live Hyperliquid desk across five isolated wallets where each tick packages the book, tape, and position as state and Jev answers Choice questions for long/short, open/close/hold, and leverage; hold sends no order. A missing private key means a dry run.
- Stars
- 214
- Language
- TypeScript
- Reading time
- 3 min
- Published by
- Community
- Author
- aowang-ai
- Last verified
- Sep 2026
About this project
I built a trading bot with Jev. Jev reads the Hyperliquid book every tick and answers buy, sell, or hold. The bot sends the order. Five coins, five wallets, real fills. Jev makes the call. Hold is one of its answers, so a tick can end with no order. Position, balance, and PnL come from Hyperliquid. Based on jev-trader by Jarrod Watts (MIT). Venue is Hyperliquid, not Monad / Kuru. Five isolated sleeves: BTC, ETH, SOL, DOGE, BNB. Each has its own wallet and its own Jev call.
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Finance & Fintech
Highlights
- Five isolated sleeves (BTC, ETH, SOL, DOGE, BNB), each with its own wallet and its own Jev call.
- Jev answers long/short, open/close/hold, and leverage; hold sends no order and pulls resting quotes.
- Entries are post-only Alo quotes one tick inside the touch; exits are Ioc orders that cross the touch.
- No PRIVATE_KEY means a dry run: real book, real decisions, simulated fills, with MODEL=mock by default.
- The dashboard is Next on port 3001, and the Bun bot streams ticks over SSE on port 3000.
Quickstart
bash
cp .env.example .env
bun install
bun run start
# dashboard, second terminal:
bun run dev:webWatch out
README states MIT while GitHub metadata reports NOASSERTION. Needs Bun 1.2+, and a configured PRIVATE_KEY sends real orders on testnet or mainnet, so start with the dry run.
Questions about this entry
Short answers drawn from the linked project or page.
Only if you supply keys. With no PRIVATE_KEY it is a dry run: real book, real decisions, simulated fills. HL_TESTNET defaults to true, and setting it to false is mainnet, so leave it alone until you mean it. DRY_RUN=true simulates every sleeve, and a sleeve with no key still dry-runs on its own.
Direction and action: long or short, then open, close, or hold, with leverage as part of the Choice set. Hold is a real answer, so a tick can end with no order, and any resting quote Jev no longer wants gets pulled. Entries are post-only ALO one tick inside the touch; exits are IOC orders that cross it.
It is based on jarrodwatts/jev-trader under MIT and credits it, but it is not a copy. The venue is Hyperliquid rather than Monad or Kuru, and the shape is a desk of five isolated sleeves (BTC, ETH, SOL, DOGE, BNB), each with its own wallet and its own Jev call.
Yes. MODEL=mock is the default and is a momentum stand-in that needs no key, so a dry run still shows the whole loop against real book data with simulated fills. Setting MODEL=jev with JEV_PROVIDER=typesafe (the default) or gateway is what calls the real model; keys and evaluation stay on the Bun process, with the dashboard on a separate port.
You need Bun 1.2 or newer. Copy .env.example to .env, `bun install`, then `bun run start`. With no PRIVATE_KEY it is a dry run with a real book, real decisions and simulated fills, and the default MODEL=mock is a momentum stand-in needing no API key.
Set MODEL=jev and pick a provider: JEV_PROVIDER=typesafe with TYPESAFE_API_KEY, or JEV_PROVIDER=gateway with AI_GATEWAY_API_KEY. For live orders keep HL_TESTNET=true, set PRIVATE_KEY for BTC and copy .wallets.example.json to .wallets.json. HL_TESTNET=false is mainnet.
An entry is a post-only Alo quote one tick inside the touch so it sits on the maker side, an exit is an Ioc that crosses the touch, and hold sends no order while pulling any resting quote Jev no longer wants. Each of the five sleeves (BTC, ETH, SOL, DOGE, BNB) has its own wallet and Jev call.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: A trading loop with Jev and GPT-6 Astra
X: News sentiment in a trading terminal
X: A Jev trading bot on Telegram
X: A Jev and Grok copy-trading bot
This post couldn't be loaded here — read it on X.https://x.com/Mnilax/status/2102760642872508510Other listings of this project
Forks and copies of this project in the directory. This entry is the canonical one.
A simulated high-frequency crypto trading loop that makes its buy and sell calls with Jev: recent BTC and ETH prices and volumes go in, a typed confidence-aware decision comes out, and a cost-aware execution simulator turns it into P&L. Not live trading.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
waxmell114514/jev-tradePython
waxmell114514/jev-tradePythonMore Jev resources like this
An intraday trading bot for the Nifty 50: Jev ranks names every 15 seconds through the Vercel AI Gateway, and code sizes positions, stops, and flatten times.
Jev Cookbooks#community#typescript#trading
Community
arimanyus/warrendufferTypeScript
arimanyus/warrendufferTypeScriptA video demo of a bot that asks Jev to decide buy or sell from a live price feed, then places real orders on Kuru's on-chain order book on Monad every 300ms block.
Jev CookbooksVideo#community#x#video
Community
A multiplayer demo workflow builder for Jev built with Liveblocks: wire Jev and LLM steps together, call the workflow through a REST API, and preview test runs with shared state and cursors.
Jev Cookbooks#community#typescript#demo
A browser Snake game where code computes the legal moves, food distance, and reachable space and Jev picks one move per tick with a single Choice question; a late answer leaves the snake going straight.
Jev Cookbooks#community#typescript#games
Community
sorrycc/typesafe-snakeTypeScript
sorrycc/typesafe-snakeTypeScriptTwo WebAssembly builds of the Chocolate Doom 3.1.1 engine play the same Freedoom map from the same initial state, with a Jev Choice decision picking each tactical macro and a local controller turning it into inputs.
Jev Cookbooks#community#typescript#games
Community
lukaske/jev-doom-agentTypeScript
lukaske/jev-doom-agentTypeScriptA small Kalshi trading bot across 15-minute and 1-hour BTC, ETH, and SOL markets, built with Effect and Cursor and powered by Jev.
Jev CookbooksPost#community#x#video
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.