Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more
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.
- Category
- Cookbooks & Demos
- Published by
- Community
- Author
- OpenByteInc
- Added
- 2026-09-22
Tagscommunitypythontradingmcppostgres
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 | bashWatch 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.
More like this
294GitHub stars
An experimental controller that has Jev choose NES inputs to play Super Mario Bros. from structured emulator telemetry instead of screenshots, logging every decision with probabilities and latency.
Cookbooks & Demos#community#python#games
Communitytypesafe-mario
181GitHub stars
A MuJoCo and Franka Panda workbench where Jev chooses the next manipulation step for pick-and-place, stacking, and obstacle-carry tasks, with rule baselines and side-by-side model comparison.
Cookbooks & Demos#community#python#robotics
Communityembodied-jev
103GitHub stars
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.
Cookbooks & Demos#community#typescript#trading
Communityjev-trade
From the community
Posts from builders shipping with Jev right now.
Inferring Jev's internals from 1,000 calls
The open System One roundup
Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more
Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格
The launch post
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x Show more
Trading bot, one decision per block
I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app
Classifying 1,500 real emails
this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Fast browser use with Stagehand
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x