Ask Jev anything. Give it a try at askjev.ai It won't answer. It will judge. Let's see if we can get to 1 million questions. @typesafeai 🤝 @convex work great together. @hmartenjoyer @CompleteSkeptic @justKDeng @mikeysee
Jev for Home Assistant
A Home Assistant integration that turns Jev questions about entity state into sensors and automation actions, with an Assist conversation agent and a daily token budget.
- Category
- Repos & SDKs
- Published by
- Community
- Author
- AboveColin
- Added
- 2026-09-22
Tagscommunitypythonhome-assistantroutingagents
Highlights
- Questions become sensors: a probability, one of your options with its distribution, or a number that can land between levels.
- Four actions answer inside an automation and return a response variable: jev.noul, jev.choice, jev.score, and jev.ask.
- Reports calls, input tokens, and estimated cost per day, and halts evaluation once the daily token budget is spent.
- A conversation agent routes spoken Assist commands through the same model and counts them against the same budget.
- Ships 15 worked examples, four pairing Jev with an LLM, and 204 tests that run against a real Home Assistant.
Watch out
MIT-licensed, but not affiliated with TypeSafe. Requires Home Assistant 2026.9 or newer and a TypeSafe API key; it installs as a custom HACS repository because it is not in the HACS default list yet.
More like this
14.3kGitHub stars
Open multilingual System 1 decision models with published checkpoints for choice, score and noul questions, plus a router that dispatches each request to the right checkpoint in one forward pass.
Repos & SDKs#community#python#open-models
Communitylaya
137GitHub stars
A Juspay TypeScript SDK that treats Jev as a third inference type beside generate and stream: providers declare which kinds they serve, and tryDecide returns typed boolean, choice, or score answers, null when no decision provider is set.
Repos & SDKs#community#typescript#sdk
Communityneurolink
61GitHub stars
A DSPy fork whose @typesafeify decorator routes decision-shaped signature fields to Jev, so bool, Literal, and scored outputs come back typed while freeform fields still use the LM.
Repos & SDKs#community#python#sdk
Communitydspy-typesafeify
From the community
Posts from builders shipping with Jev right now.
A million judged questions
Inferring Jev's internals from 1,000 calls
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
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