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
typesafe-ai-rails
A community Rails integration built on the typesafe-sdk Ruby gem that adds Rails configuration, persisted usage and cost telemetry, and persistence-backed confidence policies for Choice and Score answers.
- Category
- Repos & SDKs
- Published by
- Community
- Author
- GenieRobot
- Added
- 2026-09-22
Tagscommunityrubysdkconfidence
Highlights
- Built on the community typesafe-sdk gem and explicitly not an official TypeSafe package; the SDK stays framework-neutral while the gem adds Rails wiring.
- Each successful ask appends a typesafe_calls row with decision type, model, token counts, pricing rates, estimated cost, request ID, and latency.
- Result#act! is a fail-closed helper: without an active DecisionPolicy it raises MissingPolicyError, and a fallback of "escalate" raises LowConfidenceError.
- A Jev family rate lets jev-latest resolve to versioned names such as jev-1.13.0 without losing the cost estimate; unknown models record cost_usd = NULL.
- A telemetry database failure is non-fatal by default, and strict_logging = true makes complete accounting take priority over availability.
Quickstart
bash
bundle add typesafe-ai-rails
bin/rails generate typesafe:rails:install
bin/rails db:migrateWatch out
MIT-licensed and not an official TypeSafe package. Needs a Rails app, the community typesafe-sdk gem, and an API key in credentials; debug logging may place application state in logs.
More like this
6GitHub stars
A Ruby client for TypeSafe's System One API that returns typed Noul, Choice, and Score answers, validates obvious input mistakes before spending a request, and pools HTTP connections across threads.
Repos & SDKs#community#ruby#sdk
Communitytypesafe-sdk
50GitHub stars
A Ruby client for Noul, Choice, and Score decision models, reaching OpenRouter by default or TypeSafe's native API, with no runtime dependencies beyond the standard library.
Repos & SDKs#community#ruby#sdk
Communityruby_decision_model
18GitHub stars
A RubyLLM 2 provider that adds Jev through structured output: build Noul, Choice, and Score questions with a schema builder, pass them to chat.with_schema, and read typed answers from response.parsed.
Repos & SDKs#community#ruby#sdk
Communityruby_llm-typesafe
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