Skip to content
JevDirectory.org
CommunityTools & Integrations4 starsVerified 2026-09-22

Jev Auto Router

An experimental Codex CLI router where a local Responses proxy asks Jev one Choice per model call to select a host-available model and reasoning effort, while application-owned acceptance decides whether the task passed.

Category
Tools & Integrations
Published by
Community
Author
miniLV
Added
2026-09-22
Tagscommunitytypescriptcodexroutinggateway

Highlights

  • Jev makes one Choice over host-available (model, reasoning effort) pairs, and the proxy adds no task-type table or second router.
  • Defaults include baseline gpt-5.6-terra/medium, a 0.55 confidence floor, a 2000 ms deadline, and pinned Jev 1.13.0.
  • Route labels return in x-jev-route headers, and GET /decisions lists call and task records.
  • Only compact routing state goes to Jev; raw prompts and tool outputs are not written to routing logs by default.
  • Task acceptance is application-owned at fixed tiers, with at most two correction rounds before Root takes over.

Quickstart

bash
npm ci
npm run build
JEV_API_KEY="YOUR_API_KEY" npm start
curl -s localhost:8787/health

Watch out

Apache-2.0-licensed; it is a prototype and the README warns cross-model switching in a real Codex tool loop is not yet end-to-end verified, so it needs Node.js 22+, a logged-in Codex CLI, and a Jev API key.

More like this

140GitHub stars
A local gateway for coding agents that asks Jev which tool to call each turn and steers the LLM when Jev is confident, while every other request goes to your usual provider untouched.
Tools & Integrations#community#typescript#gateway
Communityjev-gateway
4GitHub stars
A local proxy between Claude Code and the Anthropic API that picks the model and effort level per message with Jev, routing subagents whenever cheap but gating main-chat switches on prompt-cache arithmetic.
Tools & Integrations#community#typescript#routing
Communityjcm-router
1GitHub stars
An experimental local proxy for coding agents that sends jevonian/auto turns to Jev to pick a model and thinking level after deterministic compatibility and quota filters, while explicit routes skip Jev.
Tools & Integrations#community#typescript#routing
Communityjevonian
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A 706K-parameter form filler

cua open sourced a 706k param model that fills a whole form in one 50ms pass the llm agent doing the same form took 23 turns and 39.6 seconds the specialists are going to eat the generalists from the bottom

Cua
Cua
@trycua

1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua

Image
Reply

Navigating Neo4j with Jev

Jev 这个 waitlist 还是很给力的,昨天申请,今天就能用上。 给已经拿到 API、但还不知道怎么玩的人整理了一份 Awesome Jev,目前我能确认到的 Jev 项目基本都在这里: 1. jev-ultrafast Browser Use 做的高速浏览器 Agent。Jev Show more

Image
思维怪怪
思维怪怪
@0xLogicrw

前 OpenAI 研究员 Diogo Almeida 创办的 TypeSafe AI 推出新模型 Jev。它有点像一个能读懂自然语言的超级分类器,不生成文本,只返回选项、分数和概率,专门给软件做判断。 普通大模型需要一个 token 一个 token 往外生成,Jev 则可以并行给出多个结果。TypeSafe 还用新的 RLCD

Reply

Reranking 33,047 catalog entries

拿 Jev 做搜索重排,我先泼一盆冷水:单独用,它没打赢向量检索 TypeSafe 的 Jev 这阵子很火,一堆项目拿它做重排。我们在 Agent Skills Hub 的 33,047 条目录上认真测了一次,164 条中英文真实查询,9,831 对分级标注,整套只花了 2.6 美元 三个结论 01|单独重排,约等于没赢 Jev 重排 bge-m3 Show more

Jason Zhu
Jason Zhu
@GoSailGlobal

有美团、阿里的老哥嘛? 试试加一路召回、重排(离线、近实时实现),我觉得有奇效 他在文本理解上 跟之前机器学习、llm很不一样 还能自动打标签做特征

Reply

Six uses that stuck after 60 days

Security decisions that fit Jev

This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more

TypeSafe AI
TypeSafe AI
@typesafeai

we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)

Reply

A million judged questions