Skip to content
JevDirectory.org
CommunityTools & Integrations8 starsVerified 2026-09-22

jev-router

An OpenAI-compatible LiteLLM proxy where clients send one model id and Jev picks which configured model serves each request, with capability filtering and a cheapest-eligible fallback.

Open github.comprismhq/jev-router
Category
Tools & Integrations
Published by
Community
Author
prismhq
Added
2026-09-22
Tagscommunitypythonroutinggatewayopenrouter

Highlights

  • Clients point any OpenAI-compatible client at the proxy with model jev-router; the response model field reports which model served it.
  • eligible() filters candidates in router.yaml on vision, output length, and tool support before any decision is made.
  • Without a TYPESAFE_API_KEY a RulesDecider picks the cheapest eligible model, and any failure falls back to router.yaml's fallback.
  • Transport is LiteLLM, so it can route across OpenRouter or any provider LiteLLM supports; you bring your own keys.
  • Two files: config.yaml holds the LiteLLM pool and hook registration, router.yaml the candidate descriptions, capability flags, and prices.

Quickstart

bash
pip install "litellm[proxy]" pyyaml

export OPENROUTER_API_KEY=YOUR_API_KEY
export TYPESAFE_API_KEY=YOUR_API_KEY   # optional: enables Jev routing

litellm --config config.yaml --port 4000

Watch out

MIT-licensed and experimental with changing APIs and config; needs LiteLLM plus an OpenRouter key, and Jev routing sends a minimized request summary to TypeSafe.

More like this

Hermes Jev Skills
425GitHub stars
A Python toolkit that installs nine plain SKILL.md files for Hermes, Claude Code, and Codex, letting Jev route models, filter retrieved passages, select skills, and choose bounded computer or browser actions.
Tools & Integrations#community#python#agents
Communityhermes-jev-skills
jev-gateway
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
Grok Bot Jev Router
75GitHub stars
A reference router and skill that put Jev in front of Grok Bot so each request is classified before expensive research, browser, retry, or subagent work, returning actions such as reuse_cache or ask_human.
Tools & Integrations#community#python#routing
Communitygrok-bot-jev
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Classifying rows in DuckDB

A playable 16-judgment demo

AI multiple choice, not essay writing

Screening agent actions with Jev

😎Nick 常胜
😎Nick 常胜
@isNickMa
·

Tested TypeSafe’s Jev (no-text, probability-only model) as an AI agent safety monitor. Checking each action first worked well caught most attacks with almost no false blocks, and much faster than Gemini.

Image
Image
Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read 1 reply

Cua's small System One models

A 706K-parameter form filler

Arsh - 16 y/o builder
Arsh - 16 y/o builder
@be_arsh
·

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
Read 1 reply