Skip to content
JevDirectory.org
CommunityTools & Integrations16 starsVerified 2026-09-22

Jev Agent Skill Router

An optional routing layer for Hermes Agent, shipped as a Python CLI and library, that sends a request and a public skill catalogue to Jev and returns route, no_skill, or review plus confidence and candidate distributions.

Open github.comGodsBoy/jev-agent-skill-router
Category
Tools & Integrations
Published by
Community
Author
GodsBoy
Added
2026-09-22
Tagscommunitypythonroutingagentscli

Highlights

  • Reported 68 of 72 synthetic requests routed correctly (94.4%) versus 51 of 72 (70.8%) for a lexical baseline, with zero wrong routes.
  • Sends up to three parallel Jev Choice batches and a final request; two candidates survive each batch and the final distribution is conditional on the shortlist.
  • Returns a three-valued specialist-needed Noul, final Choice confidence and winner probability, per-call candidates, latency, and API token usage.
  • The public benchmark uses 24 synthetic skills and 72 synthetic requests, and offline tests also exercise a catalogue of 1,000 skills.
  • A full live run sends roughly 288 API requests, bounded to four concurrent calls within a case, with no automatic retries and a 600-call ceiling.

Quickstart

bash
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -e '.[dev]'
export TYPESAFE_API_KEY=YOUR_API_KEY
jev-router route --model jev-1.13.0 --catalogue examples/catalogue.json

Watch out

MIT-licensed and not affiliated with TypeSafe; needs Python 3.11+ and TYPESAFE_API_KEY, results are exploratory reused-data numbers with no repeated-run analysis, and typed output guarantees shape rather than correctness.

More like this

typesafe-computer-use
799GitHub stars
A macOS computer-use loop that OCRs the screen, asks Jev for the next action with typed Choices, and clicks, at about $0.0002 per decision without sending screenshots to a frontier model.
Tools & Integrations#community#python#agents
Communitytypesafe-computer-use
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
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