Skip to content

TypeSafe Skill Router

Opt-in Hermes plugin that routes each turn to one skill: a wide Jev Choice plus request checks gate a narrow fits round, injecting a single ignorable hint line.

Stars
14
Language
Python
License
MIT
Published by
Community
Author
DECRUX9812
Last verified
Oct 2026

About this project

A Hermes Agent plugin that names the one skill worth loading — before the model call. Hermes shows the model a one-line description of every installed skill. With a few hundred of them, the model reads past the one that would have done the job. This plugin sends the request to TypeSafe (model jev-latest) first and, when a skill genuinely fits, appends a single line to the user message:

Quoted from the project's README. Read the full README.

Highlights

  • Wide Choice over 60-character index lines plus three request checks; gate is the mean with the prose check inverted.
  • Narrow Choice over top shortlist plus per-candidate fits question; wrong names cost more than silence.
  • Chunking handles large rosters with none-of-these cutoff and bit-stable ranking; slash and multimodal turns skip routing.
  • One log line per turn pairs with session history so real turns can be scored before tuning thresholds.

Watch out

Thresholds tuned on English sit about 0.14 lower on fits in Spanish, and vendor roster effects do not transfer to your skill set. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

LangChain deepagents middleware that replaces SkillsMiddleware with per-turn judging, loading only the SKILL.md files a turn needs so large catalogs stay out of the prompt.
Jev Agents & MCP#community#jevbest#catalog-import
51GitHub stars
Local LinkedIn recruiting workspace on Browser Use's Jev Ultrafast: Jev screens titles, drives navigation, and assesses profile excerpts against your brief while a live browser stays visible; matches and evidence export as JSON.
Jev Agents & MCP#community#jevbest#catalog-import
33GitHub stars
Codex Skill plus stdlib-only Python CLI that recommends which installed skill to read next for a task, allowing no-skill or uncertain answers and never executing candidates.
Jev Agents & MCP#community#jevbest#catalog-import
72GitHub stars
MCP server over stdio that gives coding agents fourteen Jev judgment tools, turning evidence plus an enumerable question into auto, review, or escalate actions from calibrated probabilities.
Jev Agents & MCP#community#jevbest#catalog-import
Research runtime that pages a large logical tool and context space through a small bounded Jev decision surface with explicit approvals.
Jev Agents & MCP#community#jevbest#catalog-import
25GitHub stars
Agent-oriented playbook for using Jev as a cheap, fast decision layer that triages, classifies, scores, and gates work before expensive browser, research, retry, or subagent steps.
Jev Agents & MCP#community#awesomejev#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai