typesafe-skill-router

TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.

Explore repository

How it uses Jev

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 :

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Language: Python 100%
License: MIT
Last activity: Sep 2026
Added: 2026-09-17
Stars at snapshot: 13
Status: Community listing

ai-agentshermes-agenthermes-pluginjevllmllm-agents

Is this your project?

Add the badge to your README to link back here.

[![Listed in Jev Library](https://jevlibrary.dev/api/badge/decrux9812-typesafe-skill-router)](https://jevlibrary.dev/projects/decrux9812-typesafe-skill-router)

Something wrong, or rather not be listed? Tell us.

Keep exploring

Similar to typesafe-skill-router

Browse all

hermes-jev

Agent tooling

Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.

KMade bykeeltrace21

ask-jev-skill

Agent tooling

Skill for Hermes, and other agents, to ask typesafe's jev

SMade byshantanugoel39

jev-agent-skill-router

Agent tooling

Typed, confidence-aware agent skill routing with TypeSafe Jev.

GMade byGodsBoy17

jev-benchmark (themsquared)

Benchmarks & research

Reproducible benchmark for TypeSafe AI's Jev on agent tool-call risk classification: accuracy, latency, and whether the confidence score is worth routing on.

TMade bythemsquared1

hermes-jev-skills

Browser & computer use

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

KMade bykerpopule726

jev-mcp-server

Benchmarks & research

MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.

WMade bywangkuangkuang2

langchain-loadout

Integrations

Per-turn skill selection for LangChain and deepagents agents: a fast judge picks the few skills a turn needs, so a catalog of hundreds stays out of the prompt.

DMade bydeyna2563

jeval

Benchmarks & research

Measures what your Jev classifier's confidence is really worth, and sets the human hand-off line from what a mistake costs.

RMade byrlaope16

jev-rerank

Applications

Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.

HMade byhev11