UussyverseAgent tooling

hermes-jev-router

Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.

Explore repository

How it uses Jev

Hermes Jev Router (experimental)

Getting started

Official POST https://api.typesafe.ai/v1/systemone , Bearer authentication, model jev-latest , structured state and a named choice question with criteria. Validate exact answer IDs/types, probabilities (finite, [0,1], sum to one), winning label, confidence and reported model. Fail closed on malformed replies. Moving m…

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

Keep exploring

Similar to hermes-jev-router

Browse all
hermes-jev-plugin project preview

hermes-jev-plugin

Agent tooling
TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate
AMade byajensenwaud5
ask-jev-skill project preview

ask-jev-skill

Agent tooling
Skill for Hermes, and other agents, to ask typesafe's jev
SMade byshantanugoel39
agent-handoff-gate project preview

agent-handoff-gate

Agent tooling
Experimental protocol for evidence-aware agent handoffs, with Jev-assisted review before results reach the lead agent.
ZMade byzsoXi0
hermes-jev-skills project preview

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
lejudge-jev-jepa project preview

lejudge-jev-jepa

Applications
Natural-language constraints for JEPA world-model planning, judged by a decision model instead of an LLM.
AMade byAbdelStark9
jev-korean-benchmark project preview

jev-korean-benchmark

Benchmarks & research
Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence
MMade bymahlernim6
jev-capability-atlas project preview

jev-capability-atlas

Benchmarks & research
Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文為主的雙語 repo。
ZMade byZaious26
JEV-Star project preview

JEV-Star

Benchmarks & research
An experimental StarCraft II controller pairing Jev action selection with optional LLM planning. Its README reports separate Jev-only and planner-assisted results; those runs do not isolate a general performance advantage for Jev.
SMade bysc2musa0
jselect project preview

jselect

Applications
Selects source-linked evidence within a token budget using Jev Noul relevance judgments and local diversity-aware selection.
KMade bykeltokhy3