jev-model-router (lucianfialho)

Cost-optimized OpenRouter model router using TypeSafe's Jev, with a live full-catalog scorer instead of a hardcoded model list

How it uses Jev

A cost-optimized model router for OpenRouter, using TypeSafe's Jev to classify each request and pick the cheapest model that can actually handle it.

Getting started

Or route and complete in one call:

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 jev-model-router (lucianfialho)

Browse all
jev-router project preview
Agent tooling
Cost-aware LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.
JevHarness project preview
Agent tooling
LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.
jev-agent-skill-router project preview
Typed, confidence-aware agent skill routing with TypeSafe Jev.
draftpulse project preview
Applications
Experimental: live X draft viral scorer powered by TypeSafe Jev
tsai-civ2 project preview
Games & simulations
TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.
jev-askable-arm project preview
Games & simulations
Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.
jevbetter project preview
Benchmarks & research
A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.
jevify (Mintzs) project preview
Applications
An optimized inference engine to turn LLMs into Jev-like machines: optimized for quick, lightweight, and accurate decision-making, classification, and scoring
jevframe project preview
Demos & playgrounds
Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.