jevbooks

← All projects

jev-router

prismhq/jev-router

Open-source LLM router where Jev picks the serving model.

Classification & Routing99%Runner-up: Infra / SDKs / Integrations

What it is

An OpenAI-compatible LLM router built on LiteLLM. Clients send one model id, "jev-router", and the router selects which underlying model serves each request. For developers who want automatic model selection across providers like OpenRouter.

How it uses Jev

When TYPESAFE_API_KEY is set, JevDecider picks one model from the eligible candidates in router.yaml. It receives a minimized summary of the request: recent messages' roles and truncated text, plus image/tool signals. The chosen model serves the request; failures fall back to router.yaml's fallback.

Primitives:choice

Technique worth stealing

Filter candidates by capability (vision, output length, tools) before the decision, then let Jev choose among the eligible set.

Try it

pip install "litellm[proxy]" pyyaml; set OPENROUTER_API_KEY and TYPESAFE_API_KEY; run litellm --config config.yaml --port 4000.

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricno0.24
  • Shows a System One patternno0.22
  • Handles uncertaintyyes0.80
  • Measuredno0.04
  • Runnableyes0.94
  • Worth recommendingno0.38
  • Model replicano0.04
  • Problem scopescore on a 0–2 scale1.82
  • About Jevyes0.97

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.