CalibratedDecisions.

Repo · Routing & model choice

Jev LLM router

Small Python project that asks TypeSafe Jev which OpenAI model should handle a text query, then has an independent local Ollama model review that…

Open github.com ↗

From the repository

Inspect Jev LLM routing decisions with an independent local Ollama judge

How builders describe it

Small Python project that asks TypeSafe Jev which OpenAI model should handle a text query, then has an independent local Ollama model review that routing decision—without calling the selected OpenAI model.

The decision Jev makes

Pick an agent, a model, a skill from a catalog, or a function and its arguments.

Where it fits

Deciding which agent, model, skill or function should handle a request. Jev is a natural router: the options are fixed and the confidence tells you when to fall back. All 348 routing & model choice projects →

Related projects