CalibratedDecisions.

Repo · Routing & model choice

XavierJev

Local decision layer for agent control flow—typed questions from one token's probabilities, measured against labelled sets.

Open github.com ↗

From the repository

A decision layer for agent control flow — yes/no, choice and rubric questions answered from one token's probabilities, measured against labelled sets — with a Claude Code permission hook and a trainable local judge

ai-agentsclaude-codeclaude-code-pluginfine-tuningguardrailsjevllmllm-evaluationlogprobsloraollamatypescript

How builders describe it

A TypeScript decision layer for agent loops that reads yes/no, one-of-n and rubric answers off one token's probabilities from a local logprobs model, with a permission gate shipped as a Claude Code plugin.

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