CalibratedDecisions.

Repo · Routing & model choice

model-router (muhx)

Claude Code mod that picks the model and reasoning effort for each task with Jev — subagent model at spawn, main-loop effort per turn, and (on by…

Open github.com ↗

From the repository

Picks the Claude model and reasoning effort for each task with Jev, TypeSafe's System One decision model

How builders describe it

Claude Code mod that picks the model and reasoning effort for each task with Jev — subagent model at spawn, main-loop effort per turn, and (on by default in this fork) main-loop model — using TypeSafe's /v1/systemone (jev-latest) or the Vercel AI Gateway, with a risky-task noul, confidence-aware…

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