Repo · Routing & model choice

todo-jev

Python CLI experiment that classifies a user request and recommends a three-tier handling path (local rule, Jev/structured skill, or foundation…

Open github.com ↗

From the repository

⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One)

How builders describe it

⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One).

Python CLI experiment that classifies a user request and recommends a three-tier handling path (local rule, Jev/structured skill, or foundation model) with skill profiles and basic environment preflight.

Python CLI that classifies a request into one of three tiers — local rule, structured decision or skill, or foundation model — using TypeSafe Jev, 20 bundled skill profiles with exclusion conditions, and local environment checks.

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