Model router built with Jev
X demo by Ephraim Duncan where Jev decides which model should serve a request before it is forwarded.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This X post shows a model router built with Jev: before a request is forwarded, Jev decides which model should handle it. The list compares it to similar routing demos.
Only the list summaries were available, so the candidate models, routing criteria and any measurements are unknown. It is a small example of using a typed choice to pick a model per request for cost or quality reasons.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which model should serve this request?(inferred) | — |
How it works
- Receive a request.
- Ask Jev to choose a target model.
- Forward the request to that model.
Strengths
- Illustrates per-request model selection with a single typed decision.
Caveats
- Social post only; no code or results in the sources.
At a glance
- Type
- Discussion
- Status
- discussion
Use cases and integrations
How curated lists describe it
X: 948-like demo where Jev decides which model should serve a request before it is forwarded.
yibie/awesome-jevEphraim Duncan's demo where Jev decides which model should serve a request.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide?
Which model a request should be sent to.
Is code available?
Not according to the listing.
Who made it?
Ephraim Duncan, posted on X.
Related projects
Korean course code for attaching Jev to Claude Code, Codex and OpenClaw: skills, hooks, routers and open-model comparisons.
ProjectproductionJavaScriptCompanion code for the ZazenCodes course on decision models: primitives notebook, use-case examples and a Pi model-router build.
ProjectproductionPythonFree 12-notebook course building 13 agent tools with Jev as the fast decider and an LLM as the slow writer, for under $0.20.
ProjectproductionPythonJanus (formerly calibre): measures on your data the confidence threshold at which a small model like Jev should defer to a larger one.
ProjectbetaPythonBeginner manual, video script and three small examples for building an agent harness with Jev via langchain-typesafe.
ProjectprototypePythonLangChain notebook of practical Jev examples: ticket triage, model routing, reply guardrails, tool selection and finance-inbox fraud checks.
ProjectprototypePython