ailerix

Where it calls Jev

const response = await fetch("https://api.typesafe.ai/v1/systemone", {

src/lib/system-one.ts:428

The link points at the commit we read, so the line number still holds.

What it asks Jev

These question sets are lifted from this project's source exactly as written.

import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    hallucination_sensitive: { type: 'boolean', instructions: 'Would a confident falsehood be expensive here?' },
  },
});

Other projects in this category

• simple-jev ▶ — Turn any open model into a classifier/jev endpoint
• typesafe-ai-benchmark ▶ — This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.
• Nemotron_Jev ▶ — Nemotron Diffusion Decision Lab
• jcm-router ▶ — Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.
• tiershift ▶ — Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.
• jev-workbench ▶ — Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.
• jev-model-router ▶ — Jev (TypeSafe) model router on the Vercel AI Gateway
• jevcache ▶ — Skip expensive LLM calls when TypeSafe Jev says same intent. OpenAI-compatible local cache proxy — npx @kushalicious/jevcache