JjomatsuSDKs & clients

zod-jev

Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.

Explore repository

Zod validates the shape. Jev validates the meaning.

How it uses Jev

Zod validates the shape. Jev validates the meaning.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to zod-jev

Browse all
jod project preview

jod

SDKs & clients
Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.
MMade bymateonunez3
hono-jev-router project preview

hono-jev-router

Agent tooling
Route HTTP requests by meaning. A semantic router for Hono powered by Jev.
YMade byyusukebe46
system-one-playground project preview

system-one-playground

SDKs & clients
Readable scripting, semantic code checks, a Go System One client, and Studio.
DMade byDonaldMurillo1
qualm project preview

qualm

SDKs & clients
Typed decisions from a System One model. An uncertain answer is a different type from a confident one — and the compiler makes you handle it.
QMade byqddegtya1
n8n-nodes-jev-classification project preview

n8n-nodes-jev-classification

Integrations
n8n community node for Jev by TypeSafe AI: classify, score and check text with calibrated probabilities. Parallel requests and multi-item batching.
KMade bykhmuhtadin2
shapeshift project preview

shapeshift

Demos & playgrounds
An input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, works offline.
AMade byanishfn491
claude-jev-plugin project preview

claude-jev-plugin

Agent tooling
TypeSafe Jev semantic guardrails for Claude Code
DMade bydr-dimitru2
pi-typesafe-jev project preview

pi-typesafe-jev

Agent tooling
A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.
LMade bylegacybridge-tech3
tenbin project preview

tenbin

Benchmarks & research
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code
SMade bysimota3