jod

Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.

How it uses Jev

Zod validates data you already understand. Jev judges data you don't. jod is the seam: your state is validated locally and for free, every question goes out in one parallel Jev request, and the answers come back as domain values your code can branch on.

Getting started

ask() accepts exactly what your state schema outputs, validates it locally, and only then spends a request. An invalid state raises JodStateError and no request is made .

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

Keep exploring

Similar to jod

Browse all
zod-jev project preview
SDKs & clients
Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.
qualm project preview
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.
typesafe-sdk-dotnet project preview
SDKs & clients
Unofficial .NET port of the TypeSafe AI client SDK (typed questions & answers)
jev-hooks project preview
Demos & playgrounds
Compose typed Jev judgments as reactive semantic state in React and backend programs
pi-jev (TheoOliveira) project preview
Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev
jev-workbench project preview
Agent tooling
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.
claude-jev-plugin project preview
Agent tooling
TypeSafe Jev semantic guardrails for Claude Code
jev_projects project preview
Demos & playgrounds
list of projects that use typesafe's jev
jev-cli project preview
Applications
CLI for TypeSafe AI's Jev evaluation model — typed questions in, structured JSON answers out