jev (kataras)

Unofficial Go client for the System One API with Noul, Choice and Score types and rate limiting, by kataras.

LibrarybetaMIT

Overview

jev by kataras is an unofficial Go client for TypeSafe's System One API. You send a state (a string or JSON such as a ticket, log or program state) and named questions, and get back a typed answer and probability per question; adding questions to the same call adds no round trip. Question names are yours and come back as answer keys rather than being part of the prompt.

It requires Go 1.27 or newer and depends only on golang.org/x/time/rate. The README notes that jev-latest is a moving alias and recommends pinning, for example WithModel("jev-1.13.0"), when runs must hit the same model, and points to the official JavaScript and Python SDKs as references.

What the decision model decides

Type	Question	Answers
Yes / no	Is this ticket about billing?	—
Choice	Which team should handle this?	billing · technical
Score	How urgent is this ticket?	—

How it works

go get the module
jev.New() reads TYPESAFE_API_KEY
Call SystemOne with state and named questions
Read typed answers by your keys

Strengths

Single small dependency
Model pinning guidance
Built-in rate limiting

Caveats

Unofficial
Requires a very recent Go version

Getting started

`go get github.com/kataras/jev`, then `client, _ := jev.New()` and `client.SystemOne(ctx, jev.Request{...})`.

At a glance

Type: Library
Status: beta
Language: Go
Runtime: Library
Has code: yes
License: MIT

Use cases and integrations

Infra / SDKs / Integrations537

SDKs and API clients331

How curated lists describe it

A Go client for the TypeSafe AI's System One API and its model, Jev.
logicrw/awesome-jev-projects
A Go client for the TypeSafe AI's System One API and its model, Jev.
hellogumbo/awesome-jev

Frequently asked questions

Is it official?

No; the official clients are the JavaScript and Python SDKs.

Should I pin a model?

Yes, if runs must be reproducible, since jev-latest moves.

Which Go version?

Go 1.27 or newer.

Related projects

ai
Hack Club's lightweight LLM proxy, listed for adding a Jev forwarding endpoint behind its auth, limits and usage logging.
MCP serverproductionTypeScript
Ax
Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.
PluginproductionTypeScript
Effect
Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.
ProjectproductionTypeScript
instructor-php
PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.
ProjectproductionPHP
jev-mcp (freepik-company)
Go MCP server giving any client typed Jev decisions via OpenRouter or TypeSafe, with validated answers and no paid retries.
MCP serverproductionGo
llm-typesafe
Simon Willison's LLM plugin that adds Jev as a model for yes/no, choice and score questions from the command line.
PluginproductionPython