Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

jev-go (kyledickey)

Go SDK for Jev with typed question and answer structs, client options and structured API errors.

LibrarybetaMIT
View on GitHub ↗

Overview

jev-go by Kyle Dickey is a Go SDK for TypeSafe's Jev API. The client reads TYPESAFE_API_KEY by default and sends SystemOneRequest values with typed NoulQuestion, ChoiceQuestion and ScoreQuestion structs, each with a matching answer type. The README's example asks whether a customer is eligible for a refund given a 30-day policy described in the Noul criteria.

Options allow a custom key, HTTP client and base URL. Non-2xx responses return an APIError with status, headers and raw body. Requests are not retried, so callers wrap them if needed. CI runs gofmt, go vet and race-enabled tests, and the project is MIT licensed.

What the decision model decides

TypeQuestionAnswers
Yes / noIs the customer eligible for a refund?—

How it works

  1. Create a client
  2. Build a SystemOneRequest with typed questions
  3. Send and type-assert answers
  4. Handle APIError on failures

Strengths

  • Typed structs per question kind
  • Clear error type
  • Tests in CI

Caveats

  • No built-in retries
  • Community SDK

Getting started

`go get github.com/kyledickey/jev-go`, then `jev.NewClient()` and `client.SystemOne(ctx, req)`.

At a glance

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

Use cases and integrations

How curated lists describe it

Frequently asked questions

Does it retry requests?

No, wrap calls yourself if needed.

How are errors reported?

As *jev.APIError with status code, headers and body.

Where does the key come from?

TYPESAFE_API_KEY by default, or WithAPIKey.

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