Skip to content

typesafe-sdk-go (Tangerg)

Dependency-free Go SDK for TypeSafe: typed questions in, probability distributions out, with isolated parallel evaluation.

LibrarybetaMIT

Overview

Tangerg's typesafe-sdk-go is an MIT-licensed Go SDK for the TypeSafe API with no third-party dependencies, requiring Go 1.25+. NewClient reads TYPESAFE_API_KEY, and SystemOne takes a request with state and NoulQuestion, ChoiceQuestion or ScoreQuestion values; accessors such as Answers.Choice return the label and confidence.

The README stresses that questions in one call are evaluated in parallel and in isolation against the same state, so each should be atomic and combined in your own code. A runnable demo is included. Accessors report a clear error when an answer is absent or of a different kind, and the client refuses invalid states such as JSON null, numbers and booleans before sending.

What the decision model decides

TypeQuestionAnswers
ChoiceWhat is this ticket about?billing · technical · other

How it works

  1. Create a client.
  2. Send state with typed questions.
  3. Read answers with typed accessors.
  4. Combine answers in your code.

Strengths

  • No dependencies.
  • Clear guidance on atomic, isolated questions.
  • Runnable demo.

Caveats

  • Community SDK; requires a key.

Getting started

go get github.com/Tangerg/typesafe-sdk-go@latest

At a glance

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

Use cases and integrations

How curated lists describe it

Frequently asked questions

Do questions see each other's answers?

No, each is evaluated in isolation against the same state.

What Go version?

Go 1.25 or newer.

Is there an example?

Yes, run go run ./examples/demo with a key.

Related projects

  • Hack Club's lightweight LLM proxy, listed for adding a Jev forwarding endpoint behind its auth, limits and usage logging.

    MCP serverproductionTypeScript
  • Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript
  • PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.

    ProjectproductionPHP
  • Go MCP server giving any client typed Jev decisions via OpenRouter or TypeSafe, with validated answers and no paid retries.

    MCP serverproductionGo
  • Simon Willison's LLM plugin that adds Jev as a model for yes/no, choice and score questions from the command line.

    PluginproductionPython