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

typesafeai-dotnet-sdk

Community .NET SDK for System One with typed noul, choice and score questions, verbatim confidence and forward-compatible raw fields.

LibrarybetaMIT
View on GitHub ↗

Overview

saibimajdi's TypeSafeAI .NET SDK is a community, MIT-licensed client for the System One HTTP API, published on NuGet as TypeSafeAI.Sdk with CI. You declare questions by kind, send them over text or JSON state in one round trip, and get structured answers: yes/no probabilities, a chosen option or a rubric position.

Its design principles are explicit: questions in one request are evaluated in parallel so speculative fan-out is cheap; confidence is surfaced verbatim and never recomputed; and nothing from the raw API is lost, since unmodeled fields, unknown answer kinds and new question kinds survive through RawJson, RawQuestion and UnknownAnswer. It clearly states it is not affiliated with TypeSafe. Support guidance in the repository explains which issues belong with the SDK and which with TypeSafe, such as accounts, billing or uptime.

What the decision model decides

TypeQuestionAnswers
Yes / noYes/no question about the stateyes · no
ChoiceOne option out of a set you define—
ScorePosition on a rubric you define—

How it works

  1. Install TypeSafeAI.Sdk.
  2. Declare typed questions.
  3. Evaluate them in one request.
  4. Read answers; access raw fields for anything unmodeled.

Strengths

  • Forward-compatible with new API fields and kinds.
  • Confidence reported verbatim.
  • Supports cheap speculative fan-out.

Caveats

  • Community SDK; requires a key.

Getting started

dotnet add package TypeSafeAI.Sdk

At a glance

Type
Library
Status
beta
Language
C#
Runtime
.NET library
Has code
yes
Has tests
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • .NET ecosystem: community .NET SDK for the TypeSafe AI System One API with strongly-typed Noul, Choice, and Score questions and structured answers.

    yibie/awesome-jev

  • Community client for typed questions and confidence-scored answers.

    AnotiaWang/awesome-decision-models

  • Community .NET SDK for TypeSafe AI and Jev, providing asynchronous typed evaluation for Choice, Score, and Noul primitives.

    logicrw/awesome-jev-projects

  • Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and…

    wh000wh000/awesome-jev-live

  • Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and score questions with structured, confidence-scored answers. Not affiliated with TypeSafe AI.

    hellogumbo/awesome-jev

  • .NET SDK.

    MrJev/awesome-jev

Frequently asked questions

Does it change confidence values?

No, it surfaces them exactly as the API reports.

What if the API adds a new answer kind?

It is preserved as UnknownAnswer with raw JSON.

Is it affiliated with TypeSafe?

No.

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