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

TypeSafeAI

NativeAOT-ready .NET SDK for System One with an AutoSDK-generated transport and handwritten typed API, DI and MEAI integrations.

Librarybeta
View on GitHub ↗

Overview

tryAGI's TypeSafeAI is a .NET SDK whose raw client is regenerated from TypeSafe's official OpenAPI definition using AutoSDK, while typed questions, batching, routing, dependency injection and Microsoft.Extensions.AI integrations are handwritten extensions. It targets modern .NET practices including nullability, trimming, NativeAOT awareness and source-generated serialization.

It aims for ecosystem parity, including the official JavaScript and Python examples and features from other .NET SDKs. Examples stay in sync between the README, an MkDocs site and integration tests. It is one of more than 200 .NET SDKs maintained by tryAGI with continuous audits of regeneration, releases and AOT compatibility. Published on NuGet with CI. Request batching, routing helpers and integration tests are maintained alongside the generated client, and examples are kept in sync across the README and docs site.

What the decision model decides

TypeQuestionAnswers
OtherTyped Choice, Score and Noul questions via the System One API—

How it works

  1. Install tryAGI.TypeSafeAI from NuGet.
  2. Use the typed API or DI integration.
  3. Send state with typed questions.
  4. Read typed answers.

Strengths

  • Generated transport stays in sync with the OpenAPI spec.
  • NativeAOT and trimming aware.
  • Microsoft.Extensions.AI integration.

Caveats

  • Large generated surface.
  • Community SDK.

Getting started

dotnet add package tryAGI.TypeSafeAI

At a glance

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

Use cases and integrations

How curated lists describe it

  • First-class, NativeAOT-ready .NET SDK for TypeSafe AI System One, generated with AutoSDK.

    hellogumbo/awesome-jev

Frequently asked questions

How is it built?

A transport generated from TypeSafe's OpenAPI spec plus handwritten typed extensions.

Is it AOT-friendly?

Yes, it is designed for trimming and NativeAOT.

Does it integrate with Microsoft.Extensions.AI?

Yes, MEAI integrations are included.

Related projects

  • 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
  • req\_llm

    Elixir library for unified LLM calls across providers, with an evaluate interface that calls Jev via TypeSafe or OpenRouter.

    ProjectproductionElixir
  • synkora-ai

    Self-hosted multi-tenant AI agent platform listed as including optional TypeSafe client tools for classification, scoring and yes/no.

    LibraryproductionPython
  • TanStack AI

    Provider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().

    ServiceproductionTypeScript