typesafe-sdk-dotnet
Community .NET port of the official JavaScript TypeSafe SDK with aligned configuration, retries and typed questions.
Overview
TypeSafe.AI.Sdk is a community .NET client that ports the official @typesafe-ai/sdk JavaScript SDK. It targets net10.0 and netstandard2.0 and aims to match the JavaScript SDK's behavior and TypeSafe's docs. Choice, Score and Noul questions are built with Question helpers, and independent questions are batched into one SystemOneAsync call.
Configuration follows the JavaScript precedence: explicit options, then environment variables, then defaults (base URL, default model jev-latest, log level, a 10 second per-attempt timeout and two retries with backoff and jitter). Retryable statuses include 408, 429 and 5xx. It is published on NuGet with CI and a documentation site. A documentation site accompanies the package, and the API key can also be passed directly to the constructor.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | What is this ticket about? | billing · technical · other |
How it works
- dotnet add package TypeSafe.AI.Sdk.
- Set TYPESAFE_API_KEY.
- Call SystemOneAsync with state and questions.
- Read typed answers.
Strengths
- Mirrors the official JavaScript SDK.
- Clear retry and timeout defaults.
- Docs site and CI.
Caveats
- Unofficial port.
- Requires the .NET 10 SDK to build.
Getting started
dotnet add package TypeSafe.AI.SdkAt 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
Unofficial .NET port of the TypeSafe AI client SDK (typed questions & answers).
hellogumbo/awesome-jev
Frequently asked questions
What is it ported from?
The official JavaScript SDK, @typesafe-ai/sdk.
What are the retry defaults?
Two retries with 500 to 5000 ms backoff and 25 percent jitter.
Which frameworks are targeted?
net10.0 and netstandard2.0.
Related projects
Hack Club's lightweight LLM proxy, listed for adding a Jev forwarding endpoint behind its auth, limits and usage logging.
MCP serverproductionTypeScriptAx, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.
PluginproductionTypeScriptEffect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.
ProjectproductionTypeScriptPHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.
ProjectproductionPHPGo MCP server giving any client typed Jev decisions via OpenRouter or TypeSafe, with validated answers and no paid retries.
MCP serverproductionGoSimon Willison's LLM plugin that adds Jev as a model for yes/no, choice and score questions from the command line.
PluginproductionPython