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

typesafe-rust-sdk

Unofficial Rust client for System One following the official Python SDK, with async and blocking clients for apps and game loops.

Librarybeta
View on GitHub ↗

Overview

typesafe-rust-sdk is an unofficial Rust client for System One whose behavior follows the official Python SDK: the same environment variables and defaults, retry policy and error kinds. It offers an async client (tokio) and a blocking client meant for synchronous code such as a game loop or CLI. It is the Rust sibling of the same author's Elixir SDK.

Questions are built with a Questions builder using Noul, Choice and Score, and the response exposes typed answers plus the model version and token usage. Feature flags control async, blocking and TLS backends. It is published on crates.io. Feature flags select the async client, the blocking client, or both, and the TLS backend, so it can be kept small for embedded or game use.

What the decision model decides

TypeQuestionAnswers
Yes / noIs this ticket about billing?yes · no
ChoiceWhat is the customer's tone?calm · frustrated · angry
ScoreHow urgent is this ticket?Can wait · This week · Today

How it works

  1. Add the crate with async and/or blocking features.
  2. Build Questions and send state.
  3. Read typed answers, model and usage.
  4. Apply thresholds in your code.

Strengths

  • Blocking client suits game loops and CLIs.
  • Mirrors official SDK behavior.

Caveats

  • Unofficial; version 0.1.
  • Requires a TypeSafe key.

Getting started

Add typesafe-rust-sdk = "0.1" to Cargo.toml (enable the blocking feature if needed).

At a glance

Type
Library
Status
beta
Language
Rust
Runtime
library (crate)
Has code
yes

Use cases and integrations

How curated lists describe it

Frequently asked questions

Why a blocking client?

For synchronous code such as game loops or CLIs.

How is the library imported?

As typesafe, e.g. use typesafe::Client.

Is it official?

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