User repository on GitHub
Rust client for the TypeSafe AI systemone API
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Repos & SDKs
systemone (Rust client)
A Rust client for the TypeSafe AI systemone API: ask named questions about text or structured state and get back typed, probabilistic answers, positioned by the README as a Rust counterpart to the official TypeSafe JavaScript SDK.
- Stars
- 0
- Language
- Rust
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- lu-zero
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
Highlights
- Rust client for the TypeSafe AI systemone API, described as the Rust counterpart to the official @typesafe-ai/sdk JavaScript package.
- Asks named questions about text or structured state and receives typed, probabilistic answers.
- Built on isahc, which the README calls executor-agnostic: the crate makes no assumption about tokio, smol or any other async runtime.
- A systemone-macro crate provides #[derive(ChoiceCriteria)] to build a choice question's labels and descriptions from an enum at compile time.
- A third crate, systemone-facet, does the same via the facet library. MIT, 0 stars, created and pushed 2026-09-18.
Watch out
README reviewed 2026-10-17; the captured excerpt ends inside the workspace-layout table, so usage examples, feature flags, authentication and release state beyond the crates.io badge are not visible in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A Rust client for the TypeSafe AI systemone API that lets you ask named questions about text or structured state and receive typed, probabilistic answers.
The README describes it as a Rust counterpart to the official @typesafe-ai/sdk for JavaScript; it is a separate community crate rather than a library published by TypeSafe itself.
The README says isahc is executor-agnostic, so the crate makes no assumption about tokio, smol or any other async runtime, which keeps it usable in projects with different runtimes.
systemone-macro provides #[derive(ChoiceCriteria)] to build a choice question's labels and descriptions from an enum at compile time, and systemone-facet offers the same idea through the facet library.
The README shows crates.io, CI and dependency-status badges, but the captured excerpt does not include a cargo add command or Cargo.toml lines, so the exact install step is not documented in the digest.
MIT, according to the license badge and digest metadata; created and last pushed 2026-09-18 with 0 stars and 0 forks, so it is a very new and small project.
The excerpt stops inside the workspace layout table, so usage examples, retries, error types, API key configuration and release history beyond the crates.io badge are not available in the digest.
More Jev resources like this
An unofficial Rust client for TypeSafe's System One API behind Jev: typed Noul, Choice, Score and Box questions, images, and both async and blocking clients. Its behaviour follows the official Python SDK, with the same environment variables, retry policy and error kinds.
Jev Repos & SDKs#community#github#rust
Community
phiat/typesafe-rust-sdkRust
phiat/typesafe-rust-sdkRustAn unofficial async Rust client for the TypeSafe System One API, mirroring the shape of the official Python and JavaScript SDKs. It builds noul, choice and score questions with a fluent builder and returns calibrated probabilities.
Jev Repos & SDKs#community#github#rust
Community
2commits/typesafe-systemoneRust
2commits/typesafe-systemoneRustAn open-source, local-first and cross-platform runtime for System One decision models that exposes a Jev-compatible POST /v1/systemone API and a native CLI without Python, PyTorch, Transformers, Conda or a virtual environment.
Jev Repos & SDKs#community#github#rust
Community
LiteVar/system-oneRust
LiteVar/system-oneRustA Rust client for System One models — which answer fixed questions with calibrated probabilities instead of generating text — whose first backend is TypeSafe AI's Jev. It layers cost-matrix decisions, caching, recording and calibration on top.
Jev Repos & SDKs#community#github#rust
Community
heyaozh/system-oneRust
heyaozh/system-oneRustA Python library that turns Jev-style decision models into ordinary function calls: check returns a bool, classify picks one option, label picks every option that applies, and score rates on a scale, with probabilities behind every answer.
Jev Repos & SDKs#community#github#python
Community
jlowin/vibecheckPython
jlowin/vibecheckPythonLaya GGUF inference and an HTTP server written in Goish Rust: one Linux binary runs upstream Laya or OpenThai-SystemOne on your CPU and serves typed choose, score and check decisions over HTTP, the CLI or a JSON-lines process.
Jev Repos & SDKs#community#catalog-import#madewithjev
Community
cogentica-ai/laya-goishRust
cogentica-ai/laya-goishRustFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.