Skip to content

Jevlin

Experimental typed Zig SDK for Jev targeting Zig 0.16.0, asking yes/no, classification, and scoring questions in one request and returning probabilities with Zig enums.

Stars
1
Language
Zig
License
MIT
Published by
Community
Author
copyleftdev
Last verified
Oct 2026

About this project

A typed Zig SDK for TypeSafe AI's Jev. Ask yes/no, classification, and scoring questions in one request. Get probabilities and Zig enums back. Zig 0.16.0 · Experimental · Independent of TypeSafe AI. The complete example shows client setup, buffers, and cleanup. Offline examples cover structured questions, error handling, and bounded parallel use. For a local checkout, add this to your build.zig.zon dependencies: In build.zig, add the dependency to your application module:

Quoted from the project's README. Read the full README.

Highlights

  • Asks noul, enum choice, and leveled score questions together with typed Zig enum answers.
  • Caller owns request, response, and scratch buffers; borrowed results must be copied before reuse.
  • Local checks run credential-free with loopback transport tests; live runs need an API key and bill.
  • Native CI covers Linux, macOS, and Windows plus TLS rejection, with separate fuzz and soak workflows.

Watch out

Pre-release without dynamic schemas, model discovery, or connection pooling; live requests are billable, retries can add charges, and the SDK reads no credential files. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

4.5kGitHub stars
Ruby-native AI framework whose RubyLLM::Judge class asks typed judgment questions: a probability that a statement holds, choices or scores, answered by the TypeSafe provider alongside 18 other hosted and local providers under one consistent API.
Jev Repos & SDKs#community#ruby#framework
882GitHub stars
A Node and TypeScript package that runs Convai's Laya checkpoint through ONNX Runtime, with the same system_one shape as the Python reference.
Jev Repos & SDKs#community#typescript#open-models
21GitHub stars
Self-hosted Python SDK and System One-compatible API for runtime-defined Choice, Boolean and Score decisions on pinned open models, across Torch, vLLM, MLX, llama.cpp and WebGPU. Each result records probabilities, token usage, timing, model revision and prompt version, with committed row-level benchmarks.
Jev Repos & SDKs#community#sdk#self-hosted
13GitHub stars
Go Unix CLI that pipes state on stdin into one Jev question — noul, choice, or score — across TypeSafe, Cloudflare, and Vercel providers, printing machine-readable JSON and signaling success by exit code.
Jev Repos & SDKs#community#github
7GitHub stars
Unofficial Go and Rust clients for the System One API covering noul, choice and score questions, with env-based config, retries, typed errors and gateway support.
Jev Repos & SDKs#community#github
5GitHub stars
Independent C++20 library for typed, model-backed routing, classification and scoring. Compile-time enum schemas define Choice, Noul, Score and Probability answers with abstention; local Laya inference runs through ONNX Runtime or ggml, and an opt-in remote backend speaks the same typed API with hosted inference.
Jev Repos & SDKs#community#cpp#library

From the Jev guides

Original write-ups on what this entry is for.

Closed weights have not stopped the ecosystem from rebuilding the shape in the open. API-compatible servers, retrained heads on small models, and inference-time tricks that skip generation entirely.
Jev Repos & SDKs#open-models#research#local
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai