Skip to content

S1 Ruby

Ruby gem that makes System One measurement a language primitive: psi prepares a state, judge/choose/score return calibrated distributions, and ? collapses them for control flow. Ships TypeSafe, protocol (/v1/systemone) and CUA providers behind one interface with its own spec suite.

Stars
2
Language
Ruby
License
MIT
Published by
Community
Last verified
Oct 2026

About this project

System One (S1) measurement — and the collapse that follows it — native to Ruby. An S1 model answers a typed question about data with a calibrated probability. It does not generate, and it does not decide. Code asks; code decides. For the Ruby on Rails implementation, see: s1-rails. For the terms, see THEORY.md. Where this README and the theory disagree, the theory is right. The three kinds — noul · choice · score · Level · Scales · Distribution · Batch · Structured state · Reading distributions.

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

Highlights

  • No runtime dependencies; requires Ruby 3.2 or newer.
  • judge, choose and score return full distributions, and a ? method collapses them to values.
  • Providers: TypeSafe by default, protocol for any /v1/systemone server, and CUA by checkpoint.
  • The optional core extension adds primitives to String, Hash and Array, plus psi.
  • S1.configure sets provider, timeout, threshold and logger, each with a default.

Watch out

MIT licensed. Real judgments need a TypeSafe API key or a self-hosted /v1/systemone server, and the psi/primitive extensions are experimental and off by default. A companion Rails gem lives at innocentdiaz/s1_rails.

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
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
4GitHub stars
A pre-release Python framework for predictions on mixed text and tabular data: Jev Noul and Score questions turn text columns into numeric features, then a tabular foundation model such as TabPFN learns from labeled rows in context. Offers hosted and fully local backends.
Jev Repos & SDKs#community#tabular#predictions
1GitHub stars
Unofficial portable Clojure SDK for TypeSafe System One. It posts state and typed questions to /v1/systemone, lists available models, and returns validated Clojure data with keyword or string answer keys, on a JVM backend or a native Jolt backend.
Jev Repos & SDKs#community#clojure#sdk
1GitHub stars
Dependency-free Go 1.24+ client for Jev Noul, Choice, and Score questions: ChoiceOf[T] and ScoreOf[L] return the caller's own types and reject labels the question never offered, with validation before sending, retries that honor Retry-After, OpenRouter support, and eleven tested examples.
Jev Repos & SDKs#community#go#sdk
1GitHub stars
Dependency-free TypeScript SDK that turns Jev Noul, Choice and Score answers into named decisions: enter/exit thresholds with hysteresis, nested decision trees settled in one call, a JSONL journal, threshold replay without inference and Brier calibration.
Jev Repos & SDKs#community#typescript#decisions

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