Effect
Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.
Overview
Effect is a widely used TypeScript library for robust, type-safe applications, handling typed errors, dependency injection, structured concurrency, scheduling, tracing and schema validation. Effect 4.x is a long-term support release.
Its AI modules include a provider-neutral Decision and DecisionModel vocabulary, and the monorepo ships @effect/ai-typesafe, a TypeSafe decision provider. According to the list summary, it maps Effect's classify, probability and rating operations to Jev's Choice, Noul and Score questions. Libraries such as Discern build on this to turn decisions into typed control flow. Most of Effect is unrelated to decision models. Effect requires TypeScript 5.9 or newer with strict mode enabled and Node.js 18 or newer for most packages, and its AI modules sit alongside many other integration packages in the same monorepo.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | classify: which label fits this input?(inferred) | — |
| Yes / no | probability: is this statement true?(inferred) | yes · no |
| Score | rating: where does this input fall on an ordered scale?(inferred) | — |
How it works
- Define decisions with Effect's Decision vocabulary
- Provide the TypeSafe DecisionModel layer
- Effect maps operations to Jev questions
- Handle typed results within Effect programs
Strengths
- First-class provider in a major TypeScript framework
- Provider-neutral decision vocabulary
Caveats
- Jev provider is a small part of a large library
- Requires adopting Effect
Getting started
npm install effect @effect/ai-typesafe and provide the TypeSafe decision model layer.At a glance
- Type
- Project
- Status
- production
- Language
- TypeScript
- Runtime
- library
- Has code
- yes
- Has tests
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
`@effect/ai-typesafe` decision model mapping Effect's classify, probability, and rating operations to Jev Choice, Noul, and Score questions.
cobanov/awesome-jev
Frequently asked questions
Which package adds Jev?
@effect/ai-typesafe.
What operations map to Jev?
classify to Choice, probability to Noul and rating to Score.
Is Effect itself a decision model?
No, it is a general TypeScript framework with a decision vocabulary in its AI modules.
Related projects
Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.
PluginproductionTypeScriptPHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.
ProjectproductionPHPElixir library for unified LLM calls across providers, with an evaluate interface that calls Jev via TypeSafe or OpenRouter.
ProjectproductionElixirSelf-hosted multi-tenant AI agent platform listed as including optional TypeSafe client tools for classification, scoring and yes/no.
LibraryproductionPythonProvider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().
ServiceproductionTypeScript- SwiftJev★ 9
TypeSafe Jev provider for the SwiftDecision framework, returning validated probability distributions through its DecisionBackend protocol.
ProjectbetaSwift