Rig
Rust LLM application framework with an experimental rig-typesafeai crate for typed Choice, Score and Noul Jev queries.
Overview
Rig is a Rust library for building modular LLM-powered applications: agentic multi-turn workflows, a unified interface over 20+ model providers and 10+ vector stores, completion and embedding workflows, OpenTelemetry GenAI conventions, and browser WASM support for the core. Its README warns that breaking changes are expected.
The fetched README excerpt does not mention Jev. Directory lists describe an experimental rig-typesafeai crate that expresses Jev questions and answers with Rust types: typed Choice, Score and Noul queries with response validation, examples and fixtures. That gives Rust applications built on Rig a typed way to call a decision model next to their LLM agents.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Typed Choice queries defined as Rust types | — |
| Score | Typed Score queries | — |
| Yes / no | Typed Noul queries | — |
How it works
- Add the rig-typesafeai crate
- Define questions as Rust types
- Send to Jev and validate the response
- Use the typed answer in a Rig workflow
Strengths
- Rust type safety for decision answers
- Response validation and fixtures
Caveats
- Crate is experimental per the list
- Jev crate not described in the fetched README
- Rig expects breaking changes
At a glance
- Type
- Library
- Status
- prototype
- Language
- Rust
- Runtime
- Rust library
- Has code
- yes
- Has tests
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
An experimental TypeSafe crate in Rig for expressing Jev questions and answers with Rust types.
logicrw/awesome-jev-projectsRust `rig-typesafeai` crate with typed Choice, Score, and Noul queries, response validation, examples, and fixtures.
cobanov/awesome-jev
Frequently asked questions
How does Rig support Jev?
Through an experimental rig-typesafeai crate with typed Choice, Score and Noul queries, per the list summaries.
Is it stable?
No; the crate is experimental and Rig warns of breaking changes.
What else does Rig do?
It is a general Rust framework for LLM agents, completions, embeddings and vector stores.
Related projects
Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.
PluginproductionTypeScriptEffect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.
ProjectproductionTypeScriptPHP 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