ruby_llm-providers-typesafe

TypeSafe System One models (Jev) for RubyLLM: typed judgments, evaluations and reranking.

How it uses Jev

TypeSafe for RubyLLM. TypeSafe's System One models, starting with Jev, answer typed questions about your data with calibrated probabilities instead of generated text.

Getting started

Outside Bundler, load it with require 'ruby llm/providers/typesafe' .

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to ruby_llm-providers-typesafe

Browse all
ruby_llm-typesafe project preview
Integrations
TypeSafe structured-output provider for RubyLLM 2
system-one (iamaamir) project preview
Benchmarks & research
Provider-neutral System One runtime for TypeScript and Pi
system-one-adapter-rust project preview
Benchmarks & research
Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations)
jev-rag-benchmark project preview
Benchmarks & research
Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG
ruby_decision_model project preview
SDKs & clients
Ruby client for decision models such as Typesafe Jev
jev (virolea) project preview
SDKs & clients
Ruby client for the typesafe AI Jev model
typesafe-sdk (joshmn) project preview
SDKs & clients
Ruby client for typesafe.ai
@ai-sdk/typesafe-ai plus experimental_evaluate; use jev-latest as an evaluation model.
jev-feels project preview
Integrations
Semantic decisions as ordinary Ruby — feels?, decide, score, Rails validations and pattern matching powered by Jev