Browse builds

Site search that recalls candidates locally, then uses Jev to score and rerank them.

Probability-tree and graph runtime for verifiable multi-step Jev decisions.

Local Jev-compatible typed decisions from unstructured state in one forward pass.

Local Jev-compatible proxy that learns an application’s typed decisions and serves them with a Laya head.

Training and inference stack for calibrated Jev-style choice models with dynamic candidate sets.

Open visual decision model that encodes an image once and answers multiple structured questions.

Solar Mini–based local model for Jev-style typed decisions.

Open-weight Jev alternative that returns typed decisions with probabilities in one forward pass.

Open-model semantic-if engine for local Jev-style decisions.

Go SDK and CLI for TypeSafe Jev typed yes/no, Choice, and Score decisions.

Swift client for TypeSafe Jev typed judgments instead of generated text.

Workbench that converts Chat Completions requests into editable Jev State and Questions, compares text generation with typed judgments, and exposes reusable proxy routes.

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

Jev-powered relevance filtering and reranking for RAG in Python.

Probabilistic control flow for Ruby and Rails - powered by TypeSafe's Jev.

Ask typed questions about text or JSON and inspect model-derived probability distributions in a browser. One container runs the model, the original Decision Lab explorer, and a TypeSafe-shaped API.

Run Jev-style typed decisions locally on your Mac with low RAM usage and fast responses.

Run SemIf (Jev-style semantic-if decisions) on a CPU — no GPU. Reads typed option probabilities straight from an open model in one forward pass, plus a web UI.

Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint.

open-jev is a browser-focused TypeScript library for typed decisions: one piece of text (the state) plus any number of typed questions go in, and one forward pass returns a calibrated probability distribution per question. Nothing is generated, so an answer is always one of the options you provided.

Supersimple way to serve LLMs as a Jev-like endpoint.

Jev-style structured decisions on DiffusionGemma: the example server from vLLM PR 57250.

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

Train small, insanely fast local classifiers from Jev-compatible examples. Run locally in your browser or Node.js.

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating).

Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime.

TypeScript library that maps Jev Choice, Score, and Noul questions onto classification, ranking, extraction, verification, and array workflows.

Local 596M typed-decision model with its own weights, Choice, Score, and Noul support, and a Jev-compatible System One endpoint.

Independent DiffusionGemma and SGLang typed-decision server for text and images, with a drawing playground and public evaluation artifacts.

Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.

React components that resolve which component to render, how to order a list, and whether to show an affordance — from calibrated judgments returned by TypeSafe's Jev. No repository-level license file was found during review.

High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from SQL.

Natural-language row filtering for MySQL, powered by TypeSafe Jev.

A lightweight, native Swift 6 bridge integrating TypeSafe AI's Jev System One decision model into Apple's Foundation Models framework.

Semantic decisions as ordinary Ruby — feels?, decide, score, Rails validations and pattern matching powered by Jev

DuckDB extension: typed Jev answers as real SQL types

SillyTavern extension where Jev scores replies against configured narration rules before adding guidance.

Conversational-avatar framework with a Jev gate that judges whether a speaker has finished a turn.

Generative UI framework with an experimental evaluator that lets Jev choose among application-supplied composition criteria.

Local Jev-like typed-decision runtime using ONNX and quantized models for offline CPU inference.