Open decision models and reproductions with decision models

Local Snake game where code computes facts for each legal move and a local Qwen3.5 picks one in a single Jev-style Choice pass.

Toy local Jev-shaped decision API on a 0.5B model that answers yes/no, choice and score questions by scoring option tokens.

Independent Jev-style server on DiffusionGemma and SGLang that classifies doodles, flowers and messages with Choice, Score and Noul.

Video demo code comparing Jev with Laya, Strands Decider and Claude on grading, fetching and prompt-injection resistance.

Small experiment: reordering enum options changed a local Jev clone's answers on its old default, while hosted Jev's did not.

Toolkit for reading Choice, Score and Noul decisions out of embedding models, with data, fine-tuning, benchmarks and a server.

Audio-native Jev-style model: a frozen Whisper encoder encodes speech once and typed questions return emotion and prosody distributions.

Archived Jev-compatible HTTP server for Laya, superseded by upstream laya[serve]; includes a migration table.

Cloudflare's Apache-2.0 27B multimodal decision model that scores every option of every question jointly, with a Jev-compatible API.

Fastino's 340M Apache-2.0 decision classifier that scores caller-defined labels in one forward pass for routing, intent and scoring.

Perplexity's Apache-2.0 multimodal decision model on Qwen3.8-27B, reporting 61.56 on the Decision Index versus 57.9 for Jev.

Multilingual non-autoregressive decision engine answering choice, score and yes/no questions in one ~33 ms pass, with a checkpoint router.

Family of small Jev-like decision models you can train and run yourself, with a server compatible with TypeSafe's SDK.

Open-source Jev-compatible decision model served by one native binary on a laptop CPU, returning probabilities in 28 to 130 ms.

Rust daemon and CLI that pulls open decision models like Laya and serves them locally behind a TypeSafe-compatible /v1/systemone.

AWS Strands Labs' 2B decision model: Qwen3.5-2B with a pointer head scoring options and calibrated confidence, plus a CLI.

Featherless AI server that turns compatible open Hugging Face models into a /v1/systemone classifier by reading next-token logits.

Native vLLM serving for Jev-style decision models on Linux and Apple Silicon, including image and video questions for Valen.

Apache-2.0 open-weight Jev alternative that answers yes/no, choice and score questions with per-option probabilities in one pass.

Proxy that distils a repeated Jev classification task into a local model on the fly and answers most requests itself once it agrees.

Python library that gets typed, calibrated decisions from any open-weights LLM in one forward pass, with packed shared-state questions.

Drop-in local replacement for Jev that serves /v1/systemone from open weights, including questions about images.

Native C++ (llama.cpp-based) CPU inference for Dohnuts and other small decision models behind a /v1/systemone server.

Local Jev alternative on zero-shot NLI models with temperature scaling and conformal abstention; reports ECE 0.170 to 0.071, offline.

Serving layer that runs typed-decision models like Laya on your GPU or Mac behind a Jev-compatible /v1/systemone API.

Open family of System One-style models fine-tuned from Qwen3.5 and Gemma that return typed decision probabilities in one pass.

Self-hostable inference server for open decision models implementing the TypeSafe /v1/systemone API, one Docker image per engine.

Open multilingual System 1 decision engine built on Laya checkpoints with a router that picks the best checkpoint per request.

Nace.AI's open Drex decision models (v2.0 MoE, v1.5 9B, diffusion DLM) serving /v1/systemone locally via Python, llama.cpp or Ollama.

Self-hosted open Jev implementation: SDK and System One API for choice, boolean and score on pinned open models across many runtimes.