All decision model projects

Experimental Minecraft bot where each TypeSafe decision picks one primitive action, which completed a 338-block flag build in recorded runs.

Experimental Jev wire-compatible engine that claims to produce typed decisions from Mandelbrot fractal dynamics rather than a trained model.

Symfony AI platform bridge for TypeSafe, letting PHP Symfony apps call System One models like Jev.

Community quickstart and FAQ for Jev that points to a third-party free playground at jevtypesafeai.com.

Public demo repository for Jev shared on X; the README gives no further detail.

Small public demo repository for TypeSafe's Jev, shared on X; its README contains only a one-line description.

Archived Jev-compatible HTTP server for Laya, superseded by upstream laya[serve]; includes a migration table.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

Desktop dictation and meeting-notes app with optional Jev fast judgments for citation checks, history search and live meeting cues.

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.

Local decision engine on zero-shot ModernBERT and SigLIP2 answering Choice, Noul, Score and Relation over text, documents and 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.

50 small interactive demos comparing Jev's Choice, Score and Noul with OpenAI gpt-4o-mini side by side, runnable offline from fixtures.

Library and MCP server that scores a fixed set of choices with a model you already run (llama.cpp, Ollama, OpenRouter).

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.