Training-free inference techniques with decision models

Jev-class decision server on an RWKV-7 1B checkpoint that reads typed answers from a constrained softmax behind /v1/systemone.

Input layout optimizer that reorders rows and fields so a prefix-caching decision model judges every record in a big table faster.

Open Jev replica on Gemma 4 E2B and Gemma 3 270M served on Modal, with eight demos and a TypeSafe eval head-to-head.

Local System One-compatible server that reads option probabilities from a small MLX LLM, with measured calibration.

Swift package for typed decisions (probability, choice, score) over local MLX or Core AI models, Clef decision heads, or the Jev API.

Python wrapper that answers System One and OpenAI Decisions API questions using any OpenAI-compatible chat model.

pijev: drop-in wrapper for the TypeSafe Python SDK that averages Jev answers across option orders in one request.

Run System One-style typed decisions on any Hugging Face instruct model, with a typesafe-sdk-compatible server and calibration tools.

TypeScript SDK and coding CLI where Jev only picks options: typed routers, decision programs and grammar-constrained AST building.

Research preview: Python client and pinned adapters for running System One decision models on your own Modal GPUs.

Ollama-style single binary that pulls and runs open decision models locally, with a TypeSafe-compatible API and playground.

Local, deterministic Rust decision engine reading single-letter answer logits from one llama.cpp pass, wire-compatible with Jev.

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.

Playful web arena where Jev does arithmetic, writes chat replies and draws pixel art one Choice or Noul decision at a time.

Chat interface with no generative model: Jev picks intent, stance, claim and tone, and a deterministic compiler writes the reply.

Experiment that makes 16x16 pixel art by asking Jev 256 parallel per-pixel color Choice questions, plus refinement passes.

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

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.

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

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

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

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

Local Jev-compatible /v1/systemone server answering Noul, Choice and Score from open-weight models, usable with the official SDK.

Makes any logprob-capable model answer typed questions Jev-style in one pass, in Jev's API shape, with probes and scorecards.

Scores every allowed option of a typed schema from one MLX prefill on Apple Silicon and assembles schema-valid JSON with probabilities.

From-scratch Rust reimplementation of Laya on candle, including the encoder, decision head, calibration, RLCD training and a server.

Open System One decision model (LoRA on Qwen3.5-4B) that reads typed answers from logits in one pass, with its benchmark harness.

Zero-training toolkit that turns local LLMs and multimodal models into Jev-style decision services via prefill-only scoring.

Serves the Jev request shape from any OpenAI-compatible endpoint by reading single-letter option probabilities from logprobs.