jevbooks

← All projects

NeoHorse

TokenRhythm/NeoHorse

Open 4B decision model for agent workflows via prefill-only inference.

Agent Decisions0.42Runner-up: Scoring & Ranking
Automated README summary

Automatically summarized from the README on 28 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

NeoHorse-Jev-4B is TokenRhythm's open-weight decision model built on NeoHorse-1-4B. It turns application state into structured decisions and probabilities for routing requests, selecting tools, or controlling workflows.

How it uses Jev

Applications define questions and possible answers. Jev uses prefill-only inference to select an action with Choice, check a condition with Noul, or assign a rating with Score. Results are used to route requests, select tools, or control a workflow.

Primitives:choicenoulscore

Technique worth stealing

Prefill-only inference on a 4B base model to produce calibrated decisions without text generation.

Try it

Download the complete model bundle and use the matching runtime or backend adapter.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectunclear0.42
  • Shows a System One patternnot found in the excerpt0.22
  • Describes handling uncertaintynot found in the excerpt0.06
  • Reports measured numbersFound in material0.80
  • Is a runnable toolFound in material0.83
  • Top-10 learning shortlist signalnot found in the excerpt0.32
  • Is a replica of the modelFound in material0.87
  • Solves a common problem (0–2)score on a 0–2 scale1.31 / 2
  • About JevFound in material0.66
Signals
Jev is core to the project0.42Shows a System One pattern0.22Describes handling uncertainty0.06Reports measured numbers0.80Is a runnable tool0.83Top-10 learning shortlist signal0.32Is a replica of the model0.8700.51Solves a common problem (0–2)1.31 / 2012

no-judgment band (0.40–0.60)

Design patterns
Check-up0.29Blind review0.2600.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 28 Sept 2026.