jevbooks

← All projects

jeff-ink

saembit/jeff-ink

Type anything; Jev maps free text to authored Ink choices.

Classification & Routing0.89Runner-up: Game & SimulationQuestionnaire
Automated README summary

Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

jeff-ink wraps an inkjs story so players type instead of click. Each typed line is sent to Jev, which returns probabilities over the story's current choices plus a none option, so the story only moves where the author wrote it.

How it uses Jev

Jev answers one Choice question (which current choice the player means, with a none option) plus two Noul yes/no questions (asking for help, off-story) in one request. The winning choice needs to clear threshold (default 0.5); otherwise decision.index is null with reason none or unsure.

Primitives:choicenoul

Technique worth stealing

Give each choice aliases after a double colon so Jev sees extra phrasings while the player only sees the first part.

Try it

export TYPESAFE_API_KEY=...; npm install; npm run demo, then open http://localhost:8787.

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-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

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 projectFound in material0.94
  • Shows a System One patternFound in material0.86
  • Describes handling uncertaintynot found in the excerpt0.12
  • Reports measured numbersnot found in the excerpt0.02
  • Is a runnable toolFound in material0.92
  • Top-10 learning shortlist signalunclear0.40
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale0.47 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.94Shows a System One pattern0.86Describes handling uncertainty0.12Reports measured numbers0.02Is a runnable tool0.92Top-10 learning shortlist signal0.40Is a replica of the model0.0400.51Solves a common problem (0–2)0.47 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.98Menu0.52Viewfinder0.49Prefetch0.36Blind review0.24Funnel0.2000.51

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 23 Oct 2026.