jevbooks

← All projects

board-games

tripodxu/board-games

Gomoku board with Jev, the TypeSafe System One model, choosing moves.

Automated README summary

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

What it is

A browser Gomoku site (standard and renju-foul modes) where the TypeSafe System One model Jev picks moves, alongside a local Rapfi WASM engine. Built with Vite and TypeScript, no UI framework, with an optional Cloudflare Worker and D1 backend.

How it uses Jev

Each engine's serializeForJev(st, side) produces { state, questions, options } for Jev; the Jev client (src/core/jev/) sends them and the returned probabilities are used to pick a move, with a deterministic tactics layer as insurance. An offline mock stands in when no backend is reachable.

Primitives:choicescore

Technique worth stealing

Pair the model's probabilistic move choice with a deterministic tactics layer (one-move wins, VCF/VCT, pressure gate) as insurance rather than deep search.

Try it

npm ci && npm run dev, 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 projectnot found in the excerpt0.23
  • Shows a System One patternnot found in the excerpt0.10
  • Describes handling uncertaintynot found in the excerpt0.39
  • Reports measured numbersnot found in the excerpt0.03
  • Is a runnable toolFound in material0.94
  • Top-10 learning shortlist signalnot found in the excerpt0.21
  • Is a replica of the modelnot found in the excerpt0.05
  • Solves a common problem (0–2)score on a 0–2 scale0.09 / 2
  • About JevFound in material0.97
Signals
Jev is core to the project0.23Shows a System One pattern0.10Describes handling uncertainty0.39Reports measured numbers0.03Is a runnable tool0.94Top-10 learning shortlist signal0.21Is a replica of the model0.0500.51Solves a common problem (0–2)0.09 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.97Fail open, fail closed0.96Check-up0.83Funnel0.82Blind review0.58Scorecard0.56Flight recorder0.56Menu0.32Prefetch0.2300.51

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 Oct 2026.