Automated README summary
Automatically summarized from the README on 15 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An Ultima Online duel bot that makes every move via a System One decision model: open-weights Laya locally or TypeSafe's Jev in the cloud. Both use the same API, so they are interchangeable and can fight each other. A live duel monitor shows each decision with probabilities.
How it uses Jev
Each turn the duel state is written as a few lines of English and Jev answers one choice question over every legal move (e.g., damage:explosion, interrupt:magicArrow, defense:cure). The monitor shows the mode and per-mode distributions. Guardrails fall through to the next most probable legal move if the game would reject a move.
Primitives:choice
Technique worth stealing
Typed questions over legal moves with guardrails that fall through to the next most probable legal move.
Try it
scripts/deps.sh sync; cp .env.example .env; docker compose up -d --build; cd bot && npm install; npm run nvm -- duel Neo:laya Morpheus:rules
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 projectnot found in the excerpt0.30
- Shows a System One patternunclear0.46
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolFound in material0.74
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale0.02 / 2
- About JevFound in material0.97
no-judgment band (0.40–0.60)
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 15 Oct 2026.