jevbooks

← All projects

dwarf-fortress-agent-skill

frederico-kluser/dwarf-fortress-agent-skill

Autoplay agent for Dwarf Fortress adventure mode using Jev decisions.

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 autoplay agent for Dwarf Fortress adventure mode. A fleet of Jev decision agents chooses each action, DeepSeek writes narrative and questions, CoALA memory grows across campaigns, and a Portuguese web UI gives the human objective, supervision, and kill-switch.

How it uses Jev

Jev-R selects CoALA memories via noul and dominant_theme. Jev-A picks a macro-action from code-generated candidates, plus urgency and needs_human. Jev-M decides narrator update, effort, and record type. Jev-D decides whether and how to ask the human. Confidence bands route to auto, hitl, or abstain.

Primitives:choicescorenoul

Technique worth stealing

Typed decision fleet with confidence-band dispatch: auto, hitl, abstain.

Try it

bash install.sh then df up

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 projectFound in material0.87
  • Shows a System One patternFound in material0.82
  • Describes handling uncertaintynot found in the excerpt0.13
  • Reports measured numbersnot found in the excerpt0.05
  • Is a runnable toolFound in material0.82
  • Top-10 learning shortlist signalnot found in the excerpt0.36
  • Is a replica of the modelnot found in the excerpt0.23
  • Solves a common problem (0–2)score on a 0–2 scale0.30 / 2
  • About JevFound in material0.93
Signals
Jev is core to the project0.87Shows a System One pattern0.82Describes handling uncertainty0.13Reports measured numbers0.05Is a runnable tool0.82Top-10 learning shortlist signal0.36Is a replica of the model0.2300.51Solves a common problem (0–2)0.30 / 2012

no-judgment band (0.40–0.60)

Design patterns
Traffic light0.98Ghostwriter0.87Funnel0.79Questionnaire0.61Menu0.31Scorecard0.31Blind 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 15 Oct 2026.