jevbooks

← All projects

jev-plays

mansicer/jev-plays

Jev plays Craftax; an LLM sets the goals.

Agent Decisions0.49Runner-up: Game & SimulationGhostwriter
Automated README summary

Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A harness, web UI and experiments where TypeSafe's jev plays Craftax (JAX Crafter), optionally guided by an OpenAI-compatible LLM planner. For researchers comparing System One and System Two agents.

How it uses Jev

Each step, code lists feasible macro options or raw actions with facts. Jev picks one Choice among them, optionally guided by an LLM-written objective and standing rules. The chosen option is executed in the game.

Primitives:choice

Technique worth stealing

Give jev facts, never advice; let it choose among typed options.

Try it

uv sync; cp .env.example .env; craftax_agent/run_server.sh; open http://localhost:8765

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 material0.94
  • Shows a System One patternFound in material0.82
  • Describes handling uncertaintynot found in the excerpt0.07
  • Reports measured numbersnot found in the excerpt0.12
  • Is a runnable toolnot found in the excerpt0.19
  • Top-10 learning shortlist signalunclear0.59
  • Is a replica of the modelnot found in the excerpt0.10
  • Solves a common problem (0–2)score on a 0–2 scale0.03 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.94Shows a System One pattern0.82Describes handling uncertainty0.07Reports measured numbers0.12Is a runnable tool0.19Top-10 learning shortlist signal0.59Is a replica of the model0.1000.51Solves a common problem (0–2)0.03 / 2012

no-judgment band (0.40–0.60)

Design patterns
Ghostwriter0.83Funnel0.62Flight recorder0.57Menu0.50Check-up0.2700.51

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 25 Sept 2026.