jevbooks

← All projects

jev-factorio-agent

CompleteDotTech/jev-factorio-agent

Jev picks what, code owns how: a System One Factorio agent.

Agent Decisions0.84Runner-up: Game & SimulationFunnel
Automated README summary

Automatically summarized from the README on 27 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Factorio agent where Jev (TypeSafe AI's System One) makes fast macro decisions—goal, next action, stuck detection—while deterministic code handles game rules, option filtering, and actuation. For researchers exploring Jev-driven game agents.

How it uses Jev

Jev answers typed Choice/Score/Noul questions about the current game state to select goals and next actions, and to detect being stuck. The loop gates actions on confidence; low-confidence results fall back to scripted behavior. Decisions are logged to distinguish Jev choices from fallbacks.

Primitives:choicescorenoul

Technique worth stealing

Separating fast macro decisions (Jev) from deterministic game rules and actuation.

Try it

Run offline: PYTHONPATH=src python -m jev_factorio --backend mock --steps 8 --tick-seconds 0

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 material0.96
  • Shows a System One patternFound in material0.89
  • Describes handling uncertaintynot found in the excerpt0.13
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolFound in material0.96
  • Top-10 learning shortlist signalunclear0.53
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale0.06 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.96Shows a System One pattern0.89Describes handling uncertainty0.13Reports measured numbers0.04Is a runnable tool0.96Top-10 learning shortlist signal0.53Is a replica of the model0.0400.51Solves a common problem (0–2)0.06 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.82Flight recorder0.66Blind review0.43Inspection0.30Fail open, fail closed0.3000.51

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 27 Sept 2026.