Automated README summary
Automatically summarized from the README on 29 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python harness that plays the Catalan Pokémon FireRed translation (Flama Roja) through mGBA, using structured game memory and typed questions to decide actions without any free-text LLM.
How it uses Jev
Each tick, build_state reads game memory into JSON, then one system_one call asks 7 parallel questions: screen_mode, overworld_action, dialog_response, battle_plan (Choice), party_critical (Noul), enemy_threat (Score), objective (Choice). policy.py combines calibrated probabilities with thresholds to emit buttons.
Primitives:choicescorenoul
Technique worth stealing
Atomic typed questions over structured state, with all decision logic in code thresholds (PolicyConfig) rather than prompts.
Try it
uv sync; ./scripts/setup-mgba-x64.sh (Apple Silicon only); cp .env.example .env; uv run flamaroja run --rom <rom>
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 projectFound in material0.97
- Shows a System One patternFound in material0.98
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.84
- Top-10 learning shortlist signalunclear0.59
- Is a replica of the modelunclear0.46
- Solves a common problem (0–2)score on a 0–2 scale0.06 / 2
- About JevFound in material0.99
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 29 Oct 2026.