jevbooks

← All projects

JevPlaysPokemon

anxkhn/JevPlaysPokemon

Level-40 Pokémon agent using Jev for battle decisions on real FireRed.

Game & Simulation0.78Runner-up: Agent Decisions
Automated README summary

Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Pokémon-playing agent that runs Gen 3 battles in two modes: Pokémon Showdown text battles on any computer, and a real FireRed ROM on Mac with Apple Silicon. Jev picks each turn's move or switch.

How it uses Jev

Each turn the host reads the battle from RAM and sends Jev a JSON snapshot of the fight plus only the legal moves and switches. Jev returns one action with a probability for every option. If the answer is illegal, the battle stops; there is no backup brain.

Primitives:choice

Technique worth stealing

Compress the live battle state into a JSON snapshot and let a typed choice over legal actions drive the turn.

Try it

Copy .env.example to .env with a TypeSafe API key; for Showdown run npm start -- --opponent all; for FireRed run setup_emulator.py and ./emulator.sh --prepare.

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 material0.80
  • Shows a System One patternFound in material0.62
  • Describes handling uncertaintynot found in the excerpt0.03
  • Reports measured numbersnot found in the excerpt0.10
  • Is a runnable toolnot found in the excerpt0.35
  • Top-10 learning shortlist signalunclear0.54
  • Is a replica of the modelnot found in the excerpt0.05
  • Solves a common problem (0–2)score on a 0–2 scale0.00 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.80Shows a System One pattern0.62Describes handling uncertainty0.03Reports measured numbers0.10Is a runnable tool0.35Top-10 learning shortlist signal0.54Is a replica of the model0.0500.51Solves a common problem (0–2)0.00 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.37Inspection0.2400.51

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 20 Sept 2026.