pokemon-player

Automate headless Pokemon gameplay through emulator RAM reads and REST endpoints.

150|25|Updated Apr 20, 2026
One-click install
npx skills add https://github.com/Devsoul2026/Hermes-One-Click --skill pokemon-player-devsoul2026
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pokemon-player
Source: https://github.com/Devsoul2026/Hermes-One-Click/tree/main/hermes-agent/skills/gaming/pokemon-player
Command: npx skills add https://github.com/Devsoul2026/Hermes-One-Click --skill pokemon-player-devsoul2026

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates controlling a headless Pokemon game session using an emulator and RAM reads.

Core Features & Use Cases

  • Headless Play: run a server-backed Pokemon session with RAM-based state inspection.
  • AI Decision Loop: observe, orient, decide, and act using REST endpoints and memory markers.
  • Use Case: train AI agents to play Gen 1 battles or demonstrate autonomous gameplay locally without a GUI.

Quick Start

Run the pokemon-agent server with a ROM attached, then call the /state and /screenshot endpoints to start automating gameplay.

Frequently Asked Questions about pokemon-player

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate headless Pokemon gameplay using RAM reads?

To automate headless Pokemon gameplay, run a local pokemon-agent server with a valid ROM, then use REST endpoints like GET /state and POST /action to inspect RAM and control the session.

What Python version do I need to run an AI Pokemon agent server?

You need Python 3.10 or higher to run the pokemon-agent server that controls the headless emulator session and exposes the REST endpoints for autonomous gameplay.

Which REST endpoints are required for an AI agent to play Pokemon autonomously?

The AI decision loop requires GET /state, GET /screenshot, POST /action, POST /save, and POST /load endpoints to observe the game state and execute actions via the emulator.

Can I train AI agents on Gen 1 Pokemon battles without a GUI?

Yes, you can train AI agents on Gen 1 battles without a GUI by running a headless emulator session backed by a local pokemon-agent server and RAM-based state inspection.

What is the decision loop for autonomous Pokemon gameplay automation?

The decision loop for autonomous Pokemon gameplay follows the observe, orient, decide, and act pattern, using REST endpoints and memory markers to continuously inspect RAM state and execute actions.

Do I need a specific ROM file to test AI gameplay in a headless emulator?

Yes, a valid ROM file must be attached to the running pokemon-agent server to initialize the headless emulator session for AI experiments or autonomous gameplay demonstrations.