pokemon-player

Automate Pokemon gameplay through a headless emulator with RAM reads.

11|Updated May 17, 2026

Search Tags:#automation #vision #ai-agent #headless #pokemon #emulator #ram-reading

Ready to run

npx skills add https://github.com/StarryCod/cogitum --skill pokemon-player-starrycod

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pokemon-player
Source: https://github.com/StarryCod/cogitum/tree/main/cogitum/data/skills/gaming/pokemon-player
Command: npx skills add https://github.com/StarryCod/cogitum --skill pokemon-player-starrycod

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables playing Pokemon games using a headless emulator with RAM reads, removing the need for a visible UI and manual setup.

Core Features & Use Cases

Headless Pokemon emulation to play games without a GUI and RAM state extraction for decision making.
Integrated save/load workflow and memory tagging to track progress across sessions.
Real-time observation and control loop driven by an agent package to guide gameplay from prompts.

Quick Start

Clone the pokemon-agent project, create a Python 3.10+ virtual environment, place a ROM in roms/, and start the server according to the startup guide.

Frequently Asked Questions about pokemon-player

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

FAQPage Schema

How do I automate playing Pokemon games using a headless emulator?▼

To automate playing Pokemon games using a headless emulator, this Skill extracts RAM state to drive gameplay decisions without a visible UI. You need to clone the pokemon-agent project, set up a Python 3.10+ environment, and provide a ROM file to start the server.

What is RAM-driven AI for Pokemon emulation?▼

RAM-driven AI for Pokemon emulation is a technique where the agent reads memory addresses directly to understand game state. This removes the need for visual screen parsing, allowing the AI to make decisions and guide gameplay based on exact memory values.

Do I need a specific Python environment to run headless Pokemon automation?▼

Yes, headless Pokemon automation requires a Python 3.10+ virtual environment. You must create this environment, install the necessary pokemon-agent package dependencies, and place your ROM file in the designated roms directory before starting.

Can I observe an AI agent playing Pokemon in real time?▼

Yes, you can observe an AI agent playing Pokemon in real time using an optional live dashboard. While the emulator runs headlessly, the dashboard provides real-time observation of the gameplay session and health checks for the running server.

How to generate training data from Pokemon gameplay using an AI agent?▼

To generate training data from Pokemon gameplay, you apply this Skill to automate sessions via a headless emulator and RAM reads. The integrated memory tagging and save/load workflow track progress across sessions to capture the gameplay data.

What are the limitations of using RAM reads for Pokemon AI automation?▼

Using RAM reads for Pokemon AI automation requires specific memory addresses for each game version, meaning the approach is limited to supported ROMs. It also requires a running server with health checks and cannot process visual elements not mapped to memory.