stickystyle/ZorkGPT

Teaching AI to play the classic text adventure Zork using Large Language Models

42
/ 100
Emerging

This project helps AI researchers teach large language models (LLMs) to genuinely play complex text-based interactive fiction games like Zork. It takes a game's state and an LLM's reasoning as input to produce strategic decisions and in-game actions. This is for researchers exploring AI agents, advanced natural language understanding, and adaptive learning in dynamic virtual environments.

Use this if you are researching how LLMs can develop sophisticated strategic reasoning, spatial awareness, and problem-solving skills in interactive, text-based worlds without hardcoded solutions.

Not ideal if you are looking for a pre-built agent to win specific games or a general-purpose gaming AI for graphical interfaces.

AI-research LLM-agents interactive-fiction adaptive-learning natural-language-understanding
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 14 / 25

How are scores calculated?

Stars

36

Forks

6

Language

Python

License

MIT

Category

ai-powered-games

Last pushed

Dec 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/stickystyle/ZorkGPT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.