stickystyle/ZorkGPT
Teaching AI to play the classic text adventure Zork using Large Language Models
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.
Stars
36
Forks
6
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
microsoft/debug-gym
A Text-Based Environment for Interactive Debugging
elizaOS/characterfile
A simple file format for character data
FlamxGames/godot-ai-assistant-hub
Embed AI assistants in Godot with the ability to read and write code in Godot's Code Editor.
TavernAI/TavernAI
Atmospheric adventure chat for AI language models (KoboldAI, NovelAI, Pygmalion, OpenAI chatgpt, gpt-4)
vegu-ai/talemate
Roleplay with AI with a focus on strong narration, consistent world and game state tracking.