Mai-xiyu/Minecraft_AI
AI Play Minecraft
Leverages an OpenAI-compatible LLM with a feedback loop that feeds action success/failure back into the agent's decision-making, enabling adaptive strategy refinement. Combines a PyQt6 GUI frontend with a Node.js mineflayer bot server, using async HTTP communication and optional response caching plus pattern recognition for faster repeated decisions across 22 action types (movement, crafting, combat, chest operations, etc.).
Stars
65
Forks
12
Language
Python
License
MIT
Category
Last pushed
Feb 22, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Mai-xiyu/Minecraft_AI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
google-deepmind/concordia
A library for generative social simulation
mikelma/craftium
A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI...
cocacola-lab/MineLand
Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs
Dominien/brunnfeld-agentic-world
Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by...
rezaho/MARSYS
Multi-Agent Reasoning Systems