cocacola-lab/MineLand
Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs
This simulator helps AI researchers and developers create and test AI agents in a complex, multi-agent environment inspired by Minecraft. It takes in AI agent designs and scenarios, and outputs data on how agents interact, communicate, and collaboratively solve problems under realistic constraints like limited senses and physical needs. It's designed for those studying collective AI behaviors and training intelligent agents.
111 stars. No commits in the last 6 months.
Use this if you need to simulate how multiple AI agents interact and cooperate in a detailed virtual world to understand complex behaviors and emergent strategies.
Not ideal if you are looking for a game to play or a simple single-agent AI environment for basic task learning.
Stars
111
Forks
25
Language
Python
License
MIT
Category
Last pushed
Sep 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/cocacola-lab/MineLand"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google-deepmind/concordia
A library for generative social simulation
Mai-xiyu/Minecraft_AI
AI Play Minecraft
mikelma/craftium
A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI...
rezaho/MARSYS
Multi-Agent Reasoning Systems
Dominien/brunnfeld-agentic-world
Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by...