cocacola-lab/MineLand
Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs
Implements a Minecraft-based simulation environment supporting up to 48 agents with constrained sensory inputs (visual, auditory, environmental) and resource management mechanics that drive emergent communication and collaboration. Built on Python 3.11 with Node.js and Java backends, it provides Gym-style APIs for agent control and exposes a standard Minecraft 1.19 server for observation and debugging. Includes the Alex agent architecture, designed around multitasking theory to handle complex coordination and scheduling within resource-constrained scenarios.
111 stars. No commits in the last 6 months.
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...
Dominien/brunnfeld-agentic-world
Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by...
rezaho/MARSYS
Multi-Agent Reasoning Systems