Amorphous Fortress Online: Collaboratively Designing Open-Ended Multi-Agent AI and Game Environments

2025-02-08

AI Summary

This work addresses the challenge of low-barrier creation and sharing of multi-agent artificial life (ALife) systems within game-like environments. Methodologically, it introduces a collaborative web-based platform featuring a lightweight finite-state-machine (FSM) agent engine, real-time WebGL/Canvas rendering, concurrent collaborative editing, and modular environment configuration—enabling zero-code authoring, execution, and dissemination of microscopic multi-agent systems. Its key contribution is the first instantiation of an integrated, open creative paradigm unifying explainable AI behavior modeling, ALife simulation, and game design—facilitating interactive visualization and transparent debugging of emergent behaviors. The platform is publicly open-sourced and hosts a continuously evolving database of multi-agent environments. Empirically, it substantially lowers barriers to multi-agent system development and pedagogy, thereby advancing accessible research and practice in artificial life and explainable AI.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

This work introduces Amorphous Fortress Online -- a web-based platform where users can design petri-dish-like environments and games consisting of multi-agent AI characters. Users can play, create, and share artificial life and game environments made up of microscopic but transparent finite-state machine agents that interact with each other. The website features multiple interactive editors and accessible settings to view the multi-agent interactions directly from the browser. This system serves to provide a database of thematically diverse AI and game environments that use the emergent behaviors of simple AI agents.

Problem

• Designing web-based multi-agent AI environments
• Creating interactive game and artificial life simulations
• Facilitating user collaboration in AI environment development

Innovation

• web-based platform
• multi-agent AI
• interactive editors