Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web

TL;DR

Holos is a scalable, web-based multi-agent system designed to enable persistent, self-organizing agent ecosystems, advancing toward Artificial General Intelligence with a novel five-layer architecture.

Contribution

Introduction of Holos, a five-layer architecture for large-scale, persistent multi-agent systems, featuring efficient agent generation, resilient coordination, and an endogenous value cycle.

Findings

Holos provides a scalable platform for long-term agent ecosystem persistence.

Holos demonstrates resilient coordination through its market-driven Orchestrator.

Holos enables continuous evolution and self-organization of agents.

Abstract

As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneous agents autonomously interact and co-evolve, marks a pivotal shift toward Artificial General Intelligence (AGI). However, LLM-based multi-agent systems (LaMAS) are hindered by open-world issues such as scaling friction, coordination breakdown, and value dissipation. To address these challenges, we introduce Holos, a web-scale LaMAS architected for long-term ecological persistence. Holos adopts a five-layer architecture, with core modules primarily featuring the Nuwa engine for high-efficiency agent generation and hosting, a market-driven Orchestrator for resilient coordination, and an endogenous value cycle to achieve incentive compatibility. By bridging the gap between micro-level collaboration and macro-scale emergence, Holos hopes to lay the foundation for the next generation of the self-organizing and continuously evolving Agentic Web. We have publicly released Holos (accessible at https://holosai.io), providing a resource for the community and a testbed for future research in large-scale agentic ecosystems.