DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems
Alessandro Cornacchia, Vaastav Anand, Muhammad Bilal, Zafar Qazi, Marco Canini
TL;DR
DMAS-Forge tackles the challenge of deploying distributed multi-agent systems by decoupling core agent logic from deployment concerns. It introduces a compiler-based solution that takes a structural agent workflow and a deployment specification to auto-generate glue code and configuration for protocol-compliant, distributed execution across diverse environments. The authors demonstrate a Go-based prototype built on Blueprint with plugins for agents, vLLM, and kagent, and a RPC-over-HTTP communication layer that deploys two Linux-container agents. They also discuss future directions including optimization pipelines, automatic security boundary management, and integration strategies with existing agentic frameworks to support write-once, deploy-anywhere development.
Abstract
Agentic AI applications increasingly rely on multiple agents with distinct roles, specialized tools, and access to memory layers to solve complex tasks -- closely resembling service-oriented architectures. Yet, in the rapid evolving landscape of programming frameworks and new protocols, deploying and testing AI agents as distributed systems remains a daunting and labor-intensive task. We present DMAS-Forge, a framework designed to close this gap. DMAS-Forge decouples application logic from specific deployment choices, and aims at transparently generating the necessary glue code and configurations to spawn distributed multi-agent applications across diverse deployment scenarios with minimal manual effort. We present our vision, design principles, and a prototype of DMAS-Forge. Finally, we discuss the opportunities and future work for our approach.