microsoft/multi-agent-reference-architecture
Guide for designing adaptive, scalable, and secure enterprise multi-agent systems
Covers agent orchestration patterns, inter-agent communication protocols, memory management across distributed agents, and governance mechanisms for multi-agent workflows. Built on production deployments with Microsoft customers, providing framework-agnostic guidance applicable across enterprise tech stacks. Includes detailed reference architecture alongside building blocks for agent registries, observability instrumentation, and security controls.
173 stars.
Stars
173
Forks
54
Language
Python
License
MIT
Category
Last pushed
Dec 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/microsoft/multi-agent-reference-architecture"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
awslabs/agent-squad
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
horizon-rl/strands-sglang
SGLang model provider for Strands Agents for on-policy agentic RL training.
rodmena-limited/stabilize
Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage...
jeremiah-k/agor
AgentOrchestrator - Multi-agent development coordination platform. Transform AI assistants into...
aws-solutions-library-samples/guidance-for-multi-agent-orchestration-on-aws
Enables developers to build, deploy, and manage multiple specialized agents that work together...