Skip to content

Architecture Variants

The seven-layer model is stable, but implementations can be small, enterprise-governed, local/private, or workflow-specific. These variants show which layers are mandatory and where teams usually add controls.

Minimal Demo Stack

Use this when the goal is learning, local testing, or documentation examples.

LayerMinimal implementation
DiscoveryLocal Agent Card and registry artifact
IdentityLocal dev token with scoped JWT claims
APIsFastAPI REST endpoints and OpenAPI contract
Agent ProtocolsMCP-shaped tools and A2A-shaped message/send
MemoryDeterministic corpus with modeled vector and graph config
ModelsStatic model-routing policy, no external provider
ApplicationsLiterature review workflow requiring human review

Enterprise Governed Stack

Use this when agents cross team or organizational boundaries.

  • Discovery uses signed or approved Agent Cards plus private registries.
  • Identity uses enterprise OIDC, scoped delegation, policy gateways, and audit.
  • APIs preserve OpenAPI contracts and compatibility rules.
  • MCP and A2A traffic passes through gateways with validation and logging.
  • Memory enforces data classification, retention, and tenant boundaries.
  • Models are routed through approved gateways with usage and cost controls.
  • Applications require evaluation suites, incident review, and human override.

Local or Private Stack

Use this when data residency, network isolation, or cost control dominates.

  • Discovery and registries stay inside a private network.
  • Identity uses local or enterprise identity providers.
  • APIs, tools, memory, and models run on controlled infrastructure.
  • Local inference and local vector or graph stores are preferred.
  • External calls require explicit approval and traceable policy decisions.

Research Workflow Stack

Use this when the primary artifact is a cited analysis, report, review, or decision memo.

  • Discovery identifies approved research agents and document sources.
  • Identity preserves the researcher, tenant, and allowed collections.
  • APIs expose document search, document retrieval, and draft creation.
  • MCP tools provide controlled access to sources.
  • A2A delegates the literature-review task to a specialized agent.
  • Memory combines semantic retrieval with graph expansion.
  • Models draft content, but the application requires human review before sharing.

Page created by Dr. C. Klukas