Skip to content

Layer Model

The reference architecture is organized into seven layers. Each layer can evolve independently, but the layers should remain easy to compose.

Use the Architecture Overview for the canonical diagram and Technology Stack for common implementation technologies.

LayerNamePurposeInitial Examples
7ApplicationsUser-facing and organization-facing agent workflowsResearch agents, coding agents, enterprise agents
6ModelsHosted and local language model providersOpenAI, Gemini, Claude, Ollama, llama.cpp, vLLM
5MemoryLong-term, semantic, and structured knowledgeVector databases, knowledge graphs
4Agent ProtocolsAgent-to-tool and agent-to-agent interoperabilityMCP, A2A
3APIsDeterministic application and system interfacesREST, GraphQL, OpenAPI
2IdentityAuthentication, authorization, delegation, and policyOAuth2, OpenID Connect, JWT
1DiscoveryMachine-readable service and agent discoveryAgent Cards, robots.txt, sitemap.xml, OpenAPI

Layer Responsibilities

Layer 1: Discovery

Agents need predictable ways to find services, understand capabilities, and locate machine-readable metadata.

Layer 2: Identity

Agents need secure ways to act on behalf of users, organizations, or service accounts while preserving permissions and auditability.

Layer 3: APIs

Agents need stable system interfaces that can be inspected, called, tested, and governed.

Layer 4: Agent Protocols

Agents need protocols for tools, resources, prompts, capability exchange, task delegation, and multi-agent collaboration.

Layer 5: Memory

Agents need durable retrieval systems for semantic search, RAG, entity relationships, and historical context.

Layer 6: Models

Agents need model access through provider-neutral abstractions that allow hosted and local models to be swapped or combined.

Layer 7: Applications

Applications compose the lower layers into useful workflows for research, software engineering, operations, and enterprise automation.

Page created by Dr. C. Klukas