Amazon Bedrock Agents: Architecture Diagrams
Diagrams of AgentCore Runtime, the managed harness, Memory, Gateway and Identity, Strands multi-agent patterns, and Bedrock Agents Classic orchestration, action groups and sessions.
How the pieces fit together. Each diagram links to the page that covers it in detail.
AgentCore
Section titled “AgentCore”Runtime request flow
Section titled “Runtime request flow”One runtimeSessionId maps to one microVM. Reusing the ID returns to the same microVM and its in-process state until the idle timeout or maximum lifetime ends the session (AgentCore guide).
caller (app, other agent, MCP/A2A client) │ InvokeAgentRuntime(arn, qualifier, runtimeSessionId, payload) │ auth: SigV4 (IAM) or Bearer JWT (customJWTAuthorizer) ▼┌──────────────────────────────────────────────────────────────┐│ AgentCore Runtime ││ endpoint "prod" ──► v4 endpoint DEFAULT ──► latest ││ ││ ┌─ session microVM (one per runtimeSessionId) ───────────┐ ││ │ your code: BedrockAgentCoreApp on port 8080 │ ││ │ GET /ping Healthy or HealthyBusy │ ││ │ POST /invocations @app.entrypoint(payload, context)│ ││ │ or an MCP server (/mcp) or A2A server (port 9000) │ ││ └──────────────┬──────────────┬──────────────┬───────────┘ │└──────────────────┼──────────────┼──────────────┼─────────────┘ ▼ ▼ ▼ Bedrock models AgentCore Gateway, Code (InvokeModel) Memory Interpreter, Browser │ └── spans, logs, metrics ──► CloudWatch (Observability)Harness or code-defined agent
Section titled “Harness or code-defined agent” ┌──────────────── AgentCore Runtime ─────────────────┐ InvokeHarness ───► │ managed harness │ (messages, │ harness.yaml: model, system prompt, tools, │ per-call │ skills, memory, limits, lifecycle hooks │ overrides) │ AWS runs the agent loop │ │ │ InvokeAgent ───► │ code-defined agent │ Runtime │ your container or zip: Strands, LangGraph, │ (payload) │ CrewAI, OpenAI Agents SDK... you own the loop │ └────────────────────────────────────────────────────┘
agentcore add harness ──► managed harness (harness.yaml) agentcore add runtime / --template ──► code-defined runtime agentcore export harness ──► harness converted to Strands code agentcore add runtime --agent-id ──► Agents Classic agent converted to codeSee Managed harness.
Memory
Section titled “Memory”Short-term memory is the raw event log. Long-term records are extracted from it asynchronously by the strategies you enable, and stored under namespaces scoped by actor (and optionally session).
agent turn │ add_turns(...) (CreateEvent: memory_id, actor_id, session_id, messages) ▼┌──────────────────────────┐ async extraction ┌─────────────────────────────┐│ short-term: events │ ───────────────────► │ long-term: memory records ││ per actor + session │ strategies: │ /users/{actorId}/facts ││ expire after N days │ SEMANTIC │ /users/{actorId}/... │└──────────────────────────┘ USER_PREFERENCE │ /summaries/{actorId}/{sid} │ ▲ list_events SUMMARIZATION └──────────────┬──────────────┘ │ (recent turns) EPISODIC │ │ search_long_term_memories(namespace_path, query) └──────────── agent context for next turn ◄───────────────────┘With Strands, AgentCoreMemorySessionManager makes these calls for you (Strands guide).
Gateway and Identity
Section titled “Gateway and Identity” inbound auth (JWT or IAM) agent ──── MCP over HTTP ────► ┌──────────────────────────┐ (MCPClient(url=gatewayUrl)) │ AgentCore Gateway │ │ tools/list, tools/call │ │ semantic tool search │ │ optional Cedar policies │ └───┬─────────┬─────────┬──┘ outbound creds: │IAM role │ OAuth / │ API key ▼ ▼ ▼ Lambda fn OpenAPI / MCP server, Smithy API knowledge base
AgentCore Identity inbound: user JWT ──► Runtime/Gateway authorizer ──► workload access token outbound: workload token ──► token vault ──► OAuth token or API key for a tool (@requires_access_token, @requires_api_key)See Integration patterns and Identity.
Deployment with the CLI
Section titled “Deployment with the CLI” agentcore/agentcore.json ─┐ agentcore/aws-targets.json├─► agentcore deploy --target prod app/<Agent>/ (code) ┘ │ ▼ CDK app (agentcore/cdk) ──► CloudFormation stack │ ┌─────────────┬───────────┼────────────┬──────────────┐ ▼ ▼ ▼ ▼ ▼ IAM execution Runtime + Memory Gateway + Online eval role endpoints targets configs (CodeZip bundle, or a container image in ECR)See the production guide.
Strands multi-agent patterns
Section titled “Strands multi-agent patterns” agents as tools swarm graph (GraphBuilder) ─────────────── ───── ──────────────────── supervisor ┌──────────┐ handoff ┌───────┐ collect ─► validate ─┬─► analyse ─► report │ │ │researcher│────────►│analyst│ ▲ │ ▼ ▼ └──────────┘ └───┬───┘ └── FAIL (bounded)┘ sales billing ▲ handoff │ .as_tool() .as_tool() └───────────── reviewer ──► answer model decides one agent active at a time; edges with conditions; ready which to call shared context, handoff tool nodes run in parallelSee the Strands guide and multi-agent patterns.
Bedrock Agents Classic
Section titled “Bedrock Agents Classic”These cover Agents Classic, which has been in maintenance mode since 30 July 2026.
Orchestration and action groups
Section titled “Orchestration and action groups” invoke_agent(agentId, agentAliasId, sessionId, inputText, sessionState) │ ▼┌─ Bedrock Agents (managed) ─────────────────────────────────────────┐│ pre-processing (optional) ─► orchestration loop ─► post-processing ││ │ model reasons, picks an action ││ ┌────────────────┼──────────────────┐ ││ ▼ ▼ ▼ ││ action group: action group: knowledge base ││ Lambda executor RETURN_CONTROL Retrieve (vector store) ││ │ │ ││ ▼ │ guardrail on input and output ││ your Lambda fn │ ││ (messageVersion 1.0 │ ││ response envelope) │ │└──────────────────────────────┼─────────────────────────────────────┘ ▼ completion stream: returnControl event your app runs the call, then invoke_agent again with sessionState.returnControlInvocationResultsSessions and memory
Section titled “Sessions and memory”Agents Classic keeps the conversation inside the service. You don’t provide a database for it.
sessionId ──► session context held by Bedrock Agents kept until idleSessionTTLInSeconds passes with no calls sessionAttributes (passed to action-group Lambdas) promptSessionAttributes (added to the prompt)
memoryConfiguration (optional, SESSION_SUMMARY) at session end ──► summary stored per memoryId, kept storageDays next session with the same memoryId ──► summaries added to contextSee the Classic reference.
Multi-agent collaboration
Section titled “Multi-agent collaboration” ┌─────────────────────────────┐ user ─────────► │ supervisor agent │ │ agentCollaboration: │ │ SUPERVISOR (plans) │ │ SUPERVISOR_ROUTER (routes)│ └───┬─────────────┬───────────┘ │ associate_agent_collaborator (alias ARN, instruction) ▼ ▼ collaborator collaborator agent alias agent alias (own action groups and knowledge bases)