Skip to content
runward
runward
Product
Who it is for
Trust
Documentation
News
Try it on an example Talk to us

Docs · The doctrine · Section 05

Runtime topology of an agentic system

Stripped of its stack, a running agentic system always keeps the same silhouette. Its components are stable; only their language and their partitioning vary, according to the preceding sections.

Runtime diagram

User / external client ENTRY POINT · interface, API, or tool protocol ORCHESTRATOR plan-and-execute loop · budget · plan · narration · events delegates calls a tool Sub-agent isolated context · own budget restricted tool scope TOOL REGISTRY + MIDDLEWARE log · access · metrics cost · approval MODEL portgateway3 tiers PERSIST. portstore / state EXEC. portsidecar viaprotocol SOURCE portinputs TOOL SERVERexposed(to external) Internal model infra(governance, observability) Specialized sidecar(stateful, circuit breaker) CROSS-CUTTING OBSERVABILITY · logs · events · lineage · metrics · cost

Reading the diagram

  • Orchestrator: drives the loop, plans, delegates, synthesizes. It contains no business logic; it composes.
  • Tool registry plus middleware: the single surface through which logging, access control, metrics, cost, and approvals pass. Adding a guardrail happens here, without touching the tools. It is also from here that a single trace stream is emitted, consumed separately by provenance, evaluation, and observability. This surface carries only cross-cutting concerns, never orchestration or business logic: it is the guard against the pitfall of the bloated integration bus of service-oriented architectures, where the channel ends up deciding the business. The logic stays in the tools and the orchestrator; the channel that connects them remains thin, and the registry remains an index, not a brain.
  • Secondary ports: model (via a gateway that centralizes governance and tier-based routing), persistence, execution (often a specialized sidecar), input sources.
  • Exposed tool server: the system publishes its use cases as standardized tools, so it can be driven by an external orchestrator without copying logic.
  • Cross-cutting observability: every step leaves a trace usable after the fact, and that trace feeds continuous evaluation, not just a dashboard.

The sidecar as a recurring pattern

A specialized capability (for example an execution engine driven by another language) runs in a session-scoped sidecar, consumed via the tool protocol. The sidecar is treated as an external dependency: health monitored, circuit breaker in case of unavailability, documented restart procedure. The rest of the system keeps running in degraded mode if the sidecar goes down.

The registry, a port with two adapters

Discovering which tools and which sub-agents are available is, like everything else, an adapter decision. As long as everything lives in a single process, the registry is a simple in-memory table, atomic and free. As soon as a capability moves out of the process, comes from another language, or from another team, the same port switches to a service discovery adapter: each agent publishes a self-describing capability card, discovered via a shared registry, by announce and subscribe with a local cache, never by a central call at every iteration. The discovery contract does not change; only the adapter changes with the topology.

Talk to us

Tell us who you are, and we will get back to you.

Your details are recorded by Another Framework, publisher of runward, to get back to you. They are neither sold nor shared, and are deleted three years after our last exchange. To see or delete them: contact@runward.dev.