Sign in
All library
Library· Architecture

Multi-agent orchestration

Supervisor, hierarchical, swarm, and role-based topologies — plus when a single agent is still the right call.

#orchestration#patterns
6 min read

A multi-agent system splits work across specialized agents that communicate. Done well, it improves quality on complex tasks; done poorly, it multiplies your token bill and failure modes.

Common topologies

  • Supervisor / worker — one router picks which specialist to call. See LangGraph supervisor.
  • Hierarchical — supervisors of supervisors, useful for large codebases or research projects.
  • Swarm / peer-to-peer — agents hand off to each other with shared state (OpenAI Swarm, now productised in the OpenAI Agents SDK).
  • Role-based crewsCrewAI style, with defined roles, goals, and backstories.

Case studies

Rule of thumb

Start with a single agent + tools. Only split when a single prompt can't hold the required context or when tasks are genuinely parallelizable.