Claude Code's multi-agent system lets you orchestrate multiple AI agents that work in parallel across isolated git worktrees, communicate directly with each other, and merge their results back into your codebase — all from a single terminal session. This is not a theoretical capability. It is production-ready infrastructure that ships with Claude Code today, and an experimental agent teams feature that takes coordination further. This guide covers every agent pattern available, when to use each one, and the practical configurations that make parallel AI coding work reliably.
The Core Primitive: AgentTool
Every multi-agent capability in Claude Code flows through a single abstraction called AgentTool. AgentTool is the orchestrator that spawns, manages, and routes communication between agents. It supports five distinct agent types, each optimized for different coordination patterns:
Sync subagents — blocking execution, parent waits for child to finish
Async agents — background execution, parent gets notified on completion
