---
title: Multi-agent patterns | Letta Docs
description: Build multi-agent systems with message passing, shared memory, and coordination patterns.
---

Letta supports multi-agent coordination patterns that combine role-specific agents, tagging, and shared state via [shared memory blocks](/guides/core-concepts/memory/shared-memory/index.md).

## Coordination styles

Most multi-agent systems in Letta use one or more of these coordination styles:

- **Delegation**: A coordinator routes work to specialized agents.
- **Parallelization**: Multiple agents work on parts of a task concurrently.
- **Synthesis**: A coordinator combines outputs into a final response.

These tutorials focus on architecture and coordination design, including role definitions, tag conventions, and shared memory strategy.

## Coordination patterns

Choose a pattern based on your use case:

[Supervisor-worker ](/tutorials/multi-agent/supervisor-worker/index.md)Coordinate specialized agents under a supervisor with tag-based routing.

[Parallel execution ](/tutorials/multi-agent/parallel-execution/index.md)Multiple agents analyze the same task from different perspectives.

[Round-robin ](/tutorials/multi-agent/round-robin/index.md)Distribute tasks evenly across agents in a rotating sequence.

[Producer-reviewer ](/tutorials/multi-agent/producer-reviewer/index.md)Iterative content refinement with feedback loops.

[Hierarchical teams ](/tutorials/multi-agent/hierarchical-teams/index.md)Multi-layer coordination with executives, managers, and workers.

## Related resources

- [Shared memory blocks](/guides/core-concepts/memory/shared-memory/index.md) - Share state between agents
- [Memory blocks overview](/guides/core-concepts/memory/memory-blocks/index.md) - Understanding core memory
- [Shared memory tutorial](/tutorials/shared-memory-blocks/index.md) - Step-by-step shared memory guide