Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.pipecat.ai/llms.txt

Use this file to discover all available pages before exploring further.

Pipecat Subagents is a distributed multi-agent framework for Pipecat. Each agent runs its own pipeline and communicates with other agents through a shared message bus. The programming model stays the same whether agents run locally in a single process or distributed across machines.

Quickstart

Build a multi-agent voice bot with agent handoff in under 10 minutes

​
What You Can Build

Agent Handoff

Specialized agents that transfer control seamlessly during a conversation.

Parallel Workers

Dispatch work to multiple agents in parallel and collect their results.

Mixed Agent Types

Combine free-form LLM agents with structured Flows agents in the same system.

Custom Voices

Give each agent its own TTS voice so users hear a different voice when transferred to a different agent.

Distributed Agents

Run agents across separate processes or machines, sharing the same bus and scaling each independently.

Proxy Agents

Connect agents on different buses for point-to-point communication.

​
Installation

uv add pipecat-ai-subagents
Optional extras: 
uv add "pipecat-ai-subagents[flows]"      # Pipecat Flows integration
uv add "pipecat-ai-subagents[redis]"       # Redis bus for distributed setups
uv add "pipecat-ai-subagents[websocket]"   # WebSocket proxy agents
Requires Python 3.11+ and pipecat-ai.

​
Next Steps

Quickstart

Build a multi-agent voice bot with agent handoff

Learn the Concepts

Walk through agents, the bus, handoff, and task coordination step by step

Fundamentals

Deep dives into the bus bridge, tools, Flows, distributed setups, and more

Examples

Complete working examples for every pattern