Skip to main content
Ready to build your own bot? The Pipecat CLI scaffolds complete projects tailored to your platform and use case.
New to Pipecat? We recommend completing the Quickstart first to understand Pipecat basics before scaffolding your own project.

​
Install the Pipecat CLI

Install the CLI globally with uv: 
uv tool install "pipecat-ai[cli]"
Verify installation: 
pipecat --version
If you’re using an AI coding assistant (Claude Code, Codex, …), make your project agent-ready with pipecat init and let the agent do the building — it follows Pipecat conventions, scaffolds the app for you, and verifies its own work. The full workflow lives on Build with a Coding Agent.

Build with a Coding Agent

Make your project agent-ready, add the Pipecat Context Hub, and let the agent build

​
Scaffold it yourself

Prefer to drive the CLI directly? Run the interactive setup wizard: 
pipecat create
The CLI will guide you through selecting your platform (phone or web/mobile), transport provider, AI services (STT, LLM, TTS), and deployment target. To skip the prompts and scaffold the canned quickstart project, run pipecat create quickstart.

CLI Reference

See detailed options and generated project structure

​
Next Steps

Once pipecat create completes, the CLI will provide specific instructions for your generated project, including:
  • How to configure your API keys
  • Installing dependencies
  • Running your bot locally
  • Customizing the bot logic and behavior
Follow the instructions displayed by the CLI to get your bot up and running!

​
Deploy to Production

Ready to deploy your bot? Choose between managed cloud hosting or self-hosted infrastructure.

Pipecat Cloud

Deploy and manage your agents with the CLI - purpose-built for Pipecat

Self-Hosted Options

Deploy to Fly.io, Modal, AWS, or your own infrastructure

​
Learn More

Core Concepts

Understand pipelines, processors, and transports

Browse Examples

30+ production-ready examples for inspiration