Pipecat
Build AI agent workflows visually, deploy as public REST API instantly.
Pipecat is a visual AI agent workflow builder that lets users drag and connect LLM nodes, tool calls, and routing logic on a canvas without writing code. Workflows support real parallel execution, live streaming, and can be deployed as public REST API endpoints with a single click. It integrates with major LLMs like OpenAI, Anthropic, and Gemini, as well as tools like Gmail, HubSpot, and custom HTTP endpoints.
Users visually connect LLM, tool-call, and routing nodes on a canvas, then enable the workflow to receive a public REST API endpoint that can be invoked synchronously, asynchronously, or via SSE stream.
Developers and teams building and deploying AI agent workflows
Background.
- Status
- launched
- Business model
- freemium
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.