Pipecat

BSD-2 voice and multimodal realtime agents (Daily)

AI Agents / Agents · BSD-2-Clause · 16.6k

Reviewed 2026-09-15 · last push 2026-10-19 · repo checked 2026-10-19

What's Good

BSD-2-Clause (pipecat-ai/pipecat). Compose STT/LLM/TTS and media transports into low-latency voice agents; multi-agent handoff/fan-out; client SDKs (JS/React/RN/iOS/Android). `pipecat init quickstart`. Docs at docs.pipecat.ai. Framework is free OSS; bring your own model/telephony providers.

The Catch

Vs LiveKit Agents (already covered under LiveKit comms stack) and OpenAI Realtime / voice extras: Pipecat is the pipeline framework for voice agents, not the SFU product. Daily transport/cloud and third-party STT/TTS meters when you leave local mocks. Not a text-only MCP orchestrator.

Verdict

BSD-2 realtime voice-agent framework. Pipelines you own; media/model meters separate.

Embed

Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.

Markdown

[![Reviewed on Stack Gems](https://stackgems.com/badge/pipecat.svg)](https://stackgems.com/gems/pipecat)

HTML

<a href="https://stackgems.com/gems/pipecat"><img src="https://stackgems.com/badge/pipecat.svg" alt="Pipecat reviewed on Stack Gems" height="20"></a>

AI Agents →

Related