#2424th of 48 in Agent frameworks and SDKs
pipecat
Python framework for real-time voice and multimodal agent pipelines
- Stars
- 16.3k
- License
- BSD-2-Clause
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Pipecat is a Python framework that chains speech-to-text, LLM, text-to-speech and speech-to-speech services into streaming pipelines, with WebSocket and WebRTC transports. It also supports multi-agent setups with handoff, parallel fan-out and a shared bus, locally or distributed. A CLI scaffolds and deploys projects, and client SDKs cover JavaScript, React, Swift, Kotlin, C++ and ESP32.
Who it is for: Python developers building real-time voice or multimodal agents
Strengths
- Many pluggable services: 23 STT, 25 LLM and 30+ TTS providers listed, including local Whisper and Ollama
- Official client SDKs for JS, React, React Native, Swift, Kotlin, C++ and ESP32
- Structured conversation flows (Pipecat Flows) built in, plus Whisker debugger and Tail dashboard
- Multi-agent support: handoff, parallel fan-out and distributed deployment over a shared bus
Weaknesses
- Library, not a ready app: you write Python pipeline code to get a working bot
- Most listed STT, LLM and TTS services are hosted APIs needing separate keys
- No Docker or compose files detected in the repo
- Hardware requirements for local models are not stated in the visible README
What it needs
- GPU optional
- Needs Python, STT/LLM/TTS provider API keys (e.g. Deepgram, OpenAI, Cartesia, ElevenLabs), WebRTC/WebSocket transport
- Models: Whisper, Moonshine, Ollama, OpenAI, Anthropic
Also in Agent frameworks and SDKs
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 93 out of 100 |
| 2 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 88 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 87 out of 100 |