万Onexiang
中EN
p

py-xiaozhi

Lightweight cross-platform multimodal AI interaction framework supporting real-time voice, vision tasks, and IoT device control.

🇨🇳 DomesticFreeOpen sourceGeneral开源桌面操作多模态IoT支持
Platforms: DesktopSelf-hosted
Visit site ↗
Region
Domestic
Pricing
Free
Open source
Yes
GitHub Stars
★ 3.4k
Source
GitHub
Added
2026-06-11
Last verified
2026-06-11
GitHub
github.com/huangjunsen0406/py-xiaozhi

Overview

py-xiaozhi is a lightweight, cross-platform multimodal AI interaction framework built on Python's asynchronous architecture. It supports real-time voice streaming, vision-language tasks, and IoT device control. It can be deployed on Windows, macOS, Linux desktops, and ARM embedded platforms (such as Raspberry Pi), seamlessly connecting large language models with physical hardware. The framework offers multiple UI modes including PySide6 + QML GUI, CLI, and GPIO, suitable for desktop, headless server, and embedded environments. Additionally, it supports dual-protocol communication via WebSocket and MQTT, and features a plugin system for easy extension.

Key features

  • ▪Real-time voice AI with low latency
  • ▪Multimodal vision integration
  • ▪MCP tool ecosystem
  • ▪Cross-platform deployment
  • ▪Multiple UI modes
  • ▪Offline wake words

Use cases

Smart home controlRobotics controlMultimodal human-machine interactionEmbedded AI applications

Pros

  • ＋Low-latency real-time voice processing
  • ＋Multimodal support
  • ＋Cross-platform compatibility
  • ＋Rich plugin system

Limitations / notes

  • －Requires stable network connection
  • －Higher learning curve

Who it's for

DevelopersIoT engineersEmbedded systems engineersAI enthusiasts

This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.

FAQ

Is it free?

Yes, the project is open-source under the MIT license.

Does it support Chinese?

Yes, the project documentation includes a simplified Chinese version.

Can it be used commercially?

Yes, the MIT license allows commercial use.

Does it require internet connectivity?

Part of the functionality requires a stable network connection.

Similar agents

K

Kimi

Featured

Kimi is a long-context AI assistant by Moonshot AI

🇨🇳 DomesticFree + Paid
豆

豆包

Featured

AI assistant by ByteDance

🇨🇳 DomesticFree + Paid
D

DeepSeek

Featured

DeepSeek is a conversational assistant by DeepSeek

🇨🇳 DomesticFree
M

Manus

Featured

General-purpose autonomous agent capable of autonomously planning and completing complex tasks

🇨🇳 DomesticFree + Paid
C

ChatGPT Agent

Featured

A general-purpose agent from OpenAI capable of operating browsers and computers

🌍 OverseasFree + Paid
A

AutoGPT

One of the earliest autonomous Agents, open-source

🌍 OverseasFreeOpen source

Something wrong? Let us know on the About page and we'll fix it.