An MCP-based chatbot | 一个基于MCP的聊天机器人
XiaoZhi is an open-source, MCP-based voice chatbot firmware written in C++ for ESP32 microcontrollers (ESP32-C3, ESP32-S3, and ESP32-P4), designed to run on over 70 supported hardware platforms including M5Stack CoreS3, Waveshare ESP32-S3-Touch-AMOLED, and LILYGO T-Circle-S3. The firmware connects to large language models such as Qwen and DeepSeek through a streaming ASR plus LLM plus TTS pipeline, enabling real-time voice interaction with offline wake-word detection via ESP-SR and speaker recognition via 3D-Speaker. MCP operates on two levels: a device-side layer that controls onboard hardware like speakers, LEDs, servos, and GPIO pins, and a cloud-side layer that extends model capabilities to smart home control, PC desktop operation, knowledge search, and email. Communication runs over WebSocket or MQTT plus UDP using the OPUS audio codec, with OLED and LCD displays supporting emoji output. A notable detail is that wake words, fonts, emojis, and chat backgrounds can all be customized through an online web tool called the Custom Assets Generator. The project targets hardware hobbyists and embedded developers building DIY AI voice assistants.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/78/xiaozhi-esp32MCP Servers overview
# An MCP-based Chatbot
(English | [中文](README_zh.md) | [日本語](README_ja.md))
## Introduction
👉 [Human: Give AI a camera vs AI: Instantly finds out the owner hasn't washed hair for three days【bilibili】](https://www.bilibili.com/video/BV1bpjgzKEhd/)
👉 [Handcraft your AI girlfriend, beginner's guide【bilibili】](https://www.bilibili.com/video/BV1XnmFYLEJN/)
As a voice interaction entry, the XiaoZhi AI chatbot leverages the AI capabilities of large models like Qwen / DeepSeek, and achieves multi-terminal control via the MCP protocol.
<img src="docs/mcp-based-graph.jpg" alt="Control everything via MCP" width="320">
## Recent Updates
- The mainline now targets ESP-IDF v6.0 or later, with v6.0.2 as the preferred stable SDK. The previous 157-variant baseline was validated on ESP-IDF v6.0.1; the current matrix contains 171 variants, of which 170 support IDF 6.0.x and the ESP32-S31 variant requires IDF 6.1 or later.
- MQTT and BluFi cryptographic code has migrated to PSA Crypto. IDF 6 component splits and third-party dependency compatibility have also been addressed.
- Audio pipeline concurrency, MQTT/UDP packet validation, and release-matrix selection have been hardened.
- ESP-IDF v5.5 is retained only for documented legacy boards. ESP32-P4 Rev1 and Rev3 are both supported on IDF 6 with ESP-SR 2.4.7; see the [ESP-IDF 6.0 Migration Guide](docs/esp-idf-6-migration.md) for full compatibility and board-validation details.
### Features Implemented
- Wi-Fi, wired Ethernet, USB RNDIS, and ML307/EC801E or NT26 Cat.1 4G networking; supported boards can switch between Wi-Fi and 4G
- Offline voice wake-up with [ESP-SR](https://github.com/espressif/esp-sr), including customizable wake words
- Two communication transports: [WebSocket](docs/websocket.md) and [MQTT + UDP](docs/mqtt-udp.md)
- Opus audio streaming with conventional streaming ASR + LLM + TTS pipelines and Realtime end-to-end voice models; AEC-capable hardware supports realtime full-duplex interaction
- Speaker recognition, identifies the current speaker [3D Speaker](https://github.com/modelscope/3D-Speaker)
- OLED / LCD displays with emoji and rich expression support, plus camera vision input on supported boards
- Battery display and power management
- 38 interface languages, with localized voice prompts where available and English fallback
- ESP32, ESP32-C3, ESP32-C5, ESP32-C6, ESP32-S3, and ESP32-P4 chip platforms
- Wi-Fi provisioning through hotspot or BluFi
- Device-side MCP for device control (Speaker, LED, Servo, GPIO, etc.)
- Cloud-side MCP to extend large model capabilities (smart home control, PC desktop operation, knowledge search, email, etc.)
- Customizable wake words, fonts, emojis, and chat backgrounds with online web-based editing ([Custom Assets Generator](https://github.com/78/xiaozhi-assets-generator))
## Hardware
### Breadboard DIY Practice
See the Feishu document tutorial:
👉 ["XiaoZhi AI Chatbot Encyclopedia"](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb?from=from_copylink)
Breadboard demo:

### Supports 138 Board Directories and 171 Release Variants (Partial List)
- <a href="https://oshwhub.com/li-chuang-kai-fa-ban/li-chuang-shi-zhan-pai-esp32-s3-kai-fa-ban" target="_blank" title="LiChuang ESP32-S3 Development Board">LiChuang ESP32-S3 Development Board</a>
- <a href="https://github.com/espressif/esp-box" target="_blank" title="Espressif ESP32-S3-BOX-3">Espressif ESP32-S3-BOX-3</a>
- <a href="https://docs.m5stack.com/zh_CN/core/CoreS3" target="_blank" title="M5Stack CoreS3">M5Stack CoreS3</a>
- <a href="https://docs.m5stack.com/en/atom/Atomic%20Echo%20Base" target="_blank" title="AtomS3R + Echo Base">M5Stack AtomS3R + Echo Base</a>
- <a href="https://gf.bilibili.com/item/detail/1108782064" target="_blank" title="Magic Button 2.4">Magic Button 2.4</a>
- <a href="https://www.waveshare.net/shop/ESP32-S3-Touch-AMOLED-1.8.htm" target="_blank" title="Waveshare ESP32-S3-Touch-AMOLED-1.8">Waveshare ESP32-S3-Touch-AMOLED-1.8</a>
- <a href="https://github.com/Xinyuan-LilyGO/T-Circle-S3" target="_blank" title="LILYGO T-Circle-S3">LILYGO T-Circle-S3</a>
- <a href="https://oshwhub.com/tenclass01/xmini_c3" target="_blank" title="XiaGe Mini C3">XiaGe Mini C3</a>
- <a href="https://oshwhub.com/movecall/cuican-ai-pendant-lights-up-y" target="_blank" title="Movecall CuiCan ESP32S3">CuiCan AI Pendant</a>
- <a href="https://github.com/WMnologo/xingzhi-ai" target="_blank" title="WMnologo-Xingzhi-1.54">WMnologo-Xingzhi-1.54TFT</a>
- <a href="https://www.seeedstudio.com/SenseCAP-Watcher-W1-A-p-5979.html" target="_blank" title="SenseCAP Watcher">SenseCAP Watcher</a>
- <a href="https://www.bilibili.com/video/BV1BHJtz6E2S/" target="_blank" title="ESP-HI Low Cost Robot Dog">ESP-HI Low Cost Robot Dog</a>
<div style="display: flex; justify-content: space-between;">
<a href="docs/v1/lichuang-s3.jpg" target="_blank" title="LiChuang ESP32-S3 Development Board">
<img src="docs/v1/lichuang-s3.jpg" width="240" />
</a>
<a href="docs/v1/espbox3.jpg" target="_blank" title="Espressif ESP32-S3-BOX3">
<img src="docs/v1/espbox3.jpg" width="240" />
</a>
<a href="docs/v1/m5cores3.jpg" target="_blank" title="M5Stack CoreS3">
<img src="docs/v1/m5cores3.jpg" width="240" />
</a>
<a href="docs/v1/atoms3r.jpg" target="_blank" title="AtomS3R + Echo Base">
<img src="docs/v1/atoms3r.jpg" width="240" />
</a>
<a href="docs/v1/magiclick.jpg" target="_blank" title="Magic Button 2.4">
<img src="docs/v1/magiclick.jpg" width="240" />
</a>
<a href="docs/v1/waveshare.jpg" target="_blank" title="Waveshare ESP32-S3-Touch-AMOLED-1.8">
<img src="docs/v1/waveshare.jpg" width="240" />
</a>
<a href="docs/v1/lilygo-t-circle-s3.jpg" target="_blank" title="LILYGO T-Circle-S3">
<img src="docs/v1/lilygo-t-circle-s3.jpg" width="240" />
</a>
<a href="docs/v1/xmini-c3.jpg" target="_blank" title="XiaGe Mini C3">
<img src="docs/v1/xmini-c3.jpg" width="240" />
</a>
<a href="docs/v1/movecall-cuican-esp32s3.jpg" target="_blank" title="CuiCan">
<img src="docs/v1/movecall-cuican-esp32s3.jpg" width="240" />
</a>
<a href="docs/v1/wmnologo_xingzhi_1.54.jpg" target="_blank" title="WMnologo-Xingzhi-1.54">
<img src="docs/v1/wmnologo_xingzhi_1.54.jpg" width="240" />
</a>
<a href="docs/v1/sensecap_watcher.jpg" target="_blank" title="SenseCAP Watcher">
<img src="docs/v1/sensecap_watcher.jpg" width="240" />
</a>
<a href="docs/v1/esp-hi.jpg" target="_blank" title="ESP-HI Low Cost Robot Dog">
<img src="docs/v1/esp-hi.jpg" width="240" />
</a>
</div>
## Software
### Firmware Flashing
For beginners, it is recommended to use the firmware that can be flashed without setting up a development environment.
The firmware connects to the official [xiaozhi.me](https://xiaozhi.me) server by default. Personal users can register an account to use the Qwen real-time model for free.
👉 [Beginner's Firmware Flashing Guide](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS)
### Development Environment
- Cursor or VSCode
- Install the ESP-IDF plugin. [ESP-IDF v6.0.2](https://github.com/espressif/esp-idf/releases/tag/v6.0.2) is preferred; use a stable v6.0 or later release. ESP-IDF v5.5.2 is retained only for legacy board compatibility
- Linux is better than Windows for faster compilation and fewer driver issues
- This project uses Google C++ code style, please ensure compliance when submitting code
### Developer Documentation
- [ESP-IDF 6.0 Migration Guide](docs/esp-idf-6-migration.md) - SDK compatibility, component changes, legacy hardware support, and board validation status
- [Custom Board Guide](docs/custom-board.md) - Learn how to create custom boards for XiaoZhi AI
- [MCP Protocol IoT Control Usage](docs/mcp-usage.md) - Learn how to control IoT devices via MCP protocol
- [MCP Protocol Interaction Flow](docs/mcp-protocol.md) - Device-side MCP protocol implementation
- [MQTT + UDP Hybrid Communication Protocol Document](docs/mqtt-udp.md)
- [A detailed WebSocket communication protocol document](docs/websocket.md)
## Large Model Configuration
If you already have a XiaoZhi AI chatbot device and have connected to the official server, you can log in to the [xiaozhi.me](https://xiaozhi.me) console for configuration.
👉 [Backend Operation Video Tutorial (Old Interface)](https://www.bilibili.com/video/BV1jUCUY2EKM/)
## Related Open Source Projects
For server deployment on personal computers, refer to the following open-source projects:
- [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) Python server
- [joey-zhou/xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) Java server
- [AnimeAIChat/xiaozhi-server-go](https://github.com/AnimeAIChat/xiaozhi-server-go) Golang server
- [hackers365/xiaozhi-esp32-server-golang](https://github.com/hackers365/xiaozhi-esp32-server-golang) Golang server
Other client projects using the XiaoZhi communication protocol:
- [huangjunsen0406/py-xiaozhi](https://github.com/huangjunsen0406/py-xiaozhi) Python client
- [TOM88812/xiaozhi-android-client](https://github.com/TOM88812/xiaozhi-android-client) Android client
- [100askTeam/xiaozhi-linux](http://github.com/100askTeam/xiaozhi-linux) Linux client by 100ask
- [78/xiaozhi-sf32](https://github.com/78/xiaozhi-sf32) Bluetooth chip firmware by Sichuan
- [QuecPython/solution-xiaozhiAI](https://github.com/QuecPython/solution-xiaozhiAI) QuecPython firmware by Quectel
Custom Assets Tools:
- [78/xiaozhi-assets-generator](https://github.com/78/xiaozhi-assets-generator) Custom Assets Generator (Wake words, fonts, emojis, backgrounds)
## About the Project
This is an open-source ESP32 project, released under the MIT license, allowing anyone to use it for free, including for commercial purposes.
We hope this project helps everyone understand AI hardware development and apply rapidly evolving large language models to real hardware deWhat people ask about xiaozhi-esp32
What is 78/xiaozhi-esp32?
+
78/xiaozhi-esp32 is mcp servers for the Claude AI ecosystem. An MCP-based chatbot | 一个基于MCP的聊天机器人 It has 28.4k GitHub stars and was last updated today.
How do I install xiaozhi-esp32?
+
You can install xiaozhi-esp32 by cloning the repository (https://github.com/78/xiaozhi-esp32) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is 78/xiaozhi-esp32 safe to use?
+
Our security agent has analyzed 78/xiaozhi-esp32 and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains 78/xiaozhi-esp32?
+
78/xiaozhi-esp32 is maintained by 78. The last recorded GitHub activity is from today, with 647 open issues.
Are there alternatives to xiaozhi-esp32?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy xiaozhi-esp32 to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/78-xiaozhi-esp32)<a href="https://claudewave.com/repo/78-xiaozhi-esp32"><img src="https://claudewave.com/api/badge/78-xiaozhi-esp32" alt="Featured on ClaudeWave: 78/xiaozhi-esp32" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!