[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-10643":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":30,"readmeContent":31,"aiSummary":32,"trendingCount":16,"starSnapshotCount":16,"syncStatus":33,"lastSyncTime":34,"discoverSource":35},10643,"xiaozhi-esp32","78\u002Fxiaozhi-esp32","78","An MCP-based chatbot | 一个基于MCP的聊天机器人","https:\u002F\u002Fxiaozhi.me",null,"C++",27240,6066,211,587,0,27,226,895,147,120,"MIT License",false,"main",true,[27,28,29],"chatbot","esp32","mcp","2026-06-12 04:00:51","# An MCP-based Chatbot\n\n(English | [中文](README_zh.md) | [日本語](README_ja.md))\n\n## Introduction\n\n👉 [Human: Give AI a camera vs AI: Instantly finds out the owner hasn't washed hair for three days【bilibili】](https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1bpjgzKEhd\u002F)\n\n👉 [Handcraft your AI girlfriend, beginner's guide【bilibili】](https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1XnmFYLEJN\u002F)\n\nAs a voice interaction entry, the XiaoZhi AI chatbot leverages the AI capabilities of large models like Qwen \u002F DeepSeek, and achieves multi-terminal control via the MCP protocol.\n\n\u003Cimg src=\"docs\u002Fmcp-based-graph.jpg\" alt=\"Control everything via MCP\" width=\"320\">\n\n## Version Notes\n\nThe current v2 version is incompatible with the v1 partition table, so it is not possible to upgrade from v1 to v2 via OTA. For partition table details, see [partitions\u002Fv2\u002FREADME.md](partitions\u002Fv2\u002FREADME.md).\n\nAll hardware running v1 can be upgraded to v2 by manually flashing the firmware.\n\nThe stable version of v1 is 1.9.2. You can switch to v1 by running `git checkout v1`. The v1 branch will be maintained until February 2026.\n\n### Features Implemented\n\n- Wi-Fi \u002F ML307 Cat.1 4G\n- Offline voice wake-up [ESP-SR](https:\u002F\u002Fgithub.com\u002Fespressif\u002Fesp-sr)\n- Supports two communication protocols ([Websocket](docs\u002Fwebsocket.md) or MQTT+UDP)\n- Uses OPUS audio codec\n- Voice interaction based on streaming ASR + LLM + TTS architecture\n- Speaker recognition, identifies the current speaker [3D Speaker](https:\u002F\u002Fgithub.com\u002Fmodelscope\u002F3D-Speaker)\n- OLED \u002F LCD display, supports emoji display\n- Battery display and power management\n- Multi-language support (Chinese, English, Japanese)\n- Supports ESP32-C3, ESP32-S3, ESP32-P4 chip platforms\n- Device-side MCP for device control (Speaker, LED, Servo, GPIO, etc.)\n- Cloud-side MCP to extend large model capabilities (smart home control, PC desktop operation, knowledge search, email, etc.)\n- Customizable wake words, fonts, emojis, and chat backgrounds with online web-based editing ([Custom Assets Generator](https:\u002F\u002Fgithub.com\u002F78\u002Fxiaozhi-assets-generator))\n\n## Hardware\n\n### Breadboard DIY Practice\n\nSee the Feishu document tutorial:\n\n👉 [\"XiaoZhi AI Chatbot Encyclopedia\"](https:\u002F\u002Fccnphfhqs21z.feishu.cn\u002Fwiki\u002FF5krwD16viZoF0kKkvDcrZNYnhb?from=from_copylink)\n\nBreadboard demo:\n\n![Breadboard Demo](docs\u002Fv1\u002Fwiring2.jpg)\n\n### Supports 70+ Open Source Hardware (Partial List)\n\n- \u003Ca href=\"https:\u002F\u002Foshwhub.com\u002Fli-chuang-kai-fa-ban\u002Fli-chuang-shi-zhan-pai-esp32-s3-kai-fa-ban\" target=\"_blank\" title=\"LiChuang ESP32-S3 Development Board\">LiChuang ESP32-S3 Development Board\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fespressif\u002Fesp-box\" target=\"_blank\" title=\"Espressif ESP32-S3-BOX3\">Espressif ESP32-S3-BOX3\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fdocs.m5stack.com\u002Fzh_CN\u002Fcore\u002FCoreS3\" target=\"_blank\" title=\"M5Stack CoreS3\">M5Stack CoreS3\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fdocs.m5stack.com\u002Fen\u002Fatom\u002FAtomic%20Echo%20Base\" target=\"_blank\" title=\"AtomS3R + Echo Base\">M5Stack AtomS3R + Echo Base\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fgf.bilibili.com\u002Fitem\u002Fdetail\u002F1108782064\" target=\"_blank\" title=\"Magic Button 2.4\">Magic Button 2.4\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fwww.waveshare.net\u002Fshop\u002FESP32-S3-Touch-AMOLED-1.8.htm\" target=\"_blank\" title=\"Waveshare ESP32-S3-Touch-AMOLED-1.8\">Waveshare ESP32-S3-Touch-AMOLED-1.8\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FXinyuan-LilyGO\u002FT-Circle-S3\" target=\"_blank\" title=\"LILYGO T-Circle-S3\">LILYGO T-Circle-S3\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Foshwhub.com\u002Ftenclass01\u002Fxmini_c3\" target=\"_blank\" title=\"XiaGe Mini C3\">XiaGe Mini C3\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Foshwhub.com\u002Fmovecall\u002Fcuican-ai-pendant-lights-up-y\" target=\"_blank\" title=\"Movecall CuiCan ESP32S3\">CuiCan AI Pendant\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FWMnologo\u002Fxingzhi-ai\" target=\"_blank\" title=\"WMnologo-Xingzhi-1.54\">WMnologo-Xingzhi-1.54TFT\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fwww.seeedstudio.com\u002FSenseCAP-Watcher-W1-A-p-5979.html\" target=\"_blank\" title=\"SenseCAP Watcher\">SenseCAP Watcher\u003C\u002Fa>\n- \u003Ca href=\"https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1BHJtz6E2S\u002F\" target=\"_blank\" title=\"ESP-HI Low Cost Robot Dog\">ESP-HI Low Cost Robot Dog\u003C\u002Fa>\n\n\u003Cdiv style=\"display: flex; justify-content: space-between;\">\n  \u003Ca href=\"docs\u002Fv1\u002Flichuang-s3.jpg\" target=\"_blank\" title=\"LiChuang ESP32-S3 Development Board\">\n    \u003Cimg src=\"docs\u002Fv1\u002Flichuang-s3.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fespbox3.jpg\" target=\"_blank\" title=\"Espressif ESP32-S3-BOX3\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fespbox3.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fm5cores3.jpg\" target=\"_blank\" title=\"M5Stack CoreS3\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fm5cores3.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fatoms3r.jpg\" target=\"_blank\" title=\"AtomS3R + Echo Base\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fatoms3r.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fmagiclick.jpg\" target=\"_blank\" title=\"Magic Button 2.4\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fmagiclick.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fwaveshare.jpg\" target=\"_blank\" title=\"Waveshare ESP32-S3-Touch-AMOLED-1.8\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fwaveshare.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Flilygo-t-circle-s3.jpg\" target=\"_blank\" title=\"LILYGO T-Circle-S3\">\n    \u003Cimg src=\"docs\u002Fv1\u002Flilygo-t-circle-s3.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fxmini-c3.jpg\" target=\"_blank\" title=\"XiaGe Mini C3\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fxmini-c3.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fmovecall-cuican-esp32s3.jpg\" target=\"_blank\" title=\"CuiCan\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fmovecall-cuican-esp32s3.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fwmnologo_xingzhi_1.54.jpg\" target=\"_blank\" title=\"WMnologo-Xingzhi-1.54\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fwmnologo_xingzhi_1.54.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fsensecap_watcher.jpg\" target=\"_blank\" title=\"SenseCAP Watcher\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fsensecap_watcher.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fv1\u002Fesp-hi.jpg\" target=\"_blank\" title=\"ESP-HI Low Cost Robot Dog\">\n    \u003Cimg src=\"docs\u002Fv1\u002Fesp-hi.jpg\" width=\"240\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n## Software\n\n### Firmware Flashing\n\nFor beginners, it is recommended to use the firmware that can be flashed without setting up a development environment.\n\nThe firmware connects to the official [xiaozhi.me](https:\u002F\u002Fxiaozhi.me) server by default. Personal users can register an account to use the Qwen real-time model for free.\n\n👉 [Beginner's Firmware Flashing Guide](https:\u002F\u002Fccnphfhqs21z.feishu.cn\u002Fwiki\u002FZpz4wXBtdimBrLk25WdcXzxcnNS)\n\n### Development Environment\n\n- Cursor or VSCode\n- Install ESP-IDF plugin, select SDK version 5.4 or above\n- Linux is better than Windows for faster compilation and fewer driver issues\n- This project uses Google C++ code style, please ensure compliance when submitting code\n\n### Developer Documentation\n\n- [Custom Board Guide](docs\u002Fcustom-board.md) - Learn how to create custom boards for XiaoZhi AI\n- [MCP Protocol IoT Control Usage](docs\u002Fmcp-usage.md) - Learn how to control IoT devices via MCP protocol\n- [MCP Protocol Interaction Flow](docs\u002Fmcp-protocol.md) - Device-side MCP protocol implementation\n- [MQTT + UDP Hybrid Communication Protocol Document](docs\u002Fmqtt-udp.md)\n- [A detailed WebSocket communication protocol document](docs\u002Fwebsocket.md)\n\n## Large Model Configuration\n\nIf you already have a XiaoZhi AI chatbot device and have connected to the official server, you can log in to the [xiaozhi.me](https:\u002F\u002Fxiaozhi.me) console for configuration.\n\n👉 [Backend Operation Video Tutorial (Old Interface)](https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1jUCUY2EKM\u002F)\n\n## Related Open Source Projects\n\nFor server deployment on personal computers, refer to the following open-source projects:\n\n- [xinnan-tech\u002Fxiaozhi-esp32-server](https:\u002F\u002Fgithub.com\u002Fxinnan-tech\u002Fxiaozhi-esp32-server) Python server\n- [joey-zhou\u002Fxiaozhi-esp32-server-java](https:\u002F\u002Fgithub.com\u002Fjoey-zhou\u002Fxiaozhi-esp32-server-java) Java server\n- [AnimeAIChat\u002Fxiaozhi-server-go](https:\u002F\u002Fgithub.com\u002FAnimeAIChat\u002Fxiaozhi-server-go) Golang server\n- [hackers365\u002Fxiaozhi-esp32-server-golang](https:\u002F\u002Fgithub.com\u002Fhackers365\u002Fxiaozhi-esp32-server-golang) Golang server\n\nOther client projects using the XiaoZhi communication protocol:\n\n- [huangjunsen0406\u002Fpy-xiaozhi](https:\u002F\u002Fgithub.com\u002Fhuangjunsen0406\u002Fpy-xiaozhi) Python client\n- [TOM88812\u002Fxiaozhi-android-client](https:\u002F\u002Fgithub.com\u002FTOM88812\u002Fxiaozhi-android-client) Android client\n- [100askTeam\u002Fxiaozhi-linux](http:\u002F\u002Fgithub.com\u002F100askTeam\u002Fxiaozhi-linux) Linux client by 100ask\n- [78\u002Fxiaozhi-sf32](https:\u002F\u002Fgithub.com\u002F78\u002Fxiaozhi-sf32) Bluetooth chip firmware by Sichuan\n- [QuecPython\u002Fsolution-xiaozhiAI](https:\u002F\u002Fgithub.com\u002FQuecPython\u002Fsolution-xiaozhiAI) QuecPython firmware by Quectel\n\nCustom Assets Tools:\n\n- [78\u002Fxiaozhi-assets-generator](https:\u002F\u002Fgithub.com\u002F78\u002Fxiaozhi-assets-generator) Custom Assets Generator (Wake words, fonts, emojis, backgrounds)\n\n## About the Project\n\nThis is an open-source ESP32 project, released under the MIT license, allowing anyone to use it for free, including for commercial purposes.\n\nWe hope this project helps everyone understand AI hardware development and apply rapidly evolving large language models to real hardware devices.\n\nIf you have any ideas or suggestions, please feel free to raise Issues or join our [Discord](https:\u002F\u002Fdiscord.gg\u002FC759fGMBcZ) or QQ group: 994694848\n\n## Star History\n\n\u003Ca href=\"https:\u002F\u002Fstar-history.com\u002F#78\u002Fxiaozhi-esp32&Date\">\n \u003Cpicture>\n   \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=78\u002Fxiaozhi-esp32&type=Date&theme=dark\" \u002F>\n   \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=78\u002Fxiaozhi-esp32&type=Date\" \u002F>\n   \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=78\u002Fxiaozhi-esp32&type=Date\" \u002F>\n \u003C\u002Fpicture>\n\u003C\u002Fa>","小智AI聊天机器人是一个基于MCP协议的智能对话系统，利用了Qwen\u002FDeepSeek等大型模型的AI能力。其核心功能包括通过Wi-Fi或4G进行联网、离线语音唤醒、支持WebSocket和MQTT+UDP两种通信协议、采用OPUS音频编码、基于流式ASR+LLM+TTS架构实现语音交互，并能够识别当前说话者。此外，它还支持OLED\u002FLCD屏幕显示表情符号、电池状态管理及多语言操作。该项目适用于需要智能家居控制、个人助手服务或者希望探索AI技术与硬件结合可能性的场景，如教育实验、DIY项目等。支持ESP32-C3, ESP32-S3, ESP32-P4等多种芯片平台以及超过70种开源硬件。",2,"2026-06-11 03:29:30","top_topic"]