#16 · Primary category: AI Chatbots
xiaozhi-esp32
An MCP-based chatbot
Project last updated:08/28/26
GitHub Stars
29.4K
Forks
6.8K
Contributors
142
License
MIT
Why we included this project
XiaoZhi turns an ESP32 board into a hands-free voice assistant that talks to large language models like Qwen and DeepSeek. The full voice loop runs on-device: offline wake-word detection, streaming speech recognition, LLM reasoning, and text-to-speech. Through the MCP protocol, the assistant can also control connected hardware such as speakers and displays, and add camera input on supported boards, so it is more than a chat window. The project supports a wide range of ESP32 chips and networking options, including Wi-Fi, Ethernet, and 4G, which makes it adaptable to different board designs. For hobbyists and product teams building a smart speaker or a voice-controlled gadget, this is a working reference implementation to build on.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
NextChat
✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
gpt4free
The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3
system_prompts_leaks
Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs