XiaoZhi ESP32

Active

Description

An MCP-based open-source chatbot for ESP32 embedded devices, supporting voice interaction, multi-model integration, and IoT control for building smart hardware agents.

Key Features

MCP protocol device control — Device-side MCP controls speaker, LED, servo, GPIO; cloud-side MCP extends to smart home, email, and more
Offline voice wake-up & recognition — ESP-SR offline wake-word detection, OPUS audio codec, streaming ASR + LLM + TTS architecture
70+ open-source hardware support — Compatible with ESP32-C3/S3/P4, LiChuang, ESP-BOX3, M5Stack, LILYGO and 70+ dev boards
Multi-language & multi-model — Supports Chinese/English/Japanese, connects to Qwen/DeepSeek, Websocket and MQTT+UDP dual protocols
Speaker recognition — Identifies current speaker via 3D Speaker model for personalized conversations
Online custom resources — Customize wake words, fonts, emojis, and chat backgrounds via web-based editor

Use Cases

💡 Smart home voice control — Voice-interact with smart lights, AC, and IoT devices via ESP32

💡 AI desktop assistant — Run LLM conversations on embedded devices for localized AI Q&A

💡 Education & maker projects — Breadboard DIY AI chatbot, learn embedded AI development

💡 Wearable device development — Build AI wearables with CuiCan AI Pendant and similar hardware

💡 Robot interaction control — Control robotic arms, robot dogs via MCP protocol

Strengths & Limitations

✅ Strengths

• Actively maintained, recent updates
• High community interest (29.6k stars)
• Permissive open-source license (MIT)
• Established track record (2 years in production)

Quick Start

# 1. Clone the project
git clone https://github.com/78/xiaozhi-esp32.git
cd xiaozhi-esp32

# 2. Install ESP-IDF SDK (v5.4+)
# See https://docs.espressif.com/projects/esp-idf/en/latest/esp32/get-started/

# 3. Build and flash firmware
idf.py set-target esp32s3
idf.py build
idf.py flash

# 4. Connect device to xiaozhi.me server and start using

Visit GitHub

Related Projects

MaxKB

22.7k · Python

Active A+

MaxKB is an open-source knowledge base Q&A and agent building platform powered by LLMs, with vector retrieval, workflow orchestration, and multi-model support out of the box.

knowledge-baseragchatbot +3

· RAG Pipeline — Document upload and online crawling with automatic splitting and vectorization to reduce hallucinations
· Agentic Workflow — Powerful workflow engine, function library and MCP tool-use for complex business scenarios
· Zero-code Integration — Seamlessly integrate into third-party business systems for smart Q&A capabilities

View full details → View on GitHub

Witsy

2.0k · TypeScript

Stale C

Witsy: desktop AI assistant and universal MCP client that connects to multiple AI models and tool services via the Model Context Protocol.

typescriptmcpagent +3

· Universal MCP client supporting any LLM provider including OpenAI, Anthropic, Google, Ollama, and more
· Prompt Anywhere feature generates content directly in any application via global keyboard shortcut
· AI Commands provide quick text-processing helpers (summarize, translate, rewrite) on selected text

View on GitHub

Better Chatbot

1.2k · TypeScript

Active A

A better chatbot platform powered by Agent, MCP, and Workflows. Supports multi-model integration, visual workflow orchestration, and low-code configuration.

mcpagentchatbot +5

· Multi-model support: integrates OpenAI, Anthropic, Google, xAI, Ollama, and all major LLMs
· MCP protocol driven: invoke browser automation, web search, code execution tools via @mention
· Visual workflow editor: drag-and-drop to build AI workflows and publish them as chat tools

View on GitHub

LangBot

17.6k · Python