A multi-agent human-computer interaction platform based on Model Context Protocol integrating real-time face recognition, Chinese speech recognition, speech synthesis, and a web interface for natural, interactive communication.
Unlock the full potential of MCP Agent Platform through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
这是一个基于多智能体架构的人机交互系统,集成了视觉识别、语音识别和语音合成等功能。系统由多个专门的智能体协同工作,实现了自然的人机交互体验。
This is a human-computer interaction system based on multi-agent architecture, integrating visual recognition, speech recognition, and speech synthesis capabilities. The system consists of multiple specialized agents working together to achieve a natural human-computer interaction experience.
系统由以下主要组件构成 / The system consists of the following main components:
大脑智能体 (Brain Agent)
视觉智能体 (Eye Agent)
听觉智能体 (Ear Agent)
发声智能体 (Mouth Agent)
人脸识别 / Face Recognition
语音交互 / Voice Interaction
Web界面 / Web Interface
git clone [repository-url] cd mcpTest
pip install -r requirements.txt
在config.py
中可以配置以下参数 / The following parameters can be configured in config.py
:
python main.py
http://localhost:8070
人脸识别 / Face Recognition
语音交互 / Voice Interaction
后端 / Backend
前端 / Frontend
├── config.py # 配置文件 / Configuration file
├── main.py # 主程序 / Main program
├── requirements.txt # 依赖清单 / Dependencies list
├── src/
│ ├── agents/ # 智能体实现 / Agent implementations
│ ├── brain/ # 大脑逻辑 / Brain logic
│ ├── platform/ # 平台核心 / Platform core
│ ├── utils/ # 工具函数 / Utility functions
│ └── web/ # Web服务 / Web service
├── static/ # 静态资源 / Static resources
└── templates/ # 页面模板 / Page templates
Discover shared experiences
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!