
ai agent app
一个全栈应用,使用LangChain的ReAct代理和SSE实现AI代理实时流式聊天。
Repository Info
About This Server
一个全栈应用,使用LangChain的ReAct代理和SSE实现AI代理实时流式聊天。
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
AI Agent Chat Service
A full-stack application for AI agent chat with real-time streaming responses using LangChain's ReAct agent and Server-Sent Events (SSE).
!AI Agent Chat Service
Features
- Real-time Streaming Responses: See the AI's thinking process and responses as they're generated
- ReAct Agent Integration: Utilizes LangChain's ReAct agent for reasoning and action capabilities
- Tool Integration: Includes tools for web search, fetching content, and more
- Session Management: Create and manage multiple chat sessions
- Model Selection: Choose from different language models
- Responsive UI: Works on desktop and mobile devices
- Docker Containerization: Easy deployment with Docker Compose
Quick Start
Prerequisites
- Docker and Docker Compose
- OpenRouter API key (or other LLM provider)
- Brave API key (for web search tool)
Installation
-
Clone the repository:
git clone https://github.com/yourusername/ai-agent-chat.git cd ai-agent-chat -
Create a
.envfile in the root directory:OPENROUTER_API_KEY=your_openrouter_api_key BRAVE_API_KEY=your_brave_api_key -
Build and start the containers:
docker-compose up -d -
Access the application at http://localhost:3000
Documentation
Comprehensive documentation is available in the docs directory:
- User Guide - Instructions for using the application
- Developer Guide - Guide for developers working on the project
- API Reference - Detailed API documentation
- Documentation Index - Overview of all documentation
Architecture
The application consists of the following components:
graph TD
A[Web UI - React Native Web] -->|HTTP/SSE| B[Server - Fastify]
B -->|API Calls| C[OpenRouter API]
B -->|Uses| D[LangChain ReAct Agent]
B -->|Stores| E[MongoDB]
F[MCP Servers] -->|Provide Tools| B
subgraph "MCP Servers"
G[Time Server]
H[Fetch Server]
I[Brave Search Server]
end
F --- G
F --- H
F --- I
Project Structure
.
├── docker-compose.yaml # Docker Compose configuration
├── README.md # Project overview
├── docs/ # Documentation
├── src/
│ ├── common/ # Shared code between server and web-ui
│ │ ├── components/ # Shared React components
│ │ ├── types/ # TypeScript type definitions
│ │ └── utils/ # Utility functions
│ └── containers/
│ ├── server/ # Backend server
│ │ ├── src/ # Server source code
│ │ ├── Dockerfile
│ │ └── package.json
│ └── web-ui/ # Frontend application
│ ├── src/ # Web UI source code
│ ├── Dockerfile
│ └── package.json
Development
Local Development
Server
cd src/containers/server
npm install
npm run dev
Web UI
cd src/containers/web-ui
npm install
npm start
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Quick Start
Clone the repository
git clone https://github.com/passive-radio/ai-agent-appInstall dependencies
cd ai-agent-app
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.