AI Agent Project

A full-stack AI agent application with a React frontend and Node.js backend services. The project includes an intelligent agent with various tools (currency conversion, weather, news) and a separate code execution service.

🏗️ Project Structure

AIAgent/
├── client/                 # React frontend application
│   ├── src/
│   ├── public/
│   ├── package.json
│   └── vite.config.ts
└── server/
    ├── agent/             # AI agent service with tools
    │   ├── agent.js
    │   ├── demo/          # Demo scripts
    │   ├── tools/         # Agent tools (currency, weather, news)
    │   └── package.json
    └── executor/          # Code execution service
        ├── index.js
        └── package.json

🚀 Getting Started

Prerequisites

• Node.js (v16 or higher)
• npm or yarn package manager

Installation

1. Clone the repository

   git clone <repository-url>
   cd AIAgent

2. Install dependencies for all services

   Client (React app):

   cd client
   npm install

   Agent service:

   cd server/agent
   npm install

   Executor service:

   cd server/executor
   npm install

3. Environment Setup

   Create a .env file in the server/agent directory with your required environment variables:

   cd server/agent
   touch .env

   Add your API keys and configuration variables to the .env file.

🏃‍♂️ Running the Application

1. Start the Executor Service

cd server/executor
node index.js

✅ Server will be running on port 3000

2. Start the Agent Service

cd server/agent
node --env-file=.env index.js

✅ Server will be running on port 3001

3. Start the Client Application

cd client
npm run dev

✅ Frontend will be available at the URL shown in terminal (typically http://localhost:5173)

🧪 Testing the Backend

You can test the AI agent service using curl:

curl -X POST http://localhost:3001/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt":"convert 5 USD to PKR","thread_id":123}'

Example API Calls

Currency Conversion:

curl -X POST http://localhost:3001/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt":"convert 100 EUR to USD","thread_id":456}'

Weather Information:

curl -X POST http://localhost:3001/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt":"What is the weather like in New York?","thread_id":789}'

🛠️ Available Tools

The AI agent comes with several built-in tools:

• 🔄 Currency Tool (currencyTool.js) - Real-time currency conversion
• 🌤️ Weather Tool (weatherTool.js) - Weather information and forecasts
• 📰 News Tool (newsTool.js) - Latest news and updates
• ⚡ JavaScript Executor (jsExecutor.js) - Execute JavaScript code safely

📁 Key Components

• server/agent/agent.js - Main AI agent logic and tool integration
• server/agent/index.js - Agent service server and API endpoints
• server/executor/index.js - Code execution service
• client/src/App.tsx - Main React application component

🔧 Development

Demo Scripts

The project includes demo scripts in server/agent/demo/:

• basicLLM.js - Basic language model interaction
• addingTools.js - Tool integration examples
• addingMemory.js - Memory management examples

Run demos:

cd server/agent
node demo/basicLLM.js

API Endpoints

Agent Service (Port 3001):

• POST /generate - Generate AI responses with tool usage

Executor Service (Port 3000):

• Available for code execution requests

🚨 Troubleshooting

1. Port conflicts: Make sure ports 3000, 3001, and 5173 are available
2. Environment variables: Ensure all required API keys are set in .env
3. Dependencies: Run npm install in each service directory if modules are missing
4. CORS issues: Check that the frontend URL is allowed in backend CORS settings

📝 Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

Happy coding! 🎉