An intelligent AI agent that can send emails and make phone calls using natural language. Built with LlamaIndex and GPT-4o-mini.
- 📧 Send Emails - Send emails via Gmail integration (Arcade)
- 📞 Make Phone Calls - Place voice calls with custom scripts (Vapi)
- 🤖 AI-Powered - Uses GPT-4o-mini for intelligent task planning
- 🔗 REST API - FastAPI server for easy integration
- 🐳 Docker Ready - Containerized deployment included
pip install -r requirements.txt
pip install fastapi uvicorn # For API serverCreate a .env file with your API keys:
python3 setup_keys.pyOr manually create .env:
OPENAI_API_KEY=your_openai_key
ARCADE_API_KEY=your_arcade_key
VAPI_API_KEY=your_vapi_key
Option A: Direct Usage
python3 agent.pyOption B: API Server (Recommended)
python3 api_server.pyThen visit: http://localhost:8000/docs
Option C: Interactive Python
from agent import chat
chat("Send an email to test@example.com with subject 'Hello'")Start the server:
python3 api_server.pySend a request:
curl -X POST "http://localhost:8000/chat" \
-H "Content-Type: application/json" \
-d '{"message": "Send an email to test@example.com"}'# Quick test
python3 test_agent.py
# Full test suite
python3 test_suite.pyaiagent/
├── agent.py # Main agent (core logic)
├── api_server.py # FastAPI REST API
├── test_agent.py # Quick test script
├── test_suite.py # Comprehensive tests
├── setup_keys.py # Interactive API key setup
├── requirements.txt # Dependencies
├── Dockerfile # Docker config
└── docker-compose.yml # Docker Compose setup
docker-compose up -d- Deployment Guide - Detailed deployment instructions
- Setup Guide - API key setup help
- OpenAI: https://platform.openai.com/api-keys
- Arcade: https://arcade.chat (for Gmail integration)
- Vapi: https://vapi.ai (for voice calls)
- LlamaIndex - Agent orchestration
- OpenAI GPT-4o-mini - AI reasoning
- FastAPI - REST API framework
- Arcade - Gmail integration
- Vapi - Voice call platform
MIT License - Feel free to use and modify!
Simple, powerful, and ready to use**