AgentOrchestrator

AgentOrchestrator: A powerful, production-grade framework for deploying AI agents anywhere - cloud, serverless, containers, or local development environments.

🚀 Quick Start (5 minutes)

Local Development

# Clone the repository
git clone https://github.com/your-username/AgentOrchestrator.git
cd AgentOrchestrator

# Set up environment with UV
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
uv pip install -e .

# Set up your .env file (copy from example)
cp .env.example .env

# Run the server
python main.py

Your server is now running at http://localhost:8000! 🎉

Using Docker (even faster)

# Clone the repository
git clone https://github.com/your-username/AgentOrchestrator.git
cd AgentOrchestrator

# Windows PowerShell
.\scripts\run_environments.ps1 -Environment dev -Build

# Linux/macOS
./scripts/run_environments.sh dev --build

The development environment will be available at http://localhost:8000.

🤖 Create Your First Agent (2 minutes)

1. Create a new directory in src/routes/my_first_agent/
2. Create a file ao_agent.py with this template:

from typing import Dict, Any
from langgraph.func import entrypoint, task
from langchain_google_genai import ChatGoogleGenerativeAI

model = ChatGoogleGenerativeAI(model="gemini-2.0-flash-exp")

@task
def generate_greeting(name: str) -> str:
    response = model.invoke(f"Generate a friendly greeting for {name}")
    return response.content

@entrypoint()
def run_workflow(name: str) -> Dict[str, Any]:
    greeting = generate_greeting(name).result()
    return {"greeting": greeting, "name": name}

3. Test your agent:

GET http://localhost:8000/api/v1/agent/my_first_agent?input=John

That's it! Your first AI agent is up and running.

🐳 Running Different Environments

AgentOrchestrator supports multiple environments through Docker:

# Windows PowerShell
# Development environment (hot-reloading)
.\scripts\run_environments.ps1 -Environment dev

# Testing environment (runs tests)
.\scripts\run_environments.ps1 -Environment test

# UAT environment (pre-production)
.\scripts\run_environments.ps1 -Environment uat

# Production environment
.\scripts\run_environments.ps1 -Environment prod

# Linux/macOS
# Development environment (hot-reloading)
./scripts/run_environments.sh dev

# Testing environment (runs tests)
./scripts/run_environments.sh test

# UAT environment (pre-production)
./scripts/run_environments.sh uat

# Production environment
./scripts/run_environments.sh prod

Access environments at:

• Development: http://localhost:8000
• UAT: http://localhost:8001
• Production: http://localhost:8000

For more details, see the Docker Environments Guide.

🔥 Key Features

• Deploy Anywhere: Cloud, serverless functions, containers or locally
• Stateless Architecture: Horizontally scalable with no shared state
• Flexible Agent System: Support for any LLM via LangChain, LlamaIndex, etc.
• Enterprise Ready: Authentication, rate limiting, caching, and metrics built-in
• Developer Friendly: Automatic API generation, hot-reloading, and useful error messages

🛣️ Roadmap

• Core framework
• Dynamic agent discovery
• API generation
• Agent marketplace
• Enterprise security features
• Managed cloud offering

📚 Documentation

• Getting Started Guide
• Creating Agents
• Deployment Options
• API Reference
• Docker Environments Guide
• Environment Management
• Examples

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

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

See our Contributing Guidelines for more information.

📄 License

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

🙏 Acknowledgements

• LangChain for the LLM integration tools
• FastAPI for the lightning-fast API framework
• UV for the modern Python package management