oflo-ai-agent-protocol 0.1.0

A protocol for building business AI agents with MCP integration

Oflo AI Agent Protocol

A powerful protocol for building business AI agents with seamless integration with MCP (Multi-Cloud Protocol), supporting multiple LLMs and multi-modal capabilities.

Features

• 🤖 Flexible Agent Architecture: Build custom AI agents with a standardized interface
• 🔌 MCP Integration: Seamless integration with Multi-Cloud Protocol
• 🧠 Multi-LLM Support: Works with OpenAI, Anthropic, and other LLM providers
• 📱 Multi-Modal: Handle text, images, and other data types
• 🏭 Agent Factory: Easy agent creation and management
• 🔄 State Management: Built-in memory and conversation history
• 🛠️ Tool Integration: Easy integration with external tools and APIs
• 🔒 Security: Built-in security features and best practices

Installation

pip install oflo-ai-agent-protocol

For development:

pip install oflo-ai-agent-protocol[dev]

For documentation:

pip install oflo-ai-agent-protocol[docs]

Quick Start

from oflo_agent_protocol import BaseAgent, Message

class MyAgent(BaseAgent):
    def __init__(self):
        super().__init__(name="MyAgent", purpose="A custom business agent")
        
    async def process_message(self, message: Message) -> Message:
        # Your custom message processing logic here
        return Message(role="assistant", content="Hello from MyAgent!")

# Create and initialize the agent
agent = MyAgent()
await agent.initialize()

# Process a message
response = await agent.process_message("Hello!")
print(response.content)  # Output: Hello from MyAgent!

Examples

Check out our example implementations:

• Ping Pong Agent: Simple example of agent communication
• Marketing Agent: AI agent for marketing tasks
• Sales Agent: AI agent for sales automation
• Revenue Agent: AI agent for revenue optimization
• Trader Agent: AI agent for trading strategies

Cloudflare Worker Deployment

Deploy your Oflo Agent as a Cloudflare Worker:

1. Install Wrangler:

npm install -g wrangler

2. Configure your worker:

cd examples/marketing-oflo/worker
wrangler dev  # For local development
wrangler publish  # For production deployment

Documentation

Full documentation is available at https://docs.oflo.ai/agent-protocol

Contributing

We welcome contributions! Please see our Contributing Guide for details.

License

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

Support

• 📚 Documentation
• 💬 Discord Community
• 🐦 Twitter
• 📧 Email Support