1

Set Your OpenAI Key

Begin by setting your OpenAI API key.

from agency import set_openai_key
set_openai_key("YOUR_API_KEY")

Alternatively, you can set the API key in the .env file.

OPENAI_API_KEY=sk-...
2

Create Project Structure

Use the create-agent-template command to create the recommended directory structure for each agent.

Command Syntax:

agency-swarm create-agent-template --name "AgentName" --description "Agent Description" [--path "/path/to/directory"] [--use_txt]

Agent Folder Structure:

When you run the create-agent-template command, it creates the following folder structure for your agent:

/your-agency-path/
└── AgentName/                    # Directory for the specific agent
    ├── files/                    # Directory for files that will be uploaded to openai
    ├── schemas/                  # Directory for OpenAPI schemas to be converted into tools
    ├── tools/                    # Directory for tools to be imported by default.
    ├── AgentName.py              # The main agent class file
    ├── __init__.py               # Initializes the agent folder as a Python package
    └── instructions.md or .txt   # Instruction document for the agent

This structure ensures that each agent has its dedicated space with all necessary files to start working on its specific tasks.

Agency Folder Structure:

The full structure of the project will look like this:

AgencyName/
├── AgentName/            # Agent folder created with the command above
├── AnotherAgent/         # Another agent folder
├── agency.py             # Main file where agents are imported and the agency is defined
├── agency_manifesto.md   # Shared instructions and guidelines for all agents
├── requirements.txt      # File listing all dependencies
└── ...
3

Create Tools

Define your custom tools by extending the BaseTool class and implementing the run method.

MyCustomTool.py:

from agency_swarm.tools import BaseTool
from pydantic import Field

class MyCustomTool(BaseTool):
    """
    A brief description of what the custom tool does.
    The docstring should clearly explain the tool's purpose and functionality.
    It will be used by the agent to determine when to use this tool.
    """

    # Define the fields with descriptions using Pydantic Field
    example_field: str = Field(
        ..., description="Description of the example field, explaining its purpose and usage for the Agent."
    )

    # Additional Pydantic fields as required
    # ...

    def run(self):
        """
        The implementation of the run method, where the tool's main functionality is executed.
        This method should utilize the fields defined above to perform the task.
        Doc string is not required for this method and will not be used by your agent.
        """

        # Your custom tool logic goes here
        do_something(self.example_field)

        # Return the result of the tool's operation as a string
        return "Result of MyCustomTool operation"
4

Define Agent Roles

Adjust the parameters and instructions for each agent.

Developer.py:

from agency_swarm import Agent

class Developer(Agent):
    def __init__(self):
        super().__init__(
            name="Developer",
            description="Responsible for executing tasks.",
            instructions="./instructions.md",
            files_folder="./files",
            schemas_folder="./schemas",
            tools_folder="./tools",
            temperature=0.3,
            max_prompt_tokens=25000,
            examples=[]
        )

Tools will be imported automatically from the tools folder.

instructions.md:

You are a Developer agent responsible for executing tasks.

# Role
You are responsible for writing clean, efficient, and reusable code.

# Process
1. How to handle incoming requests
2. When and how to use available tools
3. How to collaborate with other agents
5

Create Agency

Import your agents and initialize the Agency class.

agency.py:

from agency_swarm import Agency
from .Developer import Developer
from .CEO import CEO

developer = Developer()
ceo = CEO()

agency = Agency(
    [
        ceo,  # CEO will be the entry point for communication with the user
        [ceo, developer],  # CEO can initiate communication with Developer
    ],
    shared_instructions='./agency_manifesto.md'  # shared instructions for all agents
)

Any agents that are listed in the same list (e.g., [[ceo, developer]]) can communicate with each other. The top-level list ([ceo]) defines agents that can communicate with the user.

In Agency Swarm, communication flows are directional, meaning they are established from left to right in the agency_chart definition. For instance, in the example above, the CEO can initiate a chat with the Developer (developer), and the Developer can respond in this chat. However, the Developer cannot initiate a chat with the CEO.

6

Run Demo

There are three ways to run the demo. Add one of the following lines to your agency.py file:

Web Interface:

agency.demo_gradio(height=900)

Terminal Version:

agency.run_demo()

Backend Version:

completion_output = agency.get_completion("Please create a new website for our client.", yield_messages=False)

​
Next Steps