FAQ

How do I set my OpenAI API key in my project?

Set your API key in your code:

from agency_swarm import set_openai_key
set_openai_key("YOUR_API_KEY")

Or use a .env file:

OPENAI_API_KEY=sk-1234...

Then load it with:

from dotenv import load_dotenv
load_dotenv()

What's the difference between using .cursorrules (with Cursor IDE) and 'agency-swarm genesis'?

Can I use open source models with Agency Swarm?

How do I save and continue conversations?

To persist conversations between application restarts, implement callbacks that save and load the full message history from a local file. For example, define your callback functions:

import os
import json

def load_threads(chat_id: str) -> list[dict[str, TResponseInputItem]]:
    """Load all threads data for a specific chat session."""
    if os.path.exists(f"{chat_id}_threads.json"):
        with open(f"{chat_id}_threads.json", "r") as file:
            return json.load(file)
    return []

def save_threads(thread_dict: list[dict[str, TResponseInputItem]], chat_id: str):
    """Save all threads data to file."""
    with open(f"{chat_id}_threads.json", "w") as file:
        json.dump(thread_dict, file)

# Then, pass these callbacks during your agency initialization to resume conversations:
from agency_swarm import Agency
agency = Agency(
    agent,
    load_threads_callback=lambda: load_threads(chat_id),
    save_threads_callback=lambda thread_dict: save_threads(thread_dict, chat_id),
)

This setup preserves your conversation context between runs.

How do I manage multiple users with Agency Swarm?

How can I transfer data between tools and agents?

Why is the CodeInterpreter tool automatically added?

How can I serve an Agency as an API using FastAPI?

Embed your agency within a FastAPI endpoint:

from fastapi import FastAPI
from uuid import uuid4

app = FastAPI()

@app.post("/chat")
async def chat(user_request: UserRequest):
    chat_id = user_request.chat_id or str(uuid4())

    agency = Agency(
        agent,
        load_threads_callback=lambda: load_threads(chat_id),
        save_threads_callback=lambda thread_dict: save_threads(thread_dict, chat_id)
    )

    response = await agency.get_response(user_request.message)
    return {"chat_id": chat_id, "response": response.final_output}

# Or use the built-in FastAPI integration
agency.run_fastapi(host="0.0.0.0", port=8000)

How do I deploy my agency to production?

Getting Support

Community Support

Join our Discord community for quick help and discussions.

Professional Services

Get professional help with our Agents-as-a-Service subscription.

Welcome

Core Framework

Additional Features

References

Contributing

Migration

FAQ

Getting Support

Community Support

Professional Services

Welcome

Core Framework

Additional Features

References

Contributing

Migration

FAQ

​Getting Support

Community Support

Professional Services

Getting Support