FastAPI Integration

Agency Swarm supports serving your agencies and tools as production-ready HTTP APIs using FastAPI. This enables you to interact with your agents and tools over HTTP, integrate with other services, or connect it to web frontends.

Installation

FastAPI integration is an optional installation. To install all required dependencies, run:

pip install "agency-swarm[fastapi]"

Setting Up FastAPI Endpoints

You can expose your agencies and tools as API endpoints using the run_fastapi() function.

Example: Create an API endpoint for a single agency

from agency_swarm import Agency, Agent

agent = Agent(
    name="Assistant",
    instructions="You are a helpful assistant."
)

agency = Agency(agent, name="test_agency")

agency.run_fastapi()

run_fastapi parameters

Param	Type	Default	Description
`host`	string	`"0.0.0.0"`	Interface to bind the server.
`port`	integer	`8000`	Port to serve FastAPI on.
`app_token_env`	string	`"APP_TOKEN"`	Env var name for the bearer token; if missing, auth is disabled.
`return_app`	boolean	`false`	Return the FastAPI app instead of running the server.
`cors_origins`	list	`["*"]`	Allowed CORS origins.
`enable_agui`	boolean	`false`	Enable AG-UI streaming (hides the cancel endpoint).
`enable_logging`	boolean	`false`	Track requests and expose `/get_logs` at the server root.
`logs_dir`	string	`"activity-logs"`	Folder for request logs when logging is enabled.
`allowed_local_file_dirs`	list	`None`	Allowlist for local `file_urls`; paths outside the list are rejected.

Endpoint reference

Agencies are served at:
- /your_agency_name/get_response (POST)
- /your_agency_name/get_response_stream (POST, streaming responses)
- /your_agency_name/cancel_response_stream (POST; not registered when enable_agui=True)
- /your_agency_name/get_metadata (GET)
- /get_logs (GET; when enable_logging=True)
Tools registered via tools=[...] are available at /tool/ToolClassName (BaseTools) or /tool/function_name (function tools).
OpenAPI and interactive docs: /openapi.json, /docs, /redoc.

Response format

Non-streaming (/get_response):

{
  "response": "Hello! How can I help you today?",
  "new_messages": [
    {
      "type": "message",
      "role": "user",
      "content": [{"type": "input_text", "text": "Hello"}],
      "agent": "Assistant",
      "callerAgent": null,
      "timestamp": 1704067200000
    },
    {
      "type": "message",
      "role": "assistant",
      "content": [{"type": "output_text", "text": "Hello! How can I help you today?"}],
      "agent": "Assistant",
      "callerAgent": null,
      "timestamp": 1704067201000
    }
  ],
  "usage": {"input_tokens": 50, "output_tokens": 12, "total_cost": 0.0001},
  "file_ids_map": {"document.pdf": "file-abc123"}
}

Streaming (/get_response_stream):

event: meta
data: {"run_id": "550e8400-e29b-41d4-a716-446655440000"}

data: {"data": {"data": {"type": "response.output_text.delta", "delta": "Hello"}}}
data: {"data": {"data": {"type": "response.output_text.delta", "delta": "!"}}}

event: messages
data: {"new_messages": [...], "run_id": "...", "cancelled": false, "usage": {...}, "file_ids_map": {...}}

event: end
data: [DONE]

Cancel (/cancel_response_stream):

{
  "ok": true,
  "run_id": "550e8400-e29b-41d4-a716-446655440000",
  "cancelled": true,
  "cancel_mode": "immediate",
  "new_messages": [...]
}

Metadata (/get_metadata):

{
  "nodes": [
    {
      "id": "Assistant",
      "type": "agent",
      "data": {
        "label": "Assistant",
        "description": "Main assistant agent",
        "conversationStarters": ["Support: I need help with billing"],
        "isEntryPoint": true,
        "toolCount": 2,
        "tools": [{"name": "example_tool", "type": "function", "description": "..."}]
      }
    }
  ],
  "edges": [
    {"id": "CEO->Developer", "source": "CEO", "target": "Developer", "type": "communication"}
  ],
  "metadata": {
    "agencyName": "my_agency",
    "totalAgents": 2,
    "totalTools": 4,
    "agents": ["CEO", "Developer"],
    "entryPoints": ["CEO"]
  },
  "agency_swarm_version": "1.0.0"
}

Conversation starters appear under data.conversationStarters on each agent node when configured. See Conversation starters cache.Tool (/tool/<name>):

{
  "response": "Output returned by the tool"
}

Usage tracking

Responses include a usage object with token counts and cost by default. For streaming, the final event: messages payload includes the same usage object.To understand what’s inside usage, see Observability.Usage tracking is configured on the agent (not on FastAPI):

from agency_swarm import Agent, ModelSettings

agent = Agent(
    name="Assistant",
    instructions="You are a helpful assistant.",
    model_settings=ModelSettings(include_usage=False),
)

If you’re using LiteLLM models and want usage in streaming responses, keep include_usage=True.

Stream cancellation uses an in-memory registry per process. Use single-worker deployments (e.g., uvicorn workers=1) or sticky routing so cancel requests reach the same worker.

Authentication

Set the environment variable named by app_token_env (default APP_TOKEN) to require Authorization: Bearer <token> on every endpoint. When the variable is absent, authentication is disabled.

Implementation reference

Example: Serving Multiple Agencies and Tools

from agency_swarm import Agency, Agent, function_tool, run_fastapi

# Example tools using agents SDK
@function_tool
def example_tool(example_field: str) -> str:
    """Example tool with input field."""
    return f"Result of ExampleTool operation with {example_field}"

@function_tool
def test_tool(example_field: str) -> str:
    """Test tool with input field."""
    return f"Result of TestTool operation with {example_field}"

# Create agents
agent1 = Agent(name="Assistant1", instructions="You are assistant 1.")
agent2 = Agent(name="Assistant2", instructions="You are assistant 2.")

# Create agency factory functions for proper thread management
def create_agency_1(load_threads_callback=None, save_threads_callback=None):
    return Agency(
        agent1, 
        name="test_agency_1",
        load_threads_callback=load_threads_callback,
        save_threads_callback=save_threads_callback,
    )

def create_agency_2(load_threads_callback=None, save_threads_callback=None):
    return Agency(
        agent2, 
        name="test_agency_2",
        load_threads_callback=load_threads_callback,
        save_threads_callback=save_threads_callback,
    )

run_fastapi(
    agencies={
        "test_agency_1": create_agency_1,
        "test_agency_2": create_agency_2,
    },
    tools=[example_tool, test_tool],
)

Endpoints follow the reference above; tool schemas mirror the definitions of example_tool and test_tool.

API Usage Example

You can interact with your agents and tools using HTTP requests:

import requests

agency_url = "http://127.0.0.1:8000/test_agency_1/get_response"
payload = {
    "message": "Hello",
    "client_config": {
        "base_url": "https://my-openai-gateway.example.com/v1",
        "api_key": "sk-...",  # override per request
    },
}

headers = {
    "Authorization": "Bearer 123"  # Replace with your actual token if needed
}

agency_response = requests.post(agency_url, json=payload, headers=headers)
print("Status code:", agency_response.status_code)
print("Response:", agency_response.json())

Request payload

Field	Type	Required	Description
`message`	string	Yes	User message to start or continue the conversation.
`chat_history`	list	No	Flat list of prior messages with metadata (`agent`, `callerAgent`, `timestamp`) to preserve context.
`recipient_agent`	string	No	Target agent when you want to direct the next turn.
`file_ids`	list	No	IDs of already uploaded files to attach.
`file_urls`	object	No	`{filename: url_or_absolute_path}` map. Local paths require `allowed_local_file_dirs` on `run_fastapi`.
`additional_instructions`	string	No	Extra guidance for the current request.
`user_context`	object	No	Structured data passed to Agency Context without exposing it to the LLM.
`client_config`	object	No	Override `base_url` / `api_key` for this request (and optional `litellm_keys` for `litellm/` models).

How user_context is applied

Merges with any user_context set on the agency instance.
Useful for structured data (ids, preferences, feature flags) you do not want in the prompt.
Accessible within tools for the duration of the run. See Agency Context.

How client_config is applied

Applies only to OpenAI models (no prefix or openai/...) and LiteLLM models (litellm/...).
Custom Model subclasses are not modified; the request still runs, but the override is skipped.
For LiteLLM, you can provide litellm_keys to pass different keys per provider. Requires LiteLLM installed.

client_config fields

base_url (string, optional): Override the API base URL for this request.
api_key (string, optional): Override the API key for this request.
litellm_keys (object, optional): Only for litellm/... models.
- Map provider_name → api_key.
- Example: {"anthropic": "...", "gemini": "..."}

client_config examples

OpenAI model override (gpt-4o):

{
  "message": "Hello",
  "client_config": {
    "base_url": "https://my-openai-gateway.example.com/v1",
    "api_key": "sk-..."
  }
}

LiteLLM mixed providers (requires openai-agents[litellm]):

{
  "message": "Hello",
  "client_config": {
    "base_url": "https://my-litellm-proxy.example.com",
    "litellm_keys": {
      "anthropic": "sk-ant-...",
      "gemini": "AIza..."
    }
  }
}

Cancelling Active Streams

The streaming endpoint supports cancellation via two methods:

1. Automatic Cancellation on Disconnect

When a client disconnects (tab close, refresh, network failure), the stream is automatically cancelled to preserve token costs.

2. Cancel Endpoint

Call the cancel endpoint with the run_id received from the first event of the streaming response. This will allow you to retrieve intermediate results that were generated before the run cancellation. Optionally include cancel_mode (defaults to immediate):

immediate — stop right away and return messages that were fully generated; the in-progress message is discarded.
after_turn — finish the current turn, then stop.

import requests

# Cancel an active stream
cancel_url = "http://127.0.0.1:8000/test_agency/cancel_response_stream"
payload = {"run_id": "your-run-id", "cancel_mode": "after_turn"}  # cancel_mode is optional
response = requests.post(cancel_url, json=payload)
# Returns: {"ok": True, "run_id": "...", "cancelled": True, "cancel_mode": "after_turn", "new_messages": [...]}

Serving Standalone Tools

Expose tools as simple HTTP endpoints for external systems, webhooks, or other agents to call directly without agency orchestration.

from agency_swarm import BaseTool, run_fastapi

class Address(BaseTool):
    street: str
    zip_code: int

    def run(self) -> str:
        return f"{self.street} {self.zip_code}"

run_fastapi(tools=[Address], port=8080)

This creates:

POST /tool/Address — execute the tool
GET /openapi.json — full OpenAPI schema
GET /docs — interactive Swagger UI

Generate OpenAPI schema programmatically

Use ToolFactory.get_openapi_schema() to generate the OpenAPI spec programmatically:

from agency_swarm.tools import ToolFactory

schema = ToolFactory.get_openapi_schema(
    [Address],
    url="https://your-server.com",
    title="My Tools API"
)
print(schema)  # Returns a JSON string

File Attachments

Attach files to agency requests using file_ids or file_urls in the payload:

{
  "message": "Summarize this document",
  "file_urls": {"report.pdf": "https://example.com/report.pdf"}
}

The response includes file_ids_map with the uploaded file IDs:

{
  "response": "...",
  "file_ids_map": {"report.pdf": "file-abc123"}
}

Supported filetypes: .pdf, .jpeg, .jpg, .gif, .png, .c, .cs, .cpp, .csv, .html, .java, .json, .php, .py, .rb, .css, .js, .sh, .ts, .pkl, .tar, .xlsx, .xml, .zip, .doc, .docx, .md, .pptx, .tex, .txt

Local file paths

To support passing local filepaths in the file_urls field, set allowed_local_file_dirs on run_fastapi:

run_fastapi(agencies=..., allowed_local_file_dirs=["/data/uploads"])

Then pass absolute file paths in file_urls:

{"file_urls": {"doc.pdf": "/data/uploads/doc.pdf"}}

Invalid paths return an error field in the response body.

Welcome

Core Framework

Additional Features

References

Contributing

Migration

FAQ

Installation

Setting Up FastAPI Endpoints

Example: Create an API endpoint for a single agency

Authentication

Implementation reference

API Usage Example

How user_context is applied

How client_config is applied

client_config fields

Cancelling Active Streams

1. Automatic Cancellation on Disconnect

2. Cancel Endpoint

Serving Standalone Tools

File Attachments

Welcome

Core Framework

Additional Features

References

Contributing

Migration

FAQ

​Installation

​Setting Up FastAPI Endpoints

​Example: Create an API endpoint for a single agency

​Authentication

​Implementation reference

​API Usage Example

​How user_context is applied

​How client_config is applied

​client_config fields

​Cancelling Active Streams

​1. Automatic Cancellation on Disconnect

​2. Cancel Endpoint

​Serving Standalone Tools

​File Attachments

Installation

Setting Up FastAPI Endpoints

Example: Create an API endpoint for a single agency

Authentication

Implementation reference

API Usage Example

How user_context is applied

How client_config is applied

client_config fields

Cancelling Active Streams

1. Automatic Cancellation on Disconnect

2. Cancel Endpoint

Serving Standalone Tools

File Attachments