or run

npx @tessl/cli init
Log in

Version

Tile

Overview

Evals

Files

docs

agent.mdagentos.mdeval.mdexceptions.mdguardrails.mdindex.mdknowledge.mdmedia.mdmemory.mdmodels.mdsessions.mdstorage.mdteam.mdtools.mdworkflow.md
tile.json

agentos.mddocs/

AgentOS Runtime API

Production runtime with FastAPI server and control plane integration.

Capabilities

AgentOS Creation

from agno.os import AgentOS

class AgentOS:
    def __init__(
        self,
        *,
        agents: Optional[List[Agent]] = None,
        teams: Optional[List[Team]] = None,
        workflows: Optional[List[Workflow]] = None,
        name: Optional[str] = None,
        description: Optional[str] = None,
        version: str = "1.0.0",
        api_key: Optional[str] = None,
        enable_cors: bool = True,
        **kwargs
    ): ...

FastAPI App

def get_app(self) -> FastAPI:
    """
    Get the FastAPI application instance.
    
    Returns:
        FastAPI: The FastAPI app with all routes configured
    """

def serve(
    self,
    app: str,
    host: str = "0.0.0.0",
    port: int = 7777,
    reload: bool = False,
    **kwargs
) -> None:
    """
    Start the AgentOS server.
    
    Parameters:
        app: App path in module:app format
        host: Host address
        port: Port number
        reload: Enable auto-reload for development
        **kwargs: Additional uvicorn parameters
    """

Usage Examples

Basic AgentOS

from agno.agent import Agent
from agno.os import AgentOS
from agno.models.openai import OpenAIChat
from agno.db.sqlite import SqliteDb

# Create agents
agent = Agent(
    name="Assistant",
    model=OpenAIChat(id="gpt-4"),
    db=SqliteDb(db_file="agent.db"),
    add_history_to_context=True
)

# Create AgentOS
agent_os = AgentOS(
    agents=[agent],
    name="My AgentOS",
    version="1.0.0"
)

# Get FastAPI app
app = agent_os.get_app()

# Run server
if __name__ == "__main__":
    agent_os.serve(app="main:app", reload=True)

Multiple Agents

from agno.agent import Agent
from agno.os import AgentOS
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.yfinance import YFinanceTools

# Create multiple agents
research_agent = Agent(
    name="Researcher",
    model=OpenAIChat(id="gpt-4"),
    tools=[DuckDuckGoTools()]
)

finance_agent = Agent(
    name="Finance Analyst",
    model=OpenAIChat(id="gpt-4"),
    tools=[YFinanceTools()]
)

# Create AgentOS with multiple agents
agent_os = AgentOS(
    agents=[research_agent, finance_agent],
    name="Multi-Agent System"
)

app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="main:app", port=7777)

With Teams and Workflows

from agno.agent import Agent
from agno.team import Team
from agno.workflow import Workflow
from agno.os import AgentOS

# Create agents
agent1 = Agent(name="Agent 1", model=...)
agent2 = Agent(name="Agent 2", model=...)

# Create team
team = Team(
    name="Research Team",
    agents=[agent1, agent2]
)

# Create workflow
workflow = Workflow(
    name="Research Pipeline",
    steps=[...]
)

# Create AgentOS
agent_os = AgentOS(
    agents=[agent1, agent2],
    teams=[team],
    workflows=[workflow]
)

app = agent_os.get_app()

Connecting to Control Plane

Once the server is running, connect to the AgentOS UI at https://os.agno.com:

  1. Start your AgentOS server
  2. Visit https://os.agno.com
  3. Enter your server URL (e.g., http://localhost:7777)
  4. Chat with your agents, view session history, monitor metrics