Agent Runtime

Run agents, teams, and workflows using FastAPI.

AgentOS is the FastAPI for agents. It serves agents as an API, an MCP server, and through chat interfaces like Slack, Telegram, and WhatsApp. Here’s the simplest possible example:

workbench.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.os import AgentOS
from agno.tools.workspace import Workspace

workbench = Agent(
    name="Workbench",
    model="openai:gpt-5.5",
    db=SqliteDb(db_file="workbench.db"),  # session storage
    tools=[Workspace(".")],               # read/write in this directory
    add_history_to_context=True,          # add past 3 runs to context
)

# Serve via AgentOS, get streaming, session isolation, API endpoints
agent_os = AgentOS(
    agents=[workbench],
    tracing=True,
    scheduler=True,
    mcp_server=True,
    db=SqliteDb(db_file="workbench.db"),
)
app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="workbench:app", reload=True)

AgentOS covers the valley of death between an agent definition and a live service. It gives agents a durable runtime, multi-user RBAC, background execution, checkpointing, session management, tracing, evals, guardrails, and more.

Build agents, teams, and workflows with the Agno SDK. Run them with AgentOS. Manage and monitor them using the Control Plane.

What the runtime gives you

The runtime covers the ground between your agent code and a production service:

Concern	How AgentOS handles it
HTTP API	Auto-generated endpoints for every registered agent, team, and workflow
Persistence	Sessions and enabled memory features persist to your db
Streaming	Run endpoints support SSE; tokens and tool calls stream when stream=true
Auth	Set authorization=True and configure a JWT verification key to enforce RBAC scopes
Scheduling	Set scheduler=True to poll the database and fire due jobs in process
Observability	Set tracing=True to write OpenTelemetry traces to the AgentOS database
Interfaces	Slack, Telegram, WhatsApp, A2A, AG-UI
Human in the loop	Pause runs for user confirmation, admin approval, or external execution

Explore

Agent API

Run your agent platform as an API.

Agent Storage

Add durability and persistence.

Observability

Tracing, run history, and audit logs in your own database.

Security and Auth

JWT validation, RBAC scopes, and per-request isolation.

Scheduling

In-process cron and multi-step workflows.

Interfaces

Reach users on Slack, Telegram, WhatsApp, A2A, and AG-UI.