What is AgentOS?

AgentOS is a FastAPI app that turns your agents into a platform. The backend service:

Runs agents via REST API, MCP, or interfaces like Slack, WhatsApp and Telegram.
Stores sessions, memory, knowledge, and traces in your configured databases.
Preserves database-backed state across restarts and replicas when all instances use the same persistent stores.
Supports JWT authorization, service account tokens, and security-key authentication.
Supports database-backed tracing for agents, teams, and workflows.

Build your agents using the Agno SDK. Run them using the AgentOS runtime. A minimal AgentOS:

agno_assist.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.anthropic import Claude
from agno.os import AgentOS

agent = Agent(
    name="Agno Assist",
    model=Claude(id="claude-sonnet-4-5"),
    db=SqliteDb(db_file="agno.db"),
)

agent_os = AgentOS(agents=[agent])
app = agent_os.get_app()

Authorization and tracing are disabled by default. Telemetry is enabled by default. Configure authentication before exposing AgentOS, and review Agno telemetry before deployment.

Key Features

Production API: 50+ ready to use endpoints with SSE-compatible streaming.
Data Ownership: Sessions, memory, knowledge, and traces stored in your configured databases.
Request Context: User and session IDs scope persisted runs. JWT user isolation can bind these IDs to authenticated callers.
Security: Optional JWT-based RBAC with hierarchical scopes, service account tokens, or a shared security key.
Observability: Optional traces stored in your database.
Governance: Guardrails, human-in-the-loop, and approval flows.
Multi-framework: Serve agents built with the Claude Agent SDK, LangGraph and DSPy alongside native Agno agents. See Multi-Framework Support.

Architecture

AgentOS has two parts:

Runtime: A FastAPI service that runs agents, teams, and workflows.
Control plane: A UI for managing, monitoring, and debugging your system.

The runtime exposes the APIs that power both the control plane and your AI products. The runtime can serve agents built with the Agno SDK, the Claude Agent SDK, LangGraph, or DSPy.

Data Flow and Storage

The AgentOS runtime runs in your infrastructure. Sessions, memory, knowledge, and enabled traces are stored in your configured databases. The control plane connects from your browser to the runtime. Network traffic depends on your configuration:

Destination	Data
Configured model and tool providers	Requests required by those providers and tools
`https://os-api.agno.com`	Usage metadata when telemetry is enabled. Prompts and responses are excluded.
Your AgentOS runtime	Control plane requests sent directly from the browser

AgentOS telemetry is enabled by default. Set telemetry=False on AgentOS to disable its launch event. Agents, teams, workflows, and evals have separate telemetry controls. See Agno telemetry for payload details and AgentOS Security for authentication options.

AgentOS runtime and control plane connections

Next Steps

Run Your First AgentOS

Initialize and serve a basic agent.

Connect AgentOS to UI

Manage AgentOS using a Web UI.

Control Plane

Inspect sessions and debug traces.

Learn More

Parameter reference and configuration options for the AgentOS class.

Get Started

AgentOS

Example Usage

What is AgentOS?

Key Features

Architecture

Data Flow and Storage

Next Steps

Run Your First AgentOS

Connect AgentOS to UI

Control Plane

Learn More

​Key Features

​Architecture

​Data Flow and Storage

​Next Steps

Run Your First AgentOS

Connect AgentOS to UI

Control Plane

Learn More

Key Features

Architecture

Data Flow and Storage

Next Steps