> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-codex-docs-audit-20260719-0149.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Runtime

> Serve agents through a stateless FastAPI runtime with database persistence and optional auth.

AgentOS runs agents, teams, and workflows as an API service. A production runtime needs to:

1. Run components on demand through API requests or interfaces such as Slack and Telegram.
2. Maintain sessions across minutes, days, or weeks.
3. Preserve state across restarts, replicas, and infrastructure failures.
4. Protect application routes from unauthenticated access.
5. Record runs and actions for monitoring.

AgentOS serves native Agno components and adapters for the Claude Agent SDK, LangGraph, DSPy, and Antigravity.

This minimal persistent deployment uses PostgreSQL for agent and runtime state:

```python my_app.py theme={null}
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIResponses
from agno.os import AgentOS

db = PostgresDb(db_url="postgresql+psycopg://user:pass@host:5432/agno")

agent = Agent(model=OpenAIResponses(id="gpt-5.5"), db=db)

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

if __name__ == "__main__":
    agent_os.serve(app="my_app:app", reload=False)
```

This script starts a FastAPI application that can scale horizontally. The database persists sessions. Streaming is available by default; JWT authorization, tracing, and scheduling are optional AgentOS settings.

## 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              |

See [Multi-framework support](/agent-os/multi-framework/overview) for adapter setup.

## Explore

<CardGroup cols={2}>
  <Card title="Agent API" icon="server" href="/features/api">
    Run your agent platform as an API.
  </Card>

  <Card title="Agent Storage" icon="database" href="/features/storage">
    Add durability and persistence.
  </Card>

  <Card title="Observability" icon="chart-line" href="/features/observability">
    Tracing, run history, and audit logs in your own database.
  </Card>

  <Card title="Security and Auth" icon="shield-halved" href="/features/security-and-auth">
    JWT validation, RBAC scopes, and per-request isolation.
  </Card>

  <Card title="Scheduling" icon="clock" href="/features/scheduling">
    In-process cron and multi-step workflows.
  </Card>

  <Card title="Interfaces" icon="comments" href="/features/interfaces">
    Reach users on Slack, Telegram, WhatsApp, A2A, and AG-UI.
  </Card>
</CardGroup>