Security & Auth

Build a layered security model: authenticate every request, use scopes and roles for permissions, and isolate data between users.

AgentOS security works in layers. Each one stops a different class of attack, from unauthenticated requests at the edge to cross-user data access in the database. AgentOS gives you good defaults at every layer.

Network-layer controls (rate limiting, WAF, IP allowlists, mTLS) live at your reverse proxy or API gateway layer.

Authentication

A production AgentOS sits behind JWT-validating middleware. Tokens can come from the AgentOS control plane, your own backend, or a third-party identity provider. Your service verifies them with the matching public key. See Self-Hosted for BYO and third-party setup.

from agno.os import AgentOS

agent_os = AgentOS(
    agents=[agent],
    db=db,
    authorization=True,  # reads JWT_VERIFICATION_KEY from env
)

authorization=True drives both layers:

• Authentication (this section): requires a valid JWT on every request.
• Authorization (below): enforces the token’s scopes per endpoint.

A small set of public routes are exempt from the JWT requirement: /, /health, /info, /docs, /redoc, /openapi.json, /docs/oauth2-redirect.

Generate a Verification Key from the Control Plane

1. Toggle JWT authorization

   Open os.agno.com → Add OS → Live → paste your URL. Enable JWT authorization when connecting a new AgentOS, or later from the OS Settings page.

2. Copy the public key

   Copy the public key for your AgentOS from the modal.

3. Set the verification key

   Set the JWT_VERIFICATION_KEY environment variable to your public key in your .env file or export it directly in your terminal:

   export JWT_VERIFICATION_KEY="your-public-key"
   

   Or, if you manage keys via a JWKS file, point AgentOS at it instead:

   export JWT_JWKS_FILE="/path/to/jwks.json"
   

When tokens are issued by the AgentOS control plane, it keeps the private key and your service only sees the public key. See Generate a Verification Key from the Control Plane for the full walkthrough.

Configure JWTs from Your Backend or IDP

If you’re issuing JWTs from your own backend, or from a third-party identity provider like WorkOS, Auth0, or Okta, pass an AuthorizationConfig:

from agno.os import AgentOS
from agno.os.config import AuthorizationConfig

agent_os = AgentOS(
    agents=[agent],
    db=db,
    authorization=True,
    authorization_config=AuthorizationConfig(
        verification_keys=["public-key-1", "public-key-2"],   # multi-issuer
        algorithm="RS256",
        verify_audience=True,
        audience="my-agent-os",   # must match the token's `aud`; defaults to the AgentOS id
        user_isolation=True,      # see below
    ),
)

verification_keys is a list. AgentOS tries each key in order until one verifies the token, so you can accept tokens from multiple issuers at the same time. For key rotation, use a JWKS file instead.

With verify_audience=True, AgentOS rejects tokens whose aud claim doesn’t match the expected audience. That expected value defaults to the AgentOS id; set audience to override it when your provider mints a different value.

JWT claim names (scopes, sub) are configured on the JWT middleware itself, not on AuthorizationConfig. The defaults (scopes for the scopes claim, sub for the user id claim) match the tokens minted by the control plane.

For the full self-hosted setup including multi-issuer, see Self-Hosted.

Authorization

Every JWT carries a claim listing the caller’s permissions (scopes by default; configurable via scopes_claim if your provider uses a different name, like WorkOS’s permissions). Endpoints are gated on those scopes.

Scope	Grants
agents:read	List agents and read their config
agents:<id>:run	Run a specific agent
agents:*:run	Run any agent (same pattern for teams, workflows)
agent_os:admin	Full access including session, memory, and trace queries

The AgentOS control plane mints each token with the appropriate scopes. Scopes are bundled into roles and assigned to users in the control plane: the AgentOS control plane provides three default roles (owner, admin, member), and custom roles are available on Enterprise. Self-hosters define roles in their identity provider or backend. See the scope reference for the full scope list, Default Roles for what each grants, and Custom Roles to compose your own.

Request isolation

Every request gets a fresh copy of the agent, team, or workflow it’s hitting. AgentOS calls deep_copy() on the registered component per request, so mutable state (session-scoped variables, tool execution context, run metadata) never bleeds between concurrent calls.

Heavy resources (the DB connection, the model client, MCP tool handles) are shared by reference; only the mutable per-run state is isolated. You get cheap concurrency without the footgun of two requests racing on the same in-memory agent instance.

This is on by default for every run endpoint. There’s nothing to configure.

User isolation

Per-user data isolation is opt-in. Authorization stays in force without it, but routes operate on the unscoped DB. A caller with agents:my-agent:run could read another user’s sessions if they know the IDs. For multi-tenant deployments, turn it on:

from agno.os.config import AuthorizationConfig

agent_os = AgentOS(
    agents=[agent],
    db=db,
    authorization=True,
    authorization_config=AuthorizationConfig(
        verification_keys=[public_key],
        user_isolation=True,   # requires authorization=True; the user_id comes from the JWT sub
    ),
)

With user_isolation=True, every non-admin caller gets:

Guarantee	How
No cross-user reads	The JWT sub is threaded as user_id on every user-scoped read (sessions, memory, traces). Callers only see their own rows.
No cross-user writes	user_id is coerced on every write, so a non-admin can’t persist a session, memory, or trace attributed to another user.
Run ownership	Cancel, resume, and continue routes require session_id and verify the run belongs to the caller’s session.
WebSocket reconnect	Reconnecting to a workflow run requires session_id and workflow_id, then verifies the caller owns the run.

Admin callers (whoever holds the configured admin_scope, defaulting to agent_os:admin) bypass all of the above and see the full unscoped view: service accounts, internal tooling, the control plane.

Per-user isolation requires a database that records user_id (PostgreSQL recommended for production).

Defaults

Concern	Default behavior
Authentication	authorization=False. Opt in with authorization=True and JWT_VERIFICATION_KEY for production.
Request isolation	On. Every run endpoint deep-copies the component.
User isolation	Off. Opt in via AuthorizationConfig(user_isolation=True) for multi-tenant.

See the AuthorizationConfig reference for all configuration options and their defaults.