Kubernetes Reference

The scripts install the Helm release agentos into the agentos namespace. Override with AGENTOS_RELEASE and AGENTOS_NAMESPACE.

Manage

Task	Command
Roll to a new image tag	`IMAGE_TAG=v2 ./scripts/k8s/redeploy.sh` (build and push the tag first)
Restart pods in place	`./scripts/k8s/redeploy.sh`
Sync env variables	`./scripts/k8s/env-sync.sh` (connection and secret keys only; defaults to `.env.production`, pass `.env` to sync that instead)
Tail logs	`kubectl logs deploy/agentos -n agentos -f`
Port-forward the API	`kubectl port-forward svc/agentos 8000:8000 -n agentos`
Roll back a release	`helm rollback agentos -n agentos`
Tear down	`./scripts/k8s/down.sh` (add `--yes` to skip the confirmation)

Production auth

Token-Based Authorization is on by default. Without a JWT_VERIFICATION_KEY or JWT_JWKS_FILE, the app refuses to serve traffic in production. The platform’s job is to keep your data private, so the safe default is refuse to start. Token-Based Auth gives you three things:

No public access. The server rejects requests without a valid token.
Per-request identity. Middleware parses the token and extracts the user_id, session_id, and custom claims. Each request is tied to a user and session, giving you auditability and traceability.
Granular permissions. User tokens can run an agent and view their own sessions. Admin tokens read everyone’s sessions and test any agent.

To opt out (not recommended), set authorization=False in app/main.py, then build and push a new image tag and roll to it with IMAGE_TAG=<tag> ./scripts/k8s/redeploy.sh. Use this only inside a private VPC behind another auth layer. Without it, anyone who guesses your AgentOS URL can access your platform.

Customize

Add an agent

Ask your coding agent to run /create-new-agent, or do it by hand. Create agents/my_agent.py:

from agno.agent import Agent

from app.settings import default_model
from db import get_postgres_db

INSTRUCTIONS = """\
What the agent does, which tools it uses, the rules to follow when answering.
"""

my_agent = Agent(
    id="my-agent",
    name="My Agent",
    model=default_model(),
    db=get_postgres_db(),
    instructions=INSTRUCTIONS,
    enable_agentic_memory=True,
    add_datetime_to_context=True,
    add_history_to_context=True,
    num_history_runs=5,
)

from agents.my_agent import my_agent

agent_os = AgentOS(
    ...
    agents=[agent_builder, platform_manager, web_search, my_agent],
)

Local containers hot-reload on save. For production, build and push a new image tag, then run IMAGE_TAG=<tag> ./scripts/k8s/redeploy.sh. If the release still runs the official image, point it at your registry first: IMAGE_REPOSITORY=<registry>/agentos IMAGE_TAG=<tag> ./scripts/k8s/up.sh.

Change the model

app/settings.py defines default_model(), used by every agent. Change it in one place:

from agno.models.anthropic import Claude

def default_model():
    return Claude(id="claude-sonnet-5")

Add anthropic to pyproject.toml, set the provider key in your env, and regenerate pins:

./scripts/generate_requirements.sh

Rebuild locally with docker compose up -d --build. For production:

./scripts/k8s/env-sync.sh
docker build -t <registry>/agentos:v2 . && docker push <registry>/agentos:v2
IMAGE_TAG=v2 ./scripts/k8s/redeploy.sh

Add tools

Agno ships 100+ toolkits. See Toolkits.

from agno.tools.slack import SlackTools

my_agent = Agent(
    ...
    tools=[SlackTools()],
)

Add dependencies

Edit pyproject.toml.
Regenerate pins: ./scripts/generate_requirements.sh (add upgrade to refresh every pin).
Rebuild locally with docker compose up -d --build, or build and push a new tag and roll to it with IMAGE_TAG=<tag> ./scripts/k8s/redeploy.sh.

Enable Slack

Set both variables in your env file:

SLACK_BOT_TOKEN=xoxb-...
SLACK_SIGNING_SECRET=...

Sync with ./scripts/k8s/env-sync.sh. The interface activates automatically and routes messages to Agent Builder; change the agent= argument in app/main.py to point at another agent. See Slack setup.

Toggle scheduled workflows

The deployment check runs daily by default (ENABLE_DEPLOY_CHECK=True); it is deterministic and free. Scheduled evals are off by default (ENABLE_SCHEDULED_EVALS=False) because they use model calls. Both workflows stay runnable on demand regardless.In the cluster these are chart values. Set them via extraEnv and helm upgrade; ./scripts/k8s/env-sync.sh syncs only the connection and secret keys.

Format, validate, and run evals

The format, validate, and eval scripts run on the host and need a venv. Set it up once:

./scripts/venv_setup.sh
source .venv/bin/activate

Task	Command
Format	`./scripts/format.sh`
Lint and type-check	`./scripts/validate.sh`
Run smoke evals	`python -m evals --tag smoke`

./scripts/mcp_check.sh runs inside the container, so it needs no venv.

Environment variables

Variable	Required	Default	Description
`OPENAI_API_KEY`	Yes	-	Models and embeddings.
`RUNTIME_ENV`	No	`prd`	`dev` disables JWT. Compose sets it for local. Never put it in an env file that syncs to a real cluster, or production deploys unauthenticated.
`JWT_VERIFICATION_KEY`	Production	-	Public key from os.agno.com. Quote the value so the multi-line PEM parses as one variable.
`JWT_JWKS_FILE`	Production	-	Path to a JWKS file inside the container. Alternative to `JWT_VERIFICATION_KEY`. `up.sh` and `env-sync.sh` deliver it as the chart value `jwtJwksFile`.
`MCP_CONNECT_SECRET`	No	-	OAuth consent secret (16+ chars) for connecting claude.ai and ChatGPT to `/mcp`. `up.sh` generates it into `.env.production` when the deploy has a public URL (`INGRESS_HOST` or `AGENTOS_URL`); set it by hand otherwise.
`AGENTOS_MCP_SIGNING_KEY`	No	generated	Optional high-entropy signing-key material (32+ chars) for OAuth tokens. Unset, a strong key is generated and persisted in the database. Rotating it invalidates outstanding tokens.
`AGENTOS_URL`	No	`http://127.0.0.1:8000`	Scheduler base URL. The chart resolves it automatically: explicit value, then ingress URL, then in-cluster service DNS. Set it by hand only for a custom domain or tunnel. Also the public origin OAuth metadata derives from when `MCP_CONNECT_SECRET` is set.
`ENABLE_DEPLOY_CHECK`	No	`True`	Daily deployment-check cron.
`ENABLE_SCHEDULED_EVALS`	No	`False`	Daily run-evals cron. Uses model calls.
`EVALS_TAG`	No	`smoke`	Eval tag the run-evals workflow runs.
`EVALS_CASE_TIMEOUT_SECONDS`	No	`90`	Per-case timeout for run-evals runs.
`EVALS_SUITE_TIMEOUT_SECONDS`	No	`900`	Whole-suite timeout for run-evals runs.
`PARALLEL_API_KEY`	No	-	WebSearch uses the Parallel SDK when set, keyless MCP otherwise.
`SLACK_BOT_TOKEN`	No	-	Set with the signing secret to enable Slack.
`SLACK_SIGNING_SECRET`	No	-	Set with the bot token to enable Slack.
`DB_HOST` / `DB_PORT` / `DB_USER` / `DB_PASS` / `DB_DATABASE`	No	matches compose	Postgres connection. `up.sh` generates `DB_PASS` once and saves it to your env file.
`DB_DRIVER`	No	`postgresql+psycopg`	SQLAlchemy driver.
`AGNO_DEBUG`	No	`False`	Verbose Agno logs. Compose sets it for dev.
`WAIT_FOR_DB`	No	`False`	If `True`, the entrypoint blocks on the database before starting. Compose sets it.
`AGENTOS_NAMESPACE`	No	`agentos`	Namespace the k8s scripts target.
`AGENTOS_RELEASE`	No	`agentos`	Helm release name the k8s scripts target.
`IMAGE_REPOSITORY`	No	`agnohq/agentos`	Image the chart deploys. Read by `up.sh`.
`IMAGE_TAG`	No	`latest`	Image tag. `up.sh` installs it; `redeploy.sh` rolls the release to it.
`IMAGE_PULL_POLICY`	No	`IfNotPresent`	Set `Never` for images loaded into kind. Read by `up.sh`.
`INGRESS_HOST`	No	-	Publishes the API behind your ingress controller at this host. Read by `up.sh`.
`INGRESS_CLASS`	No	-	Ingress class name, for example `nginx`. Read by `up.sh`.

Troubleshooting

kubectl or helm: command not found

Install kubectl and Helm 3+. The scripts check for both before doing anything.

up.sh exits: no context or cluster not reachable

up.sh deploys into your current kubectl context and verifies it can reach the cluster first. Point kubectl at the target cluster and confirm kubectl get namespace works, then rerun.

up.sh pauses asking for a JWT key

Expected. Mint the key at os.agno.com: connect your OS (Connect OS → Live, enter your AgentOS URL), then turn on Token-Based Authorization (JWT) under Settings → OS & Security and paste the full PEM. To do it later, skip the prompt, add JWT_VERIFICATION_KEY or JWT_JWKS_FILE to .env.production, and run ./scripts/k8s/env-sync.sh.

App refuses to serve in production

JWT auth is on whenever RUNTIME_ENV is not dev. Set JWT_VERIFICATION_KEY or JWT_JWKS_FILE and sync. To opt out inside a private VPC behind another auth layer, set authorization=False in app/main.py and roll out your own image build.

Pods stuck in ImagePullBackOff

The cluster can’t pull the image. Confirm the tag was pushed and the cluster has access to your registry; for private registries, set imagePullSecrets in charts/agentos/values.yaml. On kind, kind load docker-image the tag and deploy with IMAGE_PULL_POLICY=Never.

Database rejects the app after a password change

The Postgres volume reads its password only on first initialization, so a lost or regenerated DB_PASS locks the app out of an existing volume. Restore the DB_PASS that up.sh saved to your env file and sync, fix the database in place with ALTER USER, or delete the PVC to reinitialize. Deleting the PVC deletes all data.

Scheduled jobs never fire

AGENTOS_URL resolves automatically: explicit value, then ingress URL, then in-cluster service DNS. If you set it by hand, make sure the pod can reach that URL, then run ./scripts/k8s/env-sync.sh.

claude.ai or ChatGPT can't connect to /mcp

up.sh generates MCP_CONNECT_SECRET only when the deploy has a public URL (INGRESS_HOST or an explicit AGENTOS_URL). Deployed without one? Set MCP_CONNECT_SECRET and a public AGENTOS_URL in .env.production and run ./scripts/k8s/env-sync.sh.

Get Started

Starters

Apps

Agno CLI

Kubernetes Reference

Manage

Production auth

Customize

Format, validate, and run evals

Environment variables

Troubleshooting

​Manage

​Production auth

​Customize

​Format, validate, and run evals

​Environment variables

​Troubleshooting

Manage

Production auth

Customize

Format, validate, and run evals

Environment variables

Troubleshooting