AWS Reference

The template names the Express service agent-os, the ECR repo agentos, and the RDS instance agentos-db. Secrets live under agentos/* in Secrets Manager, and the scripts record the service ARN and region in tmp/agentos-aws.state.

Manage

Task	Command
Deploy code changes	`./scripts/aws/redeploy.sh`
Sync env variables	`./scripts/aws/env-sync.sh` (defaults to `.env.production`; pass `.env` to sync that instead)
Tail logs	`aws logs tail /ecs/agent-os --follow`
Watch a rollout	`aws ecs monitor-express-gateway-service --region <region> --service-arn <arn>`
Tear down	`./scripts/aws/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.

Only /health stays open. AgentOS serves it unauthenticated even in production, so the ALB health checks pass. To opt out (not recommended), set authorization=False in app/main.py and redeploy. Use this only inside a private VPC behind another auth layer. Without it, anyone who guesses your service 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, run ./scripts/aws/redeploy.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/aws/redeploy.sh

It rebuilds the image and syncs .env.production in one pass.

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 redeploy with ./scripts/aws/redeploy.sh.

Enable Slack

Set both variables in your env file:

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

Sync with ./scripts/aws/env-sync.sh; both land in Secrets Manager. 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.

Switch Fargate to ARM

ARM cuts the Fargate line item from about

70 to about

57 per month. Edit runtimePlatform in scripts/aws/task-def.json, change docker build --platform linux/amd64 to linux/arm64 in both up.sh and redeploy.sh, then run ./scripts/aws/redeploy.sh.

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 AWS, 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. Alternative to `JWT_VERIFICATION_KEY`. `up.sh` delivers it through the task-definition env.
`MCP_CONNECT_SECRET`	No	generated by `up.sh`	OAuth consent secret (16+ chars) for connecting claude.ai and ChatGPT to `/mcp`. `up.sh` generates one on deploy and writes it to `.env.production`.
`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. `up.sh` sets it to your Express service URL. Scheduled jobs never fire if it stays at the default in production. Also the public origin OAuth metadata derives from when `MCP_CONNECT_SECRET` is set.
`SERVICE_ARN`	No	written by `up.sh`	Deploy metadata the scripts use to find the Express service. `env-sync.sh` never sends it to the container.
`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_DATABASE`	No	matches compose	Postgres connection. `env-sync.sh` skips these; production values come from the provisioned RDS instance.
`DB_PASS`	No	matches compose	Postgres password. `up.sh` generates the production value and stores it in Secrets Manager.
`DB_DRIVER`	No	`postgresql+psycopg`	SQLAlchemy driver. `env-sync.sh` skips it too; production uses the task-definition value.
`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.

Troubleshooting

up.sh exits: the CLI predates ECS Express Mode

Upgrade the AWS CLI (for example brew upgrade awscli) until aws ecs create-express-gateway-service help works. If credentials are the problem instead, run aws configure and confirm aws sts get-caller-identity succeeds.

up.sh exits: no default VPC

The RDS instance deploys into the region’s default VPC. Create one with aws ec2 create-default-vpc, or adapt scripts/aws/up.sh to your own VPC.

up.sh pauses asking for a JWT key

Expected. Mint the key at os.agno.com: connect your OS (Connect OS → Live, enter your service 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/aws/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.

The service URL never answers

First-time provisioning of the ALB, certificate, and DNS takes 10-25 minutes; up.sh waits through it. Past that window, the known first-run cause is freshly created IAM roles: Express’s async infrastructure calls get denied before the role policies propagate, and ECS never retries. up.sh detects this and recreates the service once; the second attempt provisions reliably. If it still stalls, inspect with aws ecs monitor-express-gateway-service --region <region> --service-arn <arn>, look for an AccessDenied CreateLoadBalancer event in CloudTrail, then delete the service and re-run ./scripts/aws/up.sh.

5xx right after deploy

The gateway is up; the app is still starting. First boot pulls the image and waits for the database. Wait a few minutes and check aws logs tail /ecs/agent-os --follow.

Scheduled jobs never fire

AGENTOS_URL is still the localhost default. up.sh sets it to your service URL automatically; for a custom domain or tunnel, set it by hand and run ./scripts/aws/env-sync.sh.

env-sync.sh or redeploy.sh can't find the service

The scripts resolve the service ARN from tmp/agentos-aws.state first, then from a SERVICE_ARN= line in .env.production or .env. On a fresh clone or a new machine, write the ARN of your Express service into the state file: printf 'SERVICE_ARN=arn:aws:ecs:...' > tmp/agentos-aws.state.

down.sh says everything is already gone, but the bill continues

The commands are hitting the wrong region. The scripts use AWS_REGION if set, then the region recorded in tmp/agentos-aws.state, then us-east-1. Set AWS_REGION to the region you deployed to and re-run ./scripts/aws/down.sh.

​Manage

​Production auth

​Customize

​Format, validate, and run evals

​Environment variables

​Troubleshooting