Skip to main content
The web service is agent-os and the database is agentos-db. Every command in scripts/render/ drives the Render API and needs RENDER_API_KEY in your environment or env file.

​
Manage

TaskCommand
Deploy code changesPush to your deploy branch. autoDeploy: true in render.yaml rebuilds automatically.
Re-run a build without a commit./scripts/render/redeploy.sh
Sync env variables./scripts/render/env-sync.sh (defaults to .env.production; pass .env to sync that instead)
Tail logsDashboard: agent-os → Logs
Tear down./scripts/render/down.sh (add --yes to skip the confirmation)

​
Auto-deploy on merge

autoDeploy: true is on in render.yaml, so every push to your deploy branch triggers a build and deploy. Render builds the pushed branch; local uncommitted changes never deploy. ./scripts/render/env-sync.sh is still how you sync env changes.

​
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:
  1. No public access. The server rejects requests without a valid token.
  2. 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.
  3. 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 and push. Use this only inside a private VPC behind another auth layer. Without it, anyone who guesses your onrender.com URL can access your platform.

​
Customize

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,
)
Register it in app/main.py:
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, commit and push; Render rebuilds automatically.
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, sync the env and push:
./scripts/render/env-sync.sh
git push
Agno ships 100+ toolkits. See Toolkits.
from agno.tools.slack import SlackTools

my_agent = Agent(
    ...
    tools=[SlackTools()],
)
  1. Edit pyproject.toml.
  2. Regenerate pins: ./scripts/generate_requirements.sh (add upgrade to refresh every pin).
  3. Rebuild locally with docker compose up -d --build, or commit and push to redeploy.
Set both variables in your env file:
SLACK_BOT_TOKEN=xoxb-...
SLACK_SIGNING_SECRET=...
Sync with ./scripts/render/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.
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.

​
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
TaskCommand
Format./scripts/format.sh
Lint and type-check./scripts/validate.sh
Run smoke evalspython -m evals --tag smoke
./scripts/mcp_check.sh runs inside the container, so it needs no venv.

​
Environment variables

VariableRequiredDefaultDescription
OPENAI_API_KEYYes-Models and embeddings. The Blueprint prompts for it at launch.
RENDER_API_KEYDeploy scripts-Drives the Render API in scripts/render/. The scripts read it from your environment or env file; env-sync.sh never pushes RENDER_* keys to the service.
RUNTIME_ENVNoprddev disables JWT. Compose sets it for local. Never put it in an env file that syncs to Render, or production deploys unauthenticated.
JWT_VERIFICATION_KEYProduction-Public key from os.agno.com. Quote the value so the multi-line PEM parses as one variable.
JWT_JWKS_FILEProduction-Path to a JWKS file. Alternative to JWT_VERIFICATION_KEY.
MCP_CONNECT_SECRETNogenerated by up.shOAuth 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_KEYNogeneratedOptional 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_URLNohttp://127.0.0.1:8000Scheduler base URL. up.sh pins it to your onrender.com 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.
ENABLE_DEPLOY_CHECKNoTrueDaily deployment-check cron.
ENABLE_SCHEDULED_EVALSNoFalseDaily run-evals cron. Uses model calls.
EVALS_TAGNosmokeEval tag the run-evals workflow runs.
EVALS_CASE_TIMEOUT_SECONDSNo90Per-case timeout for run-evals runs.
EVALS_SUITE_TIMEOUT_SECONDSNo900Whole-suite timeout for run-evals runs.
PARALLEL_API_KEYNo-WebSearch uses the Parallel SDK when set, keyless MCP otherwise.
SLACK_BOT_TOKENNo-Set with the signing secret to enable Slack.
SLACK_SIGNING_SECRETNo-Set with the bot token to enable Slack.
DB_HOST / DB_PORT / DB_USER / DB_PASS / DB_DATABASENomatches composePostgres connection. The Blueprint wires them from agentos-db.
DB_DRIVERNopostgresql+psycopgSQLAlchemy driver.
AGNO_DEBUGNoFalseVerbose Agno logs. Compose sets it for dev.
WAIT_FOR_DBNoFalseIf True, the entrypoint blocks on the database before starting. Compose and the Blueprint set it.

​
Troubleshooting

Expected before the first Blueprint launch. Open dashboard.render.com → New + → Blueprint, connect your copy of the repo, and apply. The script prints these steps and polls every 15 seconds for up to 30 minutes, so you can leave it running while you launch.
Create one in the dashboard under Account Settings → API Keys, then export it or add it to .env.production. The scripts read it from either place.
Expected. Mint the key at os.agno.com: connect your OS (Connect OS → Live, enter your onrender.com 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/render/env-sync.sh.
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.
Render builds the pushed branch, so local uncommitted changes stay on your machine. Commit, push to your deploy branch, and let autoDeploy rebuild. redeploy.sh warns when it finds uncommitted changes.
AGENTOS_URL is still the localhost default. up.sh pins it to your onrender.com URL automatically, and env-sync.sh pins it when your env file has none; for a custom domain or tunnel, set it by hand and run ./scripts/render/env-sync.sh.
The service is likely on the free plan, which sleeps between requests; the in-process scheduler and MCP streams stop when it does. Set plan: starter (or higher) in render.yaml and push.