Skip to main content
The agentos-render template is for teams that develop locally with Docker and deploy to production on Render. It includes:
  • Agent Builder, which creates agents, teams, and workflows.
  • Platform Manager, which inspects and explains the platform, eval history, deployment checks, and schedules.
  • Eight skills for setting up, building, testing, reviewing, and deploying the project with a coding agent.
Coding agents can use these skills with the AgentOS API, evals, traces, and container logs to inspect and improve the platform. Deployment is Blueprint-driven: Render provisions everything from render.yaml when you connect your repo, and one wiring script finishes the setup.

​
Get started

Copy the prompt below into Claude Code, Cursor, or Codex to configure and run the template with a coding agent.
Prefer to drive yourself? Follow the manual steps below.

​
Manual setup

Prerequisites: Docker installed and running. An OpenAI API key.
1

Clone and configure

Edit .env and set OPENAI_API_KEY.
2

Start the platform

The first build takes a few minutes. Confirm the API is available at localhost:8000/docs.
3

Verify end to end

Prints MCP OK with the tool count and a real agent answer through the MCP endpoint.
4

Connect the AgentOS UI

  1. Open os.agno.com and sign in.
  2. Click Connect OS, enter http://localhost:8000, and name it Local AgentOS.
5

Build your first agent

  1. Chat with Agent Builder: “Build an agent that tracks AI news and writes a daily brief”. Go through the agent development process.
  2. Once created, click Refresh on the top right, pick the new agent from the Agents dropdown, and ask: “What’s new with Anthropic?”
  3. Ask Platform Manager: “How healthy is the platform?” It answers from eval history, deployment checks, schedules, and the agent you just built.
At this point, your AgentOS is running locally.

​
Connect your frontends

​
Deploy to production

Prerequisites: A Render account with your copy of the repo reachable from Render, a RENDER_API_KEY (dashboard → Account Settings → API Keys) for the scripts, Python 3, and OpenSSL.
1

Create a production env

Edit .env.production with production values: a different OpenAI key, production-only credentials, a different Slack workspace.
2

Launch the Blueprint

Open dashboard.render.com → New + → Blueprint, connect your copy of the repo, and apply. Render reads render.yaml, prompts for OPENAI_API_KEY, builds the Dockerfile, and creates the basic-256mb Postgres. The first build takes about 10 minutes.The web service runs on the starter plan, the cheapest that never sleeps, which the in-process scheduler and MCP streams require. It runs as a single instance by design; two instances double-fire every cron.
3

Wire the rest

Waits for the Blueprint service to appear, pins AGENTOS_URL to the real service URL so scheduled jobs reach the platform (render.yaml can’t reference its own URL), generates MCP_CONNECT_SECRET (the chat-app OAuth consent secret, printed once in the closing summary), and pauses for a JWT verification key.
4

Mint your JWT key

The script pauses for a JWT_VERIFICATION_KEY. Token-Based Authorization is on by default. Production startup requires that verification key or a readable JWKS file at the container path in JWT_JWKS_FILE; otherwise the process exits. The script delivers a PEM value directly. For JWKS, commit and push the file into the Docker build context, or configure a mount. Set JWT_JWKS_FILE to its container path and let auto-deploy rebuild the service. The script only delivers the path.
  1. Open os.agno.com, click Connect OS → Live, and enter your onrender.com URL.
  2. Name it Live AgentOS, turn on Token-Based Authorization (JWT) on the connection panel, and connect. The UI generates the public key. If the OS is already connected, enable the setting under Settings → OS & Security.
  3. Copy the public key and paste the full PEM into the up.sh prompt. The script saves it to your env file and deploys.
If you skip the prompt, add the key to .env.production later and run ./scripts/render/env-sync.sh.
Live AgentOS connections are a paid feature. Use code PLATFORM30 for one month off.
5

Connect your MCP clients

Re-run uvx agno connect, this time pointed at your deployed domain:
For claude.ai and ChatGPT on the web: add https://<onrender-domain>/mcp as a custom connector in the chat app’s connector settings. Leave the form’s optional OAuth fields (client ID / client secret) empty. Click Connect and, on the consent page, enter the MCP_CONNECT_SECRET that up.sh generated during deploy (saved in .env.production).
6

Confirm it's live

The script prints your service URL. Open https://<onrender-domain>/docs to confirm the API is serving. Logs live in the dashboard: agent-os → Logs.
Your AgentOS is live on Render.

​
Redeploy after code changes

autoDeploy: true is on in render.yaml, so pushing to your deploy branch redeploys automatically. Render builds the pushed branch; local uncommitted changes never deploy. To re-run a build without a new commit:

​
Sync environment variables

​
Tear down

Deletes the agent-os service and the agentos-db Postgres, including all data, and verifies both are gone before declaring success. The Blueprint instance itself stays listed in the dashboard; remove it from the Blueprints tab.

​
Next steps

Build with coding agents

Skills to create → improve → evaluate your platform using coding agents.

Render reference

Commands, environment variables, troubleshooting.