- AgentOS Starters: clean AgentOS installations, one per platform: Railway, AWS, Fly, GCP and more.
- Application Blueprints: ready-to-use agentic solutions that you can deploy today.
What’s inside every Starter
Every starter template comes with a common platform core, along with cloud-specific deploy instructions.| Component | What it does |
|---|---|
| Two platform agents | Agent Builder creates agents, teams, and workflows. Platform Manager helps manage the platform. |
| Two workflows | Deployment Check checks platform health and Run Evals runs the eval suite. |
| MCP server | Makes your platform available to any AI app or MCP client. |
| Coding-agent skills | Manage your platform using skills like /create-new-agent, /improve-agent and more. |
| Eval suite | Full AgentAsJudge and Reliability eval suite, ready to catch regressions. |
| PostgreSQL | Sessions, memory, knowledge, and traces all stored in your database. |
Get started
Pick a template
- AgentOS Starters
- Application Blueprints
Railway
Run AgentOS and PostgreSQL on Railway.
Docker
Run locally or self-host anywhere Docker runs.
AWS
ECS Express Mode with RDS PostgreSQL.
Fly
A single always-on machine on Fly.io.
GCP
Cloud Run with Cloud SQL.
Kubernetes
A Helm chart for any cluster: EKS, GKE, AKS.
Azure
Container Apps with PostgreSQL.
Render
A Blueprint with managed PostgreSQL.
Modal
Modal + Neon Postgres.
Set up with a coding agent
Each Starter comes with a setup prompt you can give to coding agents like Claude Code, Cursor, or Codex. The agent clones the repo and sets everything up. Every template also comes with manual steps, but we recommend using coding agents for setup.
Connect your frontends
Connect your AgentOS to the AgentOS UI with Connect OS, and to coding agents on your machine by running
uvx agno connect. You can also use the AgentOS MCP server (https://<agentos-domain>/mcp) to connect your AgentOS to the Claude and ChatGPT apps.