Deploy with Docker

Run AgentOS locally with Docker and PostgreSQL, then deploy to any cloud.

This template runs AgentOS and PostgreSQL with pgvector in Docker. It includes example agents ready to use after startup, hot-reload for development, and works on any cloud that supports Docker.

Prerequisites

• Docker Desktop
• OpenAI API key

Development

Run locally before deploying to production.

1. Clone the template

   git clone \
     https://github.com/agno-agi/agentos-docker-template.git \
     agentos
   
   cd agentos
   

   The template includes the following agents:

   Agent	Description
   Knowledge Agent	Answers questions from your documents using Agentic RAG.
   MCP Agent	Connects to external tools via Model Context Protocol.

2. Set your API key

   cp example.env .env
   

   Edit .env and add your OPENAI_API_KEY.

3. Start AgentOS

   docker compose up -d --build
   
4. Load knowledge

   docker exec -it agentos-api python -m agents.knowledge_agent
   

   This loads the default documents into the Knowledge Agent’s vector database. You can add your own documents as needed.

5. Confirm it's running

   Navigate to localhost:8000/docs to see your AgentOS API.

6. Connect to the control plane

   1. Go to os.agno.com
   2. Click Connect OS → Select Local
   3. Enter http://localhost:8000

   

Your AgentOS is running locally.

Cloud Deployment

Deploy this template to any cloud that supports Docker:

Provider	Service
AWS	ECS, App Runner
Google Cloud	Cloud Run, Compute Engine
Azure	Container Apps
Platforms	Railway, Render, Fly.io

Build and push your image, set the environment variables from .env, and ensure your PostgreSQL instance has pgvector enabled.

Next Steps

Add apps

Browse agents, teams, and workflows for your deployment.

Connect interfaces

Expose your agents on Slack, Discord, WhatsApp, or MCP.