Deploy to Railway

Deploy AgentOS to Railway with PostgreSQL, automatic HTTPS, and a public domain.

This template deploys AgentOS and PostgreSQL to Railway. It includes example agents ready to use after deployment, automatic HTTPS, and a public domain.

Prerequisites

• Docker Desktop
• OpenAI API key

Development

Run locally before deploying to Railway.

1. Clone the template

   git clone \
     https://github.com/agno-agi/agentos-railway-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.

Production

Deploy to Railway when you’re ready to go live.

Prerequisites

• Railway account (free tier works)
• Railway CLI

1. Login to Railway

   railway login
   
2. Deploy

   ./scripts/railway_up.sh
   

   Takes ~2 minutes. The script creates your Railway project, provisions PostgreSQL with pgvector, and deploys AgentOS.

3. Load knowledge

   railway run python -m agents.knowledge_agent
   
4. Get your domain

   railway open
   

   Find your URL in the Railway dashboard (e.g., my-agentos.up.railway.app). Navigate to <your-domain>/docs to confirm the API is running.

5. Connect to the control plane

   1. Go to os.agno.com
   2. Click Connect OS → Select Live
   3. Paste your Railway domain

   

Your AgentOS is live on Railway.

Next Steps

Add apps

Browse agents, teams, and workflows for your deployment.

Connect interfaces

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