Skip to main content
This template runs AgentOS and PostgreSQL with pgvector on Railway. It includes example agents ready to use after deployment, automatic HTTPS (handled by Railway) and public domain (your-app.up.railway.app).

Prerequisites

Step-by-Step Guide

1

Set up Python environment

2

Install Agno

3

Create project codebase from template

The template includes the following agents ready to use after deployment:

Pal

Personal assistant that learns from you. Stores notes, bookmarks, and research findings.

Knowledge Agent

RAG agent that answers questions from your documents. Pre-loaded with Agno docs.

MCP Agent

Connects to external tools via MCP. Extensible with any MCP-compatible service.
4

Set your API key

5

Login and deploy to Railway

It takes ~2 min and creates the project, provisions PostgreSQL with pgvector, and deploys your AgentOS.
6

Get your domain

Find your URL in the dashboard (e.g., my-agentos.up.railway.app). Navigate to <railway-domain>/docs to see your AgentOS API.
7

Connect to your AgentOS Control Plane

  1. Go to os.agno.com
  2. Click “Connect OS” → Select “Live”
  3. Paste your Railway domain
AgentOS connection dialog
Your AgentOS is live on Railway! Manage it from os.agno.com

Tips

You can customize the agents included in the template codebase with additional capabilities.

Build Custom Agents

Create agents with your own tools and prompts.

Add Tools

Slack, GitHub, databases, and 100+ integrations.

Add Knowledge

Load documents, websites, and databases for RAG.

Add Interfaces

Deploy to Slack, Discord, WhatsApp, or expose via MCP.

Troubleshooting

Install: brew install railway (Mac) or npm install -g @railway/cli
Run railway init first, then ./scripts/railway_up.sh again.
PostgreSQL takes ~30s. Check: railway logs --service pgvector
Container starting. Wait 1-2 min. Check: railway logs --service agent_os