Skip to main content

​
What we’re building today

A multi-agent system with three agents:
AgentWhat it does
ScoutYour enterprise librarian. Navigates document stores, extracts answers, and learns from usage.
Knowledge AgentAnswers questions from a knowledge base (Agentic RAG).
MCP AgentConnects to external services via Model Context Protocol.
You’ll run it locally with Docker, then deploy to Railway. Prerequisites:

​
Run Locally

1

Clone the repository

git clone \
    https://github.com/agno-agi/agentos-railway-template.git \
    agentos-railway
cd agentos-railway
2

Configure environment

cp example.env .env
Add your OPENAI_API_KEY to .env
3

Start the application

docker compose up -d --build
4

Connect to the control plane

  1. Open os.agno.com
  2. Click Add OS → Local
  3. Enter http://localhost:8000
Your multi-agent system is now running at localhost:8000.

​
Try Your Agents

​
Scout

Scout navigates document stores, reads full documents, and extracts answers. It learns from usage, so repeated questions get faster, more accurate responses. The template includes a public demo bucket with sample company documents. Try asking:
  • What is our PTO policy?
  • Where is the deployment runbook
  • What is the incident response process?

​
Knowledge Agent

The Knowledge Agent answers questions using hybrid search over a vector database. Load the sample documents first: 
docker exec -it agentos-api python -m agents.knowledge_agent
Then try:
  • What is Agno?
  • How do I create my first agent?

​
MCP Agent

The MCP Agent connects to external tools via Model Context Protocol. Try:
  • What tools do you have access to?
  • Search the docs for how to use Learning Machines

​
Deploy to Production

1

Install Railway CLI

brew install railway
2

Login and deploy

railway login
./scripts/railway_up.sh
The script provisions PostgreSQL, configures environment variables, and deploys your system.
3

Connect to the control plane

  1. Open os.agno.com
  2. Click Add OS → Live
  3. Enter your Railway domain
Your multi-agent system is now live. Connect to the UI via the railway deployment URL.

​
Manage Your Deployment

railway logs --service agent_os      # View logs
railway open                         # Open dashboard
railway up --service agent_os -d     # Deploy updates

​
Next

Add Your Own Agent

Extend the system with custom agents

Add Tools

Connect to Slack, Gmail, Calendar, and 100+ integrations

AgentOS Deep Dive

Learn more about the production runtime

Learning System

Configure how agents learn and remember