Skip to content

first-multi-agent-system.mdx

Latest commit

 

History

History
140 lines (111 loc) · 3.66 KB

first-multi-agent-system.mdx

File metadata and controls

140 lines (111 loc) · 3.66 KB
title First Multi-Agent System
description Build and run your first multi-agent system.
keywords
agno
agent
quickstart
tutorial
mode wide

What we're building today

A multi-agent system with three agents:

Agent What it does
Scout Your enterprise librarian. Navigates document stores, extracts answers, and learns from usage.
Knowledge Agent Answers questions from a knowledge base (Agentic RAG).
MCP Agent Connects to external services via Model Context Protocol.

You'll run it locally with Docker, then deploy to Railway. Prerequisites:

Run Locally

```bash git clone \ https://github.com/agno-agi/agentos-railway-template.git \ agentos-railway cd agentos-railway ``` ```bash cp example.env .env ``` Add your `OPENAI_API_KEY` to `.env` ```bash docker compose up -d --build ``` 1. Open [os.agno.com](https://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

```bash Mac brew install railway ``` ```bash Windows npm install -g @railway/cli ``` ```bash railway login ./scripts/railway_up.sh ``` The script provisions PostgreSQL, configures environment variables, and deploys your system. 1. Open [os.agno.com](https://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

Extend the system with custom agents Connect to Slack, Gmail, Calendar, and 100+ integrations Learn more about the production runtime Configure how agents learn and remember