Quick Start

Get Elmo running on your infrastructure in under 5 minutes using the CLI.

Prerequisites

Docker — Docker Engine 24+ with Docker Compose v2

Node.js — 18.x or later (for the CLI)

At least one AI provider API key (OpenAI or Anthropic)

Install the CLI

npm install -g @elmohq/cli

Initialize Your Instance

Run the interactive setup wizard:

elmo init

The wizard walks you through:

Config directory — Where to store your elmo.yaml and .env files (default: ./elmo)

PostgreSQL — Run Postgres in Docker (recommended) or provide an existing DATABASE_URL

AI Providers — Enter your API keys for OpenAI, Anthropic, and/or DataForSEO

Start — Optionally start the stack immediately

Once complete, Elmo generates two files in your config directory:

File	Purpose
`elmo.yaml`	Docker Compose configuration for all services
`.env`	Environment variables, secrets, and API keys

Start Elmo

If you didn't start during init, bring everything up with:

elmo start

This pulls the Docker images, starts all services, and waits for them to become healthy. Once ready, open http://localhost:1515 in your browser.

System Architecture

Loading diagram...

Service	Role
Elmo CLI	Generates config files, then runs `docker compose up`
Web	Dashboard UI and REST API (port 1515)
Worker	Background scheduler — queries AI models and processes results
PostgreSQL	Shared database for brands, prompts, snapshots, and job queue
LLM Providers	OpenAI, Anthropic, Google — queried by the worker on a schedule

CLI Commands Reference

Once Elmo is running, these commands help you manage it:

# Check service health
elmo status

# View live logs
elmo logs -f

# View logs for a specific service
elmo compose logs -f web

# Stop all services
elmo stop

# Run any docker compose command
elmo compose ps
elmo compose down

What's Next

With Elmo running, head to the User Guide to create your first brand, configure prompts, and start tracking AI visibility.

Was this page helpful?