---
title: Operate
description: Operate is a self-hosted platform for running AI coding agents against your own repos, with full visibility into what they changed and why.
product: Marketplace
url: https://docs.digitalocean.com/products/marketplace/catalog/operate/
last_updated: "2026-10-06"
---

> **For AI agents:** The documentation index is at [https://docs.digitalocean.com/llms.txt](https://docs.digitalocean.com/llms.txt). Markdown versions of pages use the same URL with `index.html.md` in place of the HTML page (for example, append `index.html.md` to the directory path instead of opening the HTML document).

# Operate

Generated on 6 Oct 2026 from [the Operate catalog page](https://marketplace.digitalocean.com/apps/operate)

Operate monitors your production systems, identifies issues, runs a root cause analysis, and drafts the fix. Problems get investigated before anyone reports them. It builds a rich context layer for AI agents from the systems you already run: source control, databases, your observability stack, ticketing, and more. It also ships with Slack and MS Teams apps that let anyone on the team, including non-engineers, ask for an RCA from the tools they already use.

Unlike traditional SaaS, Operate is a self-hosted Docker image running inside your own infrastructure. Read-only, fully auditable, and your data never leaves your stack.

This Droplet bundles MongoDB and Redis, so it comes up with no external dependencies. Attach a DigitalOcean Volume to keep your database and case history through a Droplet rebuild.

## Software Included

| Package | Version | License |
|---|---|---|
| Ubuntu | 24.04 | Mixed (GNU GPL v2 and other open-source licenses) |
| Docker Engine | latest | Apache-2.0 |
| Docker Compose plugin | latest | Apache-2.0 |
| Caddy | latest | Apache-2.0 |
| Operate | latest | MIT |
| MongoDB | 5.0 | SSPL |
| Redis | 7.4 | RSALv2/SSPLv1 |

## Creating an App using the Control Panel

Click the **Deploy to DigitalOcean** button to create a Droplet based on this 1-Click App. If you aren’t logged in, this link will prompt you to log in with your DigitalOcean account.

[![Deploy to DO](https://www.deploytodo.com/do-btn-blue.svg)](https://cloud.digitalocean.com/droplets/new?image=operateengineeri-operate)

## Creating an App using the API

In addition to creating a Droplet from the Operate 1-Click App using the control panel, you can also use the [DigitalOcean API](https://docs.digitalocean.com/reference/api). As an example, to create a 4GB Operate Droplet in the SFO2 region, you can use the following `curl` command. You need to either save your [API access token](https://docs.digitalocean.com/reference/api/create-personal-access-token/index.html.md) to an environment variable or substitute it in the command below.

```shell
curl -X POST -H 'Content-Type: application/json' \
         -H 'Authorization: Bearer '$TOKEN'' -d \
        '{"name":"choose_a_name","region":"sfo2","size":"s-2vcpu-4gb","image":"operateengineeri-operate"}' \
        "https://api.digitalocean.com/v2/droplets"
```

## Getting Started After Deploying Operate

Open `https://your_droplet_public_ipv4/` in a browser to reach Operate’s onboarding page. It will ask you to create an admin account, specify Operate App ID (can be obtained via operatex.dev, used for telemetry and billing purposes) and connect your existing systems such as Github, database to help AI agents build a rich context layer to perform root cause analysis.

**Managing over SSH:** `ssh root@your_droplet_public_ipv4` gets you onto the box. The stack lives at `/opt/operate` and runs as `operate.service`:

- `systemctl status operate.service` - check it’s running
- `docker compose --env-file /opt/operate/operate.env -f /opt/operate/app/docker-compose.yml logs -f` - tail logs

**Data storage:** by default MongoDB, Redis, and Operate’s own data live in Docker volumes on the Droplet’s boot disk, durable across reboots but not Droplet destruction. For production, attach a DigitalOcean Block Storage volume when creating the Droplet, first boot detects it automatically, formats and mounts it at `/mnt/operate-data`, and migrates all data there with no configuration needed. Check current storage status any time via the SSH login banner, or see [Data Volume Docs](https://operatex.dev/docs/digitalocean#data-volume) for details and how to attach one later.