The DevOps Agent and your code

How the agent deploys repositories you already have, what it asks before acting, and when the code it cloned is deleted.

The DevOps Agent deploys software that already exists. You give it one or more GitHub or GitLab repositories; it reads them, draws how the parts fit together, proposes a plan, and deploys once you approve. It does not write your application - that is the other way into AI Studio.

How a deployment goes

Choose the repositories. In AI Studio, pick Deploy with the DevOps Agent and select the repositories that make up the system. If it is split in two - a frontend here, an API there - choose both.
The agent reads the code. It clones the repositories into the project's private sandbox and reads them there.
It draws the architecture. The Architecture tab shows the services it found and how they talk to each other, and flags anything the system needs that is missing.
It proposes a plan. Each component, its size and what it costs. Nothing is deployed until you approve it, and what it runs afterwards is held to the plan you approved.
It deploys, and records how it ended - succeeded or failed.

When a deployment needs a secret - an API key, a password - the agent names it and you supply the value. The value goes to the secret store; the model never sees it.

Your code is not kept

The repositories cloned into the sandbox are your code, read in order to deploy it. Once that work is over there is no reason for a copy to stay on the platform, so it is deleted. Specifically, the sandbox and every file in it are removed after 120 minutes without use, where an ordinary project would only be paused.

Use means a message, something the agent does, or simply the project being open in your browser: as long as it is on your screen, its sandbox is neither paused nor deleted. A deployment that finished, a turn that failed or one you stopped do not remove anything by themselves - you can carry on straight away.

No archive is made. This is the difference from a project you build in the Studio, whose files are kept as a .zip and restored on the next start.

What is not deleted: the applications, databases and services the agent deployed, the architecture drawing, the plan, and the conversation. Your repositories on GitHub or GitLab are of course untouched.

Carrying on later

Come back to the conversation whenever you like. When you send a message, the agent starts a fresh sandbox by itself and clones the repositories again before continuing - you do not need to start anything. Expect the first step after a break to take a little longer for that reason.

If the sandbox fails

A banner above the panes gives the reason and a Restart button, and the power icon at the top right has the same controls as any Studio project. See The AI Studio sandbox.

Guide

What ISOGrid is — A cloud platform built in Algeria, for teams who want to ship without running servers.

Getting started — From an account to something running on the internet.

Your experience level — Three questions at first sign-in decide how your home page is laid out and how the assistant talks to you - and nothing else.

Deploying an application — From a repository to a running address, and what happens at each step.

Git repositories — Connecting GitHub or GitLab, deciding who in the organization may build from your repositories, and what happens when you leave.

Addresses and domains — The address every application gets, using your own name instead, and what breaks when DNS is wrong.

Databases — Ordering one, what each arrangement survives, and why replication is not a backup.

Private clusters without lock-in — What runs on your machines is standard Docker Swarm or Kubernetes, and it keeps running if you leave.

Supabase — A complete backend on PostgreSQL in one deployment - what you get, which database to put behind it, and where your keys are.

Roles, permission groups and access — The three layers that decide what each member may do, the groups every organization starts with, and the rules that stop anyone climbing.

The AI Studio sandbox — The workspace behind every Studio project - starting, pausing and restarting it, what happens when it is left unused, and how your files come back.

The DevOps Agent and your code — How the agent deploys repositories you already have, what it asks before acting, and when the code it cloned is deleted.

When things go wrong — The failures you are most likely to meet, what each one actually means, and what to do.

Command line

Installing the CLI — One command on Linux, macOS or Windows, a checksum on every download, and how to update or remove it.

Command reference — Every command group, what it does, and where each one is explained in full.

Automating applications — Create, configure, deploy and remove applications from a terminal or a script, with every flag explained.

Deploying from CI/CD — Deploy on every push from GitHub Actions or GitLab CI/CD, with a narrow credential and a job that fails when the deployment does.

Repositories, groups and access — Decide who can build from a repository, manage permission groups and read who holds what, from the terminal.

Policy

Availability and support — What the platform commits to, what it does not, and how to reach a person.

Acceptable use — What you may run, what you may not, and what happens if a line is crossed.

Privacy — What personal data ISOGrid keeps, why, who else sees it, how long it is kept, and how to delete your account.