Installation and Setup

This page walks you through getting the AI Kit running from zero to a working workspace. It covers the two main delivery modes and the first-time setup assistant.

Choosing a delivery mode

Mode	What it means	Good for
Cloud (managed)	We run the AI Kit for you. You receive a URL and an invitation email.	Teams that want zero infrastructure work.
On-premise (self-hosted)	You run the AI Kit on your own servers — typically as a single Docker container.	Organizations with strict data residency or compliance requirements.

The end-user experience is identical. The only difference is where the data lives and who keeps the lights on.

If you are using the cloud version, skip ahead to The first-time setup assistant.

On-premise installation

Prerequisites

• A Linux server (or any host that runs Docker). A small virtual machine with 4 CPU cores and 8 GB of RAM is enough for a pilot.
• A persistent storage location for the AI Kit's data — config, jobs, knowledge content. Plan for a few gigabytes at the start and grow with usage.
• Outbound internet access if you intend to use external AI providers (OpenAI, Anthropic, Mistral). If your environment is air-gapped, you can run a self-hosted Ollama instead — see Models → Ollama (self-hosted).
• A reachable hostname or IP. If end users will use the platform from outside the network, place a TLS-capable reverse proxy in front of it.

Run the container

The AI Kit ships as a single Docker image that serves both the application and the web interface on port 3000. Mount one host directory as the data volume:

docker run -d \
  --name aikit \
  -p 3000:3000 \
  -v /opt/aikit/data:/data \
  -e AIKIT_CONFIG_DIR=/data/config \
  -e AIKIT_JOB_DIR=/data/job \
  schnelldigital/aikit:latest

The host directory (/opt/aikit/data in the example) holds all persistent state. Back it up the same way you back up any business-critical data store.

📷 SCREENSHOT: Output of a successful docker run followed by the AI Kit's startup log line indicating it is listening on port 3000.

Reach the user interface

Open http://<your-host>:3000/ in a browser. On the very first visit you land on the setup assistant.

For network and port specifics — including which ports must be reachable and what outbound connections the AI Kit needs — see Security → Network Access.

To let people sign in with their company account (Microsoft Entra ID, Google Workspace and other OpenID Connect providers) or to require a second factor, see Security → Single Sign-On and Second Factor.

The first-time setup assistant

The setup assistant runs at first launch and walks you through everything the installation needs before it can be used. The steps appear as a list on the left; you can click back to any step you have already seen — the assistant never traps you in a dead end.

Not every step appears every time. The assistant shows only the steps your situation actually requires, plus the ones you have already visited in this run. A fresh installation typically sees all of them; someone adding a further workspace to a running installation sees only the last three.

📷 SCREENSHOT: Setup assistant landing page with the step list visible on the left.

License Setup

You can either:

• Start a trial — no license file required, full functionality for the trial period.
• Upload a license file — for production installations. Your license file was delivered when you purchased the platform.

If the upload is rejected, the assistant says why — an expired file or one issued for a different installation is reported as such, not swallowed.

If neither option fits your situation, contact support directly from the assistant.

Trial mode

Appears when the installation is running on a trial license. It explains the limits and offers the upgrade path. Nothing here blocks you; you can move on.

Create your admin account

The first user, who will administer this installation and can invite everyone else.

• Email address — also used as the login.
• Full name and Preferred language.

Click Create account. A one-time password is then sent to the address; enter it and click Verify one-time password. The account is signed in right away.

If the installation uses single sign-on, no code is sent: the assistant forwards you to your identity provider instead. Use the email address your company account has there — the assistant continues after you sign in.

Once this account exists, the setup steps close: nobody can create an account or change the license without logging in. Further users join by invitation, and later license changes need an administrator.

Create Your Workspace

• A workspace address — a short, URL-safe identifier (for example acme). The field normalizes what you type: spaces and special characters become hyphens, capitals become lowercase. Availability is checked while you type, and the state under the field says which of the three it is: being checked, available, or already taken. Minimum three characters.
• A display name — what users will see in the workspace switcher (for example "Acme Industries").

The workspace address cannot be changed later, so pick something stable.

📷 SCREENSHOT: The Workspace step of the setup assistant with the address field showing "available".

Set up Models & Knowledge

A guided pass through connecting your first AI model and, optionally, your first knowledge base. Both can be done later from their own tabs — this step is an offer, not a gate.

Create Your First Workflow

The last step offers to build a first automation, or to go straight to the dashboard. Either way the setup is complete after it.

Recommendations

• ✅ Run the AI Kit behind a reverse proxy with TLS. Browsers and webhooks both behave better over HTTPS.
• ✅ Back up the data volume on the same schedule as your other business data.
• ✅ Document the workspace address and admin email somewhere outside the AI Kit — these are the keys to recovery if you need to migrate or restore.
• ⚠️ Pick the workspace address carefully. Many things — URLs, file paths, webhook addresses — embed it, and it cannot be changed afterwards.
• ⚠️ The trial period is generous but finite. Plan to upload a license file before it expires; running out of license puts the workspace into a read-only state.
• ❌ Do not store secrets in environment variables that get logged or committed. Use the platform's built-in secured fields for credentials inside automations.
• ❌ Do not delete files inside the data volume directly. Use the platform's administration tools to remove automations, jobs, or users.

What to do next

• Add your first AI model — Models → Create a New Model.
• Invite additional users — Administration → Manage Users.
• Plan licensing — Licensing below.