Get started with Kaidera OS

Before you start

Commercial macOS installation supports Apple-silicon Macs running macOS 14 or later. Allow about 50 GB of free storage and internet access for first setup and activation. The Operator manages Docker and Python setup when needed.

• 8 GB RAM is recommended; 4 GB is the minimum.
• Administrator access is needed only if Docker Desktop must be installed.
• Homebrew, Git, GitHub CLI, Xcode, npm, and a system Python are not required for the commercial macOS package.
• Other editions and operating systems have separate installation instructions.

Install

The commercial macOS release uses one website-hosted Installer package. Open the package, install Kaidera OS Operator into Applications, then run Install or Repair from the Operator.

• If Docker is absent, review Docker terms in the Operator before selecting Accept and Install.
• The Operator verifies the pinned Docker download and signing team before requesting administrator approval.
• Managed Python 3.12 is installed through the pinned uv runtime.
• The managed Kaidera OS runtime is staged under ~/Library/Application Support/Kaidera OS/.

Start the console

Install or Repair starts Cortex and the console, registers the LaunchAgent, and waits for health and authentication checks. When setup succeeds, use Kaidera OS Operator in the menu bar and select Open Console.

Confirm health

Before configuring workers, confirm the console, Cortex API, and app database are reachable. A healthy runtime prevents confusing empty graphs, missing history, or failed worker dispatch.

• Console: http://localhost:8765 should load the Kaidera OS UI.
• Cortex API: the memory backend should report healthy in Settings or the Dashboard.
• App database: Settings should show the store connected.
• Provider path: at least one configured model provider should be available before model-backed workers run.

First-run setup

A fresh install starts empty. The first-run flow collects the project name and key, workspace root, project scope, first lead worker, initial team template, cadence settings, and provider preferences.

What to do next

Bring one project online first. Keep propose mode on while you validate the project root, worker roster, provider settings, and Cortex memory. Turn on broader autonomy only after the first approved runs behave as expected.