Tutorials
Installation & first launch
From the download to a working workspace.
By the end of this page OOMU will be installed, set up with a model that runs on your Mac, and answering questions without sending anything anywhere.
Before you start
| You need | Why |
|---|---|
| A Mac with Apple Silicon (M1 or later) | OOMU is a native Apple Silicon application. It does not run on Intel Macs. |
| macOS 14 (Sonoma) or later | The minimum system version the application declares. |
| 8 GB of memory, more is better | The local model runs in memory you already have. |
| A few gigabytes of free disk | For the application and the models it verifies. |
You do not need an account, a credit card, or an API key. A cloud provider is optional, and you can add one later.
Step 1: Install
Download OOMU, drag it to your Applications folder, and open it.
Install it properly, in Applications. Two features check whether OOMU is running from a real application bundle: background work, which registers a macOS Login Item, and software updates. Running the app from your Downloads folder quietly disables both.
Step 2: Accept the license
The first screen is the OOMU Standard License (Version 2.0). The full terms are on screen, not behind a link. Accept and continue moves on; Decline and quit closes the application and stores nothing.
Nothing else in OOMU works until the license is accepted, including model installation.
Step 3: Set up your models
The setup screen is titled Set up OOMU, with the subtitle "Your models stay on this Mac. Cloud service keys are stored safely on this Mac." It has four rows.
| Row | What it is | Required? |
|---|---|---|
| Understanding model | The router. Reads every request and chooses the right path. | Yes |
| Assistant on this Mac | The model that handles everyday reasoning privately. | Yes |
| Image understanding | Lets the local assistant read images you attach. | Optional |
| Cloud model | A cloud service for work that benefits from cloud reasoning. | Optional |
Choosing the model files
For each of the first three rows OOMU names the exact file it expects and opens the standard macOS file picker so you can point at it. In this beta you supply the model files yourself; they are not bundled inside the application.
| Role | Expected file | Size | Upstream |
|---|---|---|---|
| Understanding model | OOMU-Qwen3-0.6B-Production-MicroRouter-Q8_0.gguf | ~610 MB | Qwen3-0.6B, Apache-2.0, fine-tuned by OOMU |
| Assistant on this Mac | gemma-4-E2B_q4_0-it.gguf | ~3.1 GB | Gemma 4 E2B QAT (Google Q4_0_QAT), Apache-2.0 |
| Image understanding | gemma-4-E2B-it-mmproj.gguf | ~940 MB | Gemma 4 E2B QAT projector, Apache-2.0 |
OOMU hashes every file you select and compares it against the SHA-256 in its embedded manifest. A file that does not match exactly is rejected and the row stays unfinished. That is what the footer means by "OOMU verifies every selected model before using it."
Connecting a cloud service, if you want one
Pick a service and a model, paste the key, and choose Connect. OOMU makes a real round trip to the provider before accepting the key. If the round trip fails, nothing is saved. Once it succeeds, the key goes into your macOS Keychain and the row shows the provider and model that verified.
Skip this row entirely if you would rather stay local. You can add a service later in Settings → Models, or from Connections.
The privacy notice and the diagnostics checkbox
Below the rows sits the Application Privacy & Data Notice, in five short sections: what stays on this Mac, where your credentials go, what choosing a cloud service means, what deleting actually removes, and optional diagnostics. It is the same notice you can reopen later in Settings → Storage & Privacy, so nothing here is a one-time screen you had to read carefully the first time.
With it sits one checkbox, Share anonymous diagnostic metrics, and it is unchecked.
Leave it unchecked and OOMU sends no analytics, now or ever, with no part of the application withheld for that choice. Check it and three lifecycle events can be sent (app_launch, first_run_completed, session_start) alongside a random installation identifier. Never your prompts, your documents, your file names, or your name. You can change the answer at any time in Settings → Storage & Privacy, and withdrawing consent discards the identifier rather than parking it.
Finishing setup does not turn it on. It is a separate choice, on purpose.
Choose Finish setup once the understanding model and the local assistant are both ready.
Step 4: Find your way around
OOMU opens on Chat. The sidebar has four destinations, with two more beneath them.
| Sidebar | What it holds |
|---|---|
| Chat | Conversations. Tabs across the top switch to Agents, Workflows, and Activity. |
| Projects | One place per case, client, or job. A Documents tab holds the files OOMU created. |
| Connections | Apple apps, Google Workspace, cloud AI providers, tools on this Mac, and messaging channels. |
| Mods | The .oomu packages you have installed. |
| On this Mac | The ledger: how much work ran locally, how much ran in the cloud, and what that saved. |
| Settings | Models, security, Mac access, storage and privacy, GDPR & EU AI Act disclosures, background work, appearance, language, updates, and your profile. |
Two shortcuts are worth learning immediately:
- ⌘K opens the quick switcher, which searches your chats, agents, workflows, and every destination in the app.
- ⌘⇧Space opens the Quick Launcher from anywhere on your Mac, even when OOMU is not in front.
Step 5: Ask your first question
The empty chat asks "What would you like to do?" and offers three starting points:
- Weekly Brief: summarize recent activity and schedule.
- Summarize Folder: pick a local folder and analyze it on this Mac.
- Help with Email: draft and triage unread messages.
Or type anything into the composer. Watch the header while it works: "Understanding your request…" is the router deciding where the request should go. Once it settles, the chat shows the route it chose.
The Model control above the composer offers three choices:
| Choice | Behavior |
|---|---|
| Automatic | OOMU chooses this Mac or your default cloud model for each request. |
| On this Mac | Reasoning never leaves your Mac. |
| Cloud | Always use the exact service and model you select. |
New chats start on Automatic. If you skipped the cloud service, everything runs locally regardless.
While a reply is in flight you are not locked out. Steer injects a correction into the running turn, Queue next lines up the following task, and Stop cancels.
Step 6: Tell OOMU who you are
Settings → Profile is worth ten minutes. Your role, expertise, priorities, preferred tone, response length, and boundaries all become standing context, so you stop repeating yourself. The panel puts it plainly: "The more OOMU knows about your work, the less you'll have to repeat yourself."
The same screen holds Memory: the things you have explicitly asked OOMU to remember, each labeled with its scope (This project or Everywhere) and a Forget button.
What you have now
- OOMU installed in Applications, license accepted
- A verified understanding model and local assistant
- An encrypted database on this Mac, keyed to your Keychain
- A first conversation underway
Where to go next
- Setting up a project: the right way to keep a case or client together.
- Working fast: the Quick Launcher, quick actions, and the quick switcher.
- How OOMU picks a model: what the understanding model is actually deciding.
- Connecting services: Apple apps, Google Workspace, and more.