Install & first launch

Three steps to get Spendif.ai running on your computer: download, install, first launch. All offline, no account required.

โœจWhat you get

1Download for your system

Official installers are published as assets on each GitHub Release. Pick the format for your OS.

๐ŸŽ

macOS

SpendifAi-*.dmg
Download DMG
macOS 12 Monterey or later. Apple Silicon + Intel.
๐ŸชŸ

Windows

SpendifAi-*.msix
Download MSIX
Windows 10 1809+ / Windows 11. Sideload + trusted cert needed during pre-alpha.
๐Ÿง

Debian / Ubuntu

spendifai_*_amd64.deb
Download .deb
Ubuntu 22.04+, Debian 12+, Mint 21+.
๐ŸŽฉ

Fedora / RHEL

spendifai-*.rpm
Download .rpm
Fedora 40+, RHEL 9+, Rocky / Alma 9+.

Looking for a specific version? See all releases ยท Source code: drake69/spendif-ai.

2Install

macOS โ€” DMG

1. Double-click the downloaded .dmg.

2. Drag Spendif.ai.app into the Applications folder.

3. Eject the DMG (Cmd+E) and launch the app from Launchpad.

If you see "Spendif.ai cannot be opened because the developer cannot be verified" (build not yet signed): right-click the app โ†’ Open โ†’ confirm.

๐Ÿ“ท Screenshot
assets/screenshots/macos-dmg-dragdrop.png
(drag & drop from DMG to Applications)

Windows โ€” MSIX

1. Double-click the downloaded .msix.

2. The built-in App Installer opens. Click Install.

3. The app appears in the Start Menu โ€” launch from there.

If you see "Unknown publisher": open PowerShell as admin and import the certificate once (see the guide).

๐Ÿ“ท Screenshot
assets/screenshots/windows-msix-install.png
(Windows App Installer dialog)

Linux โ€” .deb / .rpm

From the terminal:

sudo apt install ./spendifai_*.deb  (Debian/Ubuntu)

sudo dnf install ./spendifai-*.rpm  (Fedora/RHEL)

The postinst installs uv, creates the venv, downloads the model and writes .env. Full guide: installation docs.

๐Ÿ“ท Screenshot
assets/screenshots/linux-deb-install.png
(dpkg/dnf terminal output)

3First launch

On first launch Spendif.ai sets up its environment โ€” it's the longest step, but happens only once.

โฑ Time required: depends on your connection speed (usually 5-15 minutes). Free disk space required: ~5 GB. Good news: you can start filling in the wizard right away, the model downloads in parallel.

3a. Splash + AI model download (in parallel)

Double-clicking opens a native window with a splash screen. Spendif.ai detects your RAM/VRAM and kicks off a background download of the LLM best suited for your hardware (Qwen 2.5, Gemma 3 โ€” sizes from 1 to 8 GB).

The model lives at ~/.spendifai/models/ (macOS/Linux) or %USERPROFILE%\.spendifai\models\ (Windows) and survives reinstalls. The configuration wizard appears within seconds, without waiting for the download to finish.

๐Ÿ“ท Screenshot
assets/screenshots/splash-download-progress.png
(splash + model download progress)

3b. Onboarding wizard โ€” 4 steps

While the model continues downloading in the background, the configuration wizard guides you through 4 steps:

1. Language โ€” taxonomy, date format, number separators.
2. Holders โ€” your name and the variants your bank uses.
3. Accounts โ€” current account, cards, cash.
4. Summary + Start โ€” everything is written only here, no partial persistence.

Every step shows a live download banner at the top (e.g. "๐Ÿ“š 78% ยท ~3 min"). On the final summary, the Start button stays disabled until the model is 100% โ€” so the Import page works immediately when you reach the app. Everything is changeable from Settings later.

๐Ÿ“ท Screenshot
assets/screenshots/onboarding-step-1-language.png
(wizard step 1 โ€” language selection)

3c. App ready

On confirm the wizard creates the SQLite database and lands you on the Import page. From here you load your first bank CSV/XLSX files.

From then on the flow is: double-click โ†’ splash (1-2 seconds) โ†’ app. No more downloads, no more wizard.

๐Ÿ“ท Screenshot
assets/screenshots/app-ready-import-page.png
(app ready, Import page)

Having trouble?

Full documentation: install guide ยท user guide ยท macOS deep-dive ยท Windows deep-dive.

Bugs, questions, requests: open a GitHub issue.

What's coming next

Spendif.ai is in alpha. The features we add next are decided together with the people using the app today: no speculative work, no roadmap dictated from above.

Features under evaluation based on alpha-tester feedback:

Would one of these help you? Tell us in GitHub Discussions. When enough requests stack up on the same feature, it moves to the top of the queue.