Getting Started

Short, opinionated walk-through. For the full list of commands, architecture, and hardening details, read the README. This page is the thing to read before you run the installer.

  1. Prerequisites
  2. Before you start: read MODELS.md
  3. Phase 1 — Bootstrap the Mac Mini
  4. Phase 2 — Install from your MacBook
  5. First run
  6. Troubleshooting

Prerequisites

Hardware

  • Apple Silicon Mac (M2 Pro or later recommended)
  • 24 GB+ unified memory for the default 26B-parameter model
  • macOS 14 (Sonoma) or later
  • FileVault enabled (the installer hard-requires it — all secrets at rest rely on it)
  • An external drive for backups (optional but strongly recommended)
  • A MacBook to drive the installer over SSH (or run --local on the Mini itself)

Accounts

  • A domain name you control
  • Cloudflare account (free)
  • Resend account (free tier: 3k emails/month, shared between sent and received)
  • Telegram bot token, via @BotFather
  • Your Telegram user ID, via @userinfobot
  • Tailscale account (free for up to 3 users / 100 devices)
  • Optional: iCal URLs from iCloud / Google / M365 for read-only calendar sync

Full shopping-list table with pricing and links lives in the README’s Requirements section. Don’t front-load all the sign-ups — the wizard opens the right browser tab at the right moment, and you’ll forget which is which if you try to pre-register everything.

Before you start: read MODELS.md

The default model is Gemma 4 26B-A4B from Google. It is not open source. Loading it means accepting Google’s Gemma Terms of Use and Prohibited Use Policy.

You, the operator running yabby on your own hardware, are the licensee. yabby does not redistribute weights, does not mediate the licensing relationship, and does not warrant the model’s behaviour. If that’s not OK with you, there are Apache-2.0 fallbacks documented with their caveats.

This is non-negotiable reading before you run the wizard: docs/MODELS.md.

Phase 1 — Bootstrap the Mac Mini

Boot the Mini with keyboard and monitor attached. Sign in as the user who will own the install. Paste this into Terminal:

curl -fsSL https://getyabby.com/bootstrap.sh | bash

In roughly two minutes it installs Xcode CLT, Homebrew, Tailscale, joins the Mini to your tailnet, flips macOS into server mode, and enables SSH with a temporary password. At the end it prints the Mini’s tailnet hostname and the SSH command your MacBook will use next. Write it down.

Phase 2 — Install from your MacBook

On your MacBook:

curl -fsSL https://getyabby.com/install.sh | bash

This clones the repo, installs dependencies, deposits an SSH key on the Mini, and launches the wizard. The wizard runs locally but drives the Mini remotely. Total time: ~15 minutes plus the model download (~18 GB from Hugging Face — pace yourself on a slow connection).

Full flow with every prompt and what it means is in the README’s Quick Start section.

First run

When the wizard finishes it prints a summary with URLs, your Telegram bot handle, and health-check commands. What to expect next:

  1. Open Telegram, find your bot, send /start.
  2. Send a test message (“what time is it?”) and wait for a reply. If you get one, the inference backend, the gateway, and the Telegram channel are all wired up correctly.
  3. The first scheduled daily post lands at 3 pm local time. Don’t panic if nothing happens the first afternoon — check the cron log with scripts/health-check.sh.
  4. Inbound mail starts flowing once your domain’s MX is pointed at Resend (the wizard prints the exact records). Until then the agent has nothing to triage.

Troubleshooting

If something doesn’t work — and something always doesn’t work the first time — file an issue. Include the output of scripts/health-check.sh and the last 50 lines of ~/Library/Logs/yabby/mlx-vlm.out.log.

Open an issue