Magento 2 & Hyvä, done right by one developer.

Both. Everything in the build runs on stock Magento 2.4.7+ Open Source — there’s no Adobe Commerce-specific API used. The observer hooks into catalog_product_save_after, which is identical on both editions. The MessageQueue layer uses Magento’s built-in MessageQueue module (also Open Source). The only Adobe Commerce-only consideration is the Image Editor extension Adobe ships, which you’d disable to avoid duplicate processing. Bottom line: Open Source merchants get the full benefit without paying for Adobe Commerce just for image handling.

MCP is an open protocol Anthropic shipped in November 2024 that lets large language models talk to external tools and data sources through a standard interface. Think of it as USB-C for AI — one socket, many devices. For Magento, MCP means Claude, ChatGPT, or Cursor can query your catalogue, check stock, summarise yesterday’s orders, or draft a discount code without you writing five different REST integrations. The protocol crossed tribal lines fast: OpenAI and Google both adopted it in early 2025, and Adobe made it the default agent protocol for Commerce at Summit 2026. That puts MCP in the same “assume it’s there” bucket as JSON-RPC or OAuth — you build for it once and every major AI client gets your Magento data for free.

The honest minimum is 12 weeks of daily sales data per SKU — that’s enough for Prophet to lock onto a weekly pattern and produce a usable 4–6 week forecast. With 26 weeks you start getting yearly seasonality. With 52+ weeks (one full annual cycle including your peak season) Prophet really shines and you can forecast 90 days out with sub-15% MAPE on most retail SKUs. Below 12 weeks, do NOT use Prophet — fall back to a 28-day moving average plus a manual safety-stock multiplier. The model will overfit garbage if you feed it too little.

No — they are different products from the same company. Hyvä Theme is a free, open-source (OSL3) Tailwind + Alpine storefront frontend for Magento, released to free in November 2025. Hyvä Commerce is a paid commercial suite of admin, media, and CMS modules that sits on top of Magento Open Source. You can run Theme without Commerce, but most stores that buy Commerce also use Theme.

Yes — in the segments where it’s strongest. Magento (Open Source + Adobe Commerce) will dominate enterprise B2B, multi-store, regulated industries, and EU-compliance-heavy commerce through 2030 and beyond. Where it bleeds is the SMB / DTC segment under $5M GMV, which Shopify already won and now cements with Sidekick + Hydrogen. Magento survives, but its addressable market shrinks: from “everyone” to “serious B2B + custom-heavy enterprise.” That’s still a multi-billion-dollar segment globally. The platform isn’t going anywhere; the merchants who choose it just look more specific.

No — Claude Code is paid, but the entry tier is approachable. The cost has two parts:

• Claude Pro subscription: $20/mo. This unlocks Claude Code access in the IDE/CLI plus a baseline message allowance.
• Metered API usage: beyond the included allowance, you pay per token (currently ~$3 per million input tokens and ~$15 per million output tokens for Sonnet, ~$15/$75 for Opus).

Real-world bills:

• Solo dev, 4 – 6 hours/day Claude Code use: $25 – $80/mo all-in
• Small team (5 devs), heavy daily use: $300 – $700/mo for the whole team
• Agency, 15 devs + CI workflows + sub-agents: $1,000 – $2,500/mo

Compare to Copilot ($19/mo flat per seat, no metering) or Cursor ($20/mo + their own model API on top, similar metered model). Claude Code is rarely the cheapest, but it’s usually the highest-leverage on a per-hour-saved basis.

registration.php tells Composer's autoloader where the module lives on disk — it runs at bootstrap and registers the namespace + path with ComponentRegistrar. Without it, Magento literally cannot find your code. etc/module.xml tells Magento's module manager the module exists, what its setup_version is, and its load-order dependencies via <sequence>. You need both: registration.php for the autoloader, module.xml for module:enable. A common bug is a working registration.php with a missing module.xml — the class loads, but DI etc/di.xml is silently ignored because the module is not enabled.