Project and task management decision

Morgen

A narrow, self-hosted or small SaaS replacement that syncs a couple of calendars and runs an LLM-based daily-scheduling loop is realistic for a small team, but reproducing Morgen’s cross-platform polish, broad integrations, scheduling pages, and Swiss-hosting/GDPR promises at production quality is substantial work and not covered by a minimal build.

Visit website
Subscription$25/month ✓ verified
Initial build80 hours
Monthly upkeep8 hours + $50
Evidence2/3 runs agree

No open-source build does this yet

Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.

What a replacement has to do

  • Sync user calendars and tasks → generate a prioritized daily plan with an LLM → propose time-blocked schedule and let user accept/adjust → write scheduled events back to calendar

What it still won’t have

  • Swiss-hosted data residency & official GDPR-hosting claims
  • Polished cross-platform desktop & mobile apps shipping on Win/Mac/Linux/iOS/Android
  • Breadth and depth of existing integrations and edge-case handling for many calendar providers
  • Team features requiring minimum-seat billing, admin/billing flows, and mature UX polish
  • Any proprietary AI assistant behavior implemented server-side by Morgen (Kai) not documented in pages

What remains hard

  • Compliance and regulationSwiss-hosted & GDPR compliant
  • Compliance and regulationWe store all data in Switzerland or in the European Union.
Read the build prompt

First-year cost

Keep paying

Paying ischeaper in year one.

On cash alone, building overtakes the subscription at 3 seats.

Paid seatsseats

Money you would actually spend

Keep paying

Subscription price × seats × 12

Build it

AI build APIs + hosting

Time you would spend

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal web-first Morgen-like app using Next.js (React) + Tailwind, Postgres, and a worker queue (BullMQ). Implement: 1) OAuth calendar sync for Google Calendar and Outlook (read/write events), 2) a simple task importer for Todoist/Notion via their APIs, 3) an AI Planner service that queries OpenAI-style LLM to prioritize tasks and assign time blocks respecting calendar availability, buffer rules, and travel time, 4) a calendar UI with drag-and-drop time-blocking and accept/reject scheduling flow, and 5) simple booking link pages that check availability and create events. Out of scope: native desktop installers, iCloud/Fastmail integrations, multi-tenant billing/admin, Swiss data residency. Include tests for calendar sync, task import, and AI Planner outputs; add error handling for OAuth expiry, API rate limits, and conflicting writes; provide Dockerfile and deployment manifest for one cloud region.
How we checked2 sources · 2/3 runs agreed · evidence score 53

How the score was reached

  • Partly verdict base52
  • 2 cited sources+1
  • Price verified on pricing page+3
  • Hard moats found in the evidence-3
  • Evidence score53

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time — so the same evidence always produces the same number.

How scoring works →

Cited sources · 2

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 2 moats quoted from the page