Morgen
Unify calendars and tasks, create booking pages, and plan work across time zones
The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Morgen, unify calendars and tasks, create booking pages, and plan work across time zones. The hard boundary is multiple calendar providers, task integrations, mobile apps, and sync reliability, plus cross-device reliability and workflow polish.
Build verification: not recorded. How we judge buildability
What you give up
- multiple calendar providers, task integrations, mobile apps, and sync reliability
- perfect mobile sync
- calendar and email integrations
- shared workspaces
- behavioral coaching polish
Why people still pay
People still pay for Morgen because task software is sticky because trust, speed, and ubiquitous capture matter more than the database schema. The recurring cost buys recurrence edge cases, notifications, sync conflicts, calendar APIs, mobile capture, and backups, not just the visible interface.
Your build guide
The stack, security requirements, and agent rules for a focused replacement.
Before you start
- Google OAuth credentials, a registered HTTPS callback and calendar access granted by the owner. Confirm the provider scopes and publishing requirements before adding guests.
- Implementation components: Next.js App Router and TypeScript for server-rendered pages and validated mutations. PostgreSQL with Drizzle migrations; Better Auth sessions for a small private workspace. One Google Calendar OAuth adapter, a timezone-aware date library, and an outbox worker for email/ICS delivery.
- Scope boundary: multiple calendar providers, task integrations, mobile apps, and sync reliability; perfect mobile sync
Use these project rules and optional skill references alongside the prompt. Review each skill before adding it to your agent; the AGENTS.md export includes the same guidance.
Optional external skill: gws-calendar — Use Google Calendar calendars, events, recurrence, free/busy queries and integration discovery through the gws CLI. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: supabase-postgres-best-practices — Review PostgreSQL schemas, queries, indexes, pooling, concurrency and row-level security. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: web-design-guidelines — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: calendar connections, provider event IDs, tasks, planned blocks, timezones and conflict-resolution records
Project rule — preserve this invariant: User-owned event edits are conditional on provider revisions; moving a task block cannot overwrite an unrelated calendar event.
Project rule — acceptance evidence: A provider edit between fetch and save raises a conflict; moving a block across a daylight-saving transition retains its intended duration.
Implementation plan
Phase 1
Scope and fixtures. Implement this bounded workflow: Combine events from one supported calendar account with a task inbox, drag work into time blocks and show two selected timezones. Add a daily planning review before expanding to more providers. Record prerequisites, select representative user-owned fixtures and document the unsupported features: multiple calendar providers, task integrations, mobile apps, and sync reliability; perfect mobile sync
Phase 2
Durable model. Model calendar connections, provider event IDs, tasks, planned blocks, timezones and conflict-resolution records Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: User-owned event edits are conditional on provider revisions; moving a task block cannot overwrite an unrelated calendar event.
Phase 3
Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Store UTC instants plus the intended IANA timezone. Reserve locally in a transaction, recheck provider availability, create with a stable external ID, then reconcile timeouts before retrying.
Phase 4
Permissions and integration failure. Encrypt refresh tokens with a separately managed key; expose busy intervals rather than event titles publicly. Hash guest management tokens and bound their lifetime. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
Phase 5
Portable handoff. Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
Phase 6
Acceptance scenarios. A provider edit between fetch and save raises a conflict; moving a block across a daylight-saving transition retains its intended duration. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.
WORKING SLICE Combine events from one supported calendar account with a task inbox, drag work into time blocks and show two selected timezones. Add a daily planning review before expanding to more providers. Build this scoped Morgen-inspired workflow with a documented data model and visible failure states. Architecture - Next.js App Router and TypeScript for server-rendered pages and validated mutations. - PostgreSQL with Drizzle migrations; Better Auth sessions for a small private workspace. - One Google Calendar OAuth adapter, a timezone-aware date library, and an outbox worker for email/ICS delivery. Prerequisites and limits Google OAuth credentials, a registered HTTPS callback and calendar access granted by the owner. Confirm the provider scopes and publishing requirements before adding guests. Outside this release: multiple calendar providers, task integrations, mobile apps, and sync reliability; perfect mobile sync Data model and correctness calendar connections, provider event IDs, tasks, planned blocks, timezones and conflict-resolution records Invariant: User-owned event edits are conditional on provider revisions; moving a task block cannot overwrite an unrelated calendar event. Store UTC instants plus the intended IANA timezone. Reserve locally in a transaction, recheck provider availability, create with a stable external ID, then reconcile timeouts before retrying. Security and privacy Encrypt refresh tokens with a separately managed key; expose busy intervals rather than event titles publicly. Hash guest management tokens and bound their lifetime. Recovery and export Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching. Implementation order 1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Combine events from one supported calendar account with a task inbox, drag work into time blocks and show two selected timezones. Add a daily planning review before expanding to more providers. Record prerequisites, select representative user-owned fixtures and document the unsupported features: multiple calendar providers, task integrations, mobile apps, and sync reliability; perfect mobile sync 2. Phase 2 — Durable model. Model calendar connections, provider event IDs, tasks, planned blocks, timezones and conflict-resolution records Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: User-owned event edits are conditional on provider revisions; moving a task block cannot overwrite an unrelated calendar event. 3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Store UTC instants plus the intended IANA timezone. Reserve locally in a transaction, recheck provider availability, create with a stable external ID, then reconcile timeouts before retrying. 4. Phase 4 — Permissions and integration failure. Encrypt refresh tokens with a separately managed key; expose busy intervals rather than event titles publicly. Hash guest management tokens and bound their lifetime. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results. 5. Phase 5 — Portable handoff. Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README. 6. Phase 6 — Acceptance scenarios. A provider edit between fetch and save raises a conflict; moving a block across a daylight-saving transition retains its intended duration. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder. Acceptance A provider edit between fetch and save raises a conflict; moving a block across a daylight-saving transition retains its intended duration. Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees. Optional agent guidance Optional external skill: [gws-calendar](https://github.com/googleworkspace/cli/blob/main/skills/gws-calendar/SKILL.md) — Use Google Calendar calendars, events, recurrence, free/busy queries and integration discovery through the gws CLI. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Optional external skill: [supabase-postgres-best-practices](https://github.com/supabase/agent-skills/blob/main/skills/supabase-postgres-best-practices/SKILL.md) — Review PostgreSQL schemas, queries, indexes, pooling, concurrency and row-level security. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Project rule — data model: calendar connections, provider event IDs, tasks, planned blocks, timezones and conflict-resolution records Project rule — preserve this invariant: User-owned event edits are conditional on provider revisions; moving a task block cannot overwrite an unrelated calendar event. Project rule — acceptance evidence: A provider edit between fetch and save raises a conflict; moving a block across a daylight-saving transition retains its intended duration.
$ open in your agent (prompt prefilled, you press enter), copy the prompt or copy or download AGENTS.md
prompt copied. want to know what dies next week?
new verdicts + top votes, weekly. free. one-click out.
Morgen pricing
| plan | monthly | annual (per mo) | what you get |
|---|---|---|---|
| individual | $30/user | $15/user | 1 user; calendar, task, planner, and scheduling features. |
| team | $25/user | $10/user | Minimum 2 paid seats; shared team scheduling and administration. |
free tierno free tier
billingmonthly + annual; 14-day trial; 30-day money-back guarantee
hidden costsTeam requires at least 2 paid seats; switchers can receive 15% off the first year, while student/nonprofit discounts can be 25%.
pricing sources checked 2026-08-14 · pricing source ↗
Questions about Morgen
Can you build your own Morgen with AI?
Partly. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Morgen, unify calendars and tasks, create booking pages, and plan work across time zones. The hard boundary is multiple calendar providers, task integrations, mobile apps, and sync reliability, plus cross-device reliability and workflow polish.
What does the Morgen build prompt cover?
The prompt starts with this scope: Combine events from one supported calendar account with a task inbox, drag work into time blocks and show two selected timezones. Add a daily planning review before expanding to more providers. Full-product capabilities excluded from the comparison include: multiple calendar providers, task integrations, mobile apps, and sync reliability; perfect mobile sync; calendar and email integrations. Follow the implementation plan and its prerequisites before expanding the build.
How do I use the prompt, AGENTS.md and agent skills?
Start with the Morgen prerequisites and stack, then copy the prompt into your coding agent. Save the project rules as AGENTS.md in the project root. Linked skills are optional packages or source instructions for specific tasks; review their current contents and install only those matching the chosen stack. A skill does not supply API credentials or verify the finished app.
How long will this Morgen project take?
The catalogue estimate is one sitting for the limited scope. Setup, integration approvals, debugging, deployment and ongoing maintenance can add time. This is an estimate, not a delivery guarantee.
What would I give up by replacing Morgen?
multiple calendar providers, task integrations, mobile apps, and sync reliability; perfect mobile sync; calendar and email integrations; shared workspaces; behavioral coaching polish. People still pay for Morgen because task software is sticky because trust, speed, and ubiquitous capture matter more than the database schema. The recurring cost buys recurrence edge cases, notifications, sync conflicts, calendar APIs, mobile capture, and backups, not just the visible interface.
What price is this guide comparing against?
The recorded Team plan is $25/mo per seat (monthly per user), checked 2026-08-14. Check the linked pricing source before buying. Building your own also has hosting, API and maintenance costs; the recorded amount is not a guaranteed saving.
What can I use instead of building Morgen?
The prior-art section lists Vikunja as starting points. Review their current scope, license and maintenance before adopting one.