Productivity

Stop paying for Trello

Cards move left. Cards move right. The work gets done.

Trello costs US$10–17.5 per person / mo, which is US$120–210 a year. You have two paths:

Option 1 · Install

Install Kan for free

Kan takes the core of Trello and stops there: boards, lists, cards you drag around. On each card: labels, checklist, due date, attachments, comments. On top, board templates, filters, the calendar view Trello keeps for Premium, and an MCP server so Claude can create and move your cards. Importing from Trello brings over your boards with their lists, cards, labels and checklists, but without comments, attachments or due dates. On kan.bn it is free for one person, then about €7 per member per month for teams. On your own server with Docker, everything is unlocked, with no member cap. What is missing compared to Trello: a mobile app, Butler-style automations, and integrations, which are announced but not there yet.

Kan vs Trello

CriterionKanTrello
PriceUS$0 on your server, free online for one personUS$10–17.5 per person per month
Number of boardsUnlimited10 per workspace on the free plan
Team membersUnlimited on your server10 at most for free, then each one is paid
Calendar viewIncluded on your serverPremium plan, €11/month
Driving your cards from ClaudeMCP server includedNo, only the in-house AI on Premium
Where your boards liveTheir cloud, or your server with DockerAtlassian's cloud
Mobile appNo, the website adapts to the phoneYes, iPhone and Android
AutomationsNot yetYes, 250 runs a month for free

How to install it (even from zero)

On your own, a free account on kan.bn is enough, with nothing to install. As a team, your server is where Kan becomes free for everyone: the prompt does the Docker install, then imports your Trello boards.

  1. 1

    Paste this prompt into Claude (Code or Desktop)

    It asks whether you are alone or on a team, installs Kan, then brings your Trello boards over:

    I want to replace Trello with Kan, the open source alternative (GitHub repo kanbn/kan, site kan.bn). First ask me whether I'll use it alone or as a team, and how many of us there are. If alone, help me create a free account on kan.bn. If as a team, install Kan on my server with the official docker-compose from the kanbn/kan repo: tell me what kind of machine is needed, generate the BETTER_AUTH_SECRET secret and the database password, set NEXT_PUBLIC_BASE_URL to my domain, configure email sending for invitations and explain how to back up the database. Then bring over my Trello boards: if Kan runs on my server, guide me through creating a Trello API key and entering it in TRELLO_APP_API_KEY and TRELLO_APP_API_SECRET, then connect my Trello account in Kan's settings and import my boards. Tell me what comes across in the import (lists, cards, descriptions, labels, checklists) and what stays in Trello (comments, attachments, due dates), and check an imported board with me. Finally, connect Kan's MCP server (npx -y @kan/mcp, with KAN_BASE_URL and an API key created in Kan's settings) so you can read and edit my cards.
    
    Review the GitHub repository and check whether it is safe to install given my machine and my infrastructure. Ask me as many questions as possible, using widgets, to clarify my request and be as precise as you can.
  2. 2

    Import a single board to start

    Take your most-used board and work on it for a week before moving the rest. You will quickly see whether you miss the comments or due dates left behind in Trello.

  3. 3

    Invite your team

    On your server, members are no longer paid for one by one: one invite link and everyone is in.

What you'll use it for

Your Trello boards, without the bill

The import brings over lists, cards, labels and checklists. Your setup is back in minutes, with nothing to retype.

The whole team at the same price: zero

At Trello, every extra member is paid for. On your server, Kan takes as many people as you want, calendar view included.

Your cards driven by Claude

The built-in MCP server lets Claude read your boards, create cards and move them. You describe the task, and it lands in the right list.

Project health

GitHub stars
5,739
Forks
499
Contributors
53
Commits
860
Project age
2.9 years
License
AGPL-3.0

Built with: TypeScript 95.8% · PLpgSQL 2.2% · MDX 1.1% · JavaScript 0.6%

Public GitHub repository data, captured on October 8, 2026.

Option 2 · Build

Build your own Trello

Who this is for

This build is for a small team managing one shared project board. The goal: make current work visible and easy to move from idea to done. If you need more than that, keep paying. Building it yourself is about owning a tool shaped exactly like your workflow, not re-implementing a venture-funded roadmap.

Same build, different logo: this v1 also replaces Asana, since they all solve the same core job.

What the prompt builds and what stays out

The prompt below builds a single version with what actually gets used. Everything else is left out on purpose.

What the prompt buildscolumns, drag-and-drop cards, checklists, labels, filters, activity timeline
What stays outreal-time sync, power-ups, automation, mobile apps

What a minimal Trello alternative needs

  • boards with ordered columns and drag-and-drop cards
  • card description, assignee, due date, labels, and checklist
  • comments and a compact activity timeline
  • filters for member, label, overdue, and keyword
  • archive and restore for cards and columns

Data model

Board, Column, Card, ChecklistItem, Comment

Integrations

email invite links

Capability context

Astro, Alpine, D1

The guardrail

Enforce board membership on every change, not just in the interface.

Deliberate non-goals

Do not build workspace billing, Power-Ups, complex automation, or portfolio views.

The complete build prompt

Pick your stack, copy the prompt and hand it to your coding agent (Claude Code, Cursor, Codex…).

You are building a production-ready software product named “Deck”, a deliberately focused alternative to Trello. Build a complete, usable vertical slice, not a landing page, a static mockup, or a pile of disconnected components.

WORKING AGREEMENT
Before you write any implementation code, put together a short technical plan naming the routes or pages, server actions or endpoints, data tables, key state transitions, authorization boundaries, background jobs, and external adapters. When something conflicts, side with the narrow audience and the non-goals below. Choose a small, readable architecture over speculative abstraction, but never skip persistence, validation, error handling, or tests.

PRODUCT BRIEF
Primary user: a small team managing one shared project board.
Primary outcome: make current work visible and easy to move from idea to done.
Product principle: optimize the exact workflow below rather than copying the full breadth of Trello. A first-time user should understand what to do from the interface itself, with no tour or documentation.

END-TO-END USER JOURNEYS
Implement every one of these flows through the real interface and the persistent data layer:
1. The board owner creates a board, names three ordered columns, invites two teammates by email, and adds labeled cards with assignees, due dates, and checklists.
2. A teammate filters the board down to their own cards, opens one, completes checklist items, comments with an update, and drags the card from In progress to Done.
3. The owner archives an obsolete card and an empty column, reviews the activity trail, then restores the card to an active column and position of their choosing.

SCREENS AND INFORMATION ARCHITECTURE
Build these as coherent, responsive views. Each screen must define its primary action, secondary actions, visible status, validation feedback, empty state, loading or pending state, success confirmation, and recoverable failure state.
1. Boards dashboard: active and archived boards, member count, recent activity, a create-board action, and pending invitation status.
2. Board view: horizontally ordered columns, card counts, draggable cards, add-card controls, member and label filters, keyword search, and overdue emphasis.
3. Card detail: title, markdown description, assignee, due date, labels, ordered checklist, comments, activity timeline, and archive and restore controls.
4. Board settings and archive: board name, members and roles, invitation management, column ordering, archived cards and columns, and a permanent board-close action.

CORE CAPABILITIES
1. boards with ordered columns and drag-and-drop cards
2. card description, assignee, due date, labels, and checklist
3. comments and a compact activity timeline
4. filters for member, label, overdue, and keyword
5. archive and restore for cards and columns

DETAILED BEHAVIOR AND BUSINESS RULES
Treat these as product requirements enforced on the server, not as interface suggestions:
1. Authorize every board, column, card, checklist, comment, and archive change on the server against active board membership.
2. Store explicit integer positions for columns, cards, and checklist items; reorder the affected siblings atomically and reject moves into archived columns.
3. Record card moves and meaningful field changes as immutable activity events containing the actor, old value, new value, and timestamp.
4. Archiving is reversible and keeps comments and history; restoring requires a valid active destination and never silently recreates a deleted membership.

DATA MODEL AND LIFECYCLE
Design a small relational schema centered on Board, Column, Card, ChecklistItem, Comment. Before implementing it, document:
1. The purpose of each table, its primary key, ownership or tenant boundary, timestamps, status fields, and important attributes.
2. Foreign keys, uniqueness constraints, check constraints, the indexes the named screens need, and transaction boundaries for changes that touch several records.
3. The allowed lifecycle or state transitions, who can trigger each one, which transitions are terminal or reversible, and which audit history must stay immutable.
4. Archive, retention, and deletion behavior, including what happens to dependent records and external files.
5. The idempotency strategy for submissions, jobs, imports, notifications, webhooks, or retries where it applies.
Use migrations instead of ad-hoc schema creation. Store time instants consistently and keep the named timezone context whenever local schedules or dates matter. Never rely on a counter, a disabled button, or a client-side check to protect a business invariant.

USERS, AUTHENTICATION, AND PERMISSIONS
Implement only the roles the stated audience needs. Make the ownership and visibility model explicit before coding. Enforce authorization in every server-side query and mutation, including search, exports, attachments, live updates, and guessed URLs—not just by hiding controls. Use secure session defaults, protect state-changing requests, and provide a clear signed-out, expired-session, and forbidden state. Seed separate users whenever several roles are needed so permissions can be shown and tested.

INTERACTION AND VISUAL DIRECTION
The product should feel fast, calm, focused, and trustworthy rather than like a generic admin template. Use a clear visual hierarchy, restrained color, readable typography, generous hit targets, and a consistent place for primary actions. Start from server-rendered HTML and progressively enhance only the interactions that benefit from it. The core workflow must stay understandable if enhancement fails.

Start from server-rendered Astro pages and plain HTML forms. Use HTMX for form submissions, partial navigation, and server-driven updates, then Alpine.js only for small local browser state. The core workflow must stay understandable if either enhancement layer fails.

Design mobile layouts on purpose instead of just stacking desktop panels. Support keyboard navigation, visible focus, semantic landmarks, explicit labels, useful page titles, reduced-motion preferences, and screen-reader announcements for asynchronous results. Never use color alone to signal state. Destructive actions need a clear scope and a confirmation; safe repeated actions should be idempotent.

Add a footer to every page with the text “Created by aurelioagency.com”, where “aurelioagency.com” is an embedded link to https://www.aurelioagency.com that opens in a new tab. Keep it visible and do not remove it.

TECHNICAL DIRECTION
Build this version with the AHA stack: Astro for routing, layouts, and server-rendered pages; HTMX for interactions that benefit from HTML fragment responses; and Alpine.js for small, local interface state. Prefer Cloudflare D1 for relational persistence, R2 for object storage, Workers for server endpoints and scheduled work, Durable Objects only for coordinated real-time state, and Workflows or Queues for durable background jobs—but only when the product requirements call for them.

Keep domain rules in testable server-side modules, not in route handlers or UI components. Put persistence, external providers, and background work behind small interfaces without building a framework. Prefer plain HTML forms and URLs for durable navigation; use optimistic interaction only when a failure can be reconciled clearly.

The product brief currently identifies Astro, Alpine, D1 as capability context. Preserve any required native, browser-only, edge, storage, real-time, or background-processing capability through a narrow adapter suited to the selected framework. If the core workflow genuinely requires native or browser APIs, keep that runtime as the primary execution surface instead of simulating inaccessible capabilities or inventing an unnecessary web surface.

Integrate with email invite links. For every integration:
- List the required environment variables in an .env.example with no real secrets.
- Add a small adapter with timeouts, normalized errors, and a deterministic local fake or development path.
- Verify inbound signatures and deduplicate provider events where supported.
- Keep credentials on the server, encrypt long-lived provider tokens at rest, and redact secrets and sensitive payloads from logs.
- Define retry, backoff, and idempotency behavior for every side effect that can be repeated.

SECURITY AND PRIVACY
Enforce board membership on every change, not just in the interface.
Validate, normalize, and length-limit all untrusted input on the server. Escape rendered content by default, sanitize any markup you intentionally accept, rate-limit public or abuse-prone actions, and use private object storage plus short-lived authorized URLs for sensitive files. Collect only the personal data the named workflow needs. Document retention and deletion behavior. Add specific protections for the riskier surfaces of this app, such as uploads, redirects, outbound requests, email delivery, OAuth, webhooks, CSV import or export, and real-time connections.

ACCEPTANCE SCENARIOS
Automate these app-specific scenarios at the most suitable level:
1. Given two members viewing the same board, when one moves a card, both views converge on the new column and position without duplicating the card.
2. Given a user whose board membership was removed, when they submit a card edit they had loaded earlier, the request is denied and the card stays unchanged.
3. Given an archived card with completed checklist items and comments, when it is restored, all of its content comes back intact and the restore shows up in the activity.

TESTING
Add focused unit tests for state transitions, authorization predicates, normalization, date or money calculations, and other risky domain rules. Add integration tests for persistence constraints and for each external adapter's success, timeout, retry, and rejection paths. Add at least one browser-level test for every end-to-end journey above, including one on a small-screen viewport. Tests must use isolated data and run with one documented command.

OPERATIONS AND FAILURE RECOVERY
Add structured server logs with request, job, or event correlation IDs, but no secrets or unnecessarily sensitive data. Make failures actionable both in the interface and in the logs. Background work must expose pending, succeeded, failed, and retrying states where relevant; never swallow errors silently. Include safe database migration and rollback guidance, seed data, backup and restore notes, external-data cleanup behavior, and a basic health or diagnostic path suited to the stack.

DELIVERABLES
Ship the working application, migrations, representative seed data, tests, .env.example, and a short README. The README must cover prerequisites, local setup, environment variables, migrations, seed and test commands, deployment, integration setup, backup and restore, security decisions, and known limitations. Seed data should cover the happy path plus at least one empty, failed, overdue, expired, archived, or permission-restricted state that matters for the product.

DEFINITION OF DONE
The app is done when a new developer can follow the README, create and migrate the database, run the app, sign in as each relevant role, complete every named journey with real persisted data, refresh without losing state, recover from common failures, and use the core interface on phone and desktop. All acceptance scenarios pass, permission boundaries are covered by tests, no core screen is left as a placeholder, and the “Created by aurelioagency.com” footer credit is visible on every page.

NON-GOALS
Do not build workspace billing, Power-Ups, complex automation, or portfolio views.

The app you build with this prompt carries a “Created by aurelioagency.com” footer.

Build just one piece

Short prompts that solve the hardest part without building everything.

Card ordering that survives the ten-thousandth dragExplicit integers, atomic renumbering, and no fractional-position decay.
Build drag-and-drop card ordering for a kanban board that stays correct after ten thousand drags.

Store explicit integer positions per card within a column. A move, whether within a column or across columns, computes the target position and renumbers the affected siblings in a single transaction. At board scale, rewriting a column's positions on every move is fine, and beats clever fractional schemes that accumulate precision debt. Whatever you choose, the invariant is a gapless, duplicate-free ordering after any move.

The moves that break naive implementations: dropping at the very top and the very bottom, moving the only card out of a column, cross-column moves that must renumber two columns atomically, and a move racing a concurrent move of a neighboring card. Reject moves into archived columns with a visible error and a revert animation, never a silent snap.

The same routine powers checklist-item and column reordering: one reorder function, three uses.

Done when: any drag sequence leaves every column gapless and duplicate-free in the database, concurrent moves of different cards both land correctly, and archived columns refuse drops loudly.
Two people, one board, no duplicate cardsOptimistic drags, server arbitration, and clients that always converge.
Build multi-viewer consistency for a shared kanban board without building a realtime engine.

Two people have the same board open. One drags a card; the other should see it soon and, above all, see it correctly. Use optimistic UI plus server reconciliation: the dragger's client applies the move instantly and sends a request carrying a client-generated operation id. The server is the single arbiter of order; the other clients poll (or listen on a cheap channel) for changes since their last-seen board version and apply the difference.

The correctness traps: the dragger's own move echoing back must be recognized by operation id and not re-applied as a visual stutter; a rejected move, say because the card was archived in the meantime, must revert the optimistic state with an explanation; and two clients moving the same card converge on the server's answer, both ending up identical. When versions drift too far apart, refetch-and-diff beats surgical patching.

Done when: a move appears on the second client within one poll cycle without duplicating the card, the mover never sees their own echo jitter, and deliberately conflicting moves end with both clients identical to the server.
The activity log that remembers old valuesImmutable events with old and new values, coalesced only at display time.
Build an activity timeline for a project board, recorded as immutable events with real old and new values.

Every meaningful change, card moved, assignee changed, due date set, checklist item completed, comment added, card archived, writes an event: actor, verb, old value, new value, timestamp. Write it in the same transaction as the change itself, or the log will eventually lie. Never update or delete events; corrections are new events.

Displaying them is a compression problem: raw events are noisy, so coalesce at display time, so that five title edits within a minute by one actor collapse into a single expandable entry. Renamed entities need care: the event stores values as they were at the time (column name, member name), so history reads correctly even after the column is renamed or the member is removed from the board.

Support filtering by actor and event type. The card detail shows its own slice; the board view shows the merged stream.

Done when: every field change can be reconstructed from events alone, display coalescing never hides the fact that something happened, and events referencing renamed or deleted entities still render meaningfully.
Archive is a promise you can take backReversible by design, with restores that need a real destination.
Build archive and restore for kanban cards and columns: deletion with an undo, done properly.

Archiving is a reversible state, not a soft-delete flag bolted on later. An archived card keeps everything, comments, checklist state, labels, history, leaves the board view, stops matching filters, and lands in a browsable, searchable archive. Archiving a column archives its cards as one operation, remembering which cards were archived by the cascade versus already archived beforehand, because restoring the column must not resurrect cards someone deliberately archived last month.

Restore requires a valid destination: the original column if it is still active, otherwise an explicit choice. Position on restore appends to the end of the column; honoring a stale position claim is how duplicate-position chaos begins. Both operations write activity events, and restoring never reinstates board memberships that were revoked while the card sat in the archive.

Permanent deletion exists only as a separate, confirmed action on already-archived items.

Done when: archive and restore round-trip a card with all content intact, a column cascade restores exactly the cards it archived, and no restore ever lands in an archived or missing column.

Frequently asked questions

How much does Trello cost if I keep subscribing?

Trello runs $10–$17.5 per person per month on public paid plans, which is $120–$210 per year for every person on your team. A focused self-built replacement costs your build time plus close-to-zero hosting.

What stack should I use to build a Trello alternative?

The build prompt on this page comes in four flavors: the AHA stack (Astro, HTMX, Alpine.js), Next.js, Laravel, and Ruby on Rails. The capability context for this product is Astro, Alpine, D1. Pick the stack you already know, because the scope matters more than the framework.

What features does a minimal Trello replacement need?

A useful v1 needs: boards with ordered columns and drag-and-drop cards; card description, assignee, due date, labels, and checklist; comments and a compact activity timeline; filters for member, label, overdue, and keyword; archive and restore for cards and columns. Everything else is scope creep until you personally miss it.

What should I deliberately not build?

Do not build workspace billing, Power-Ups, complex automation, or portfolio views.

Does this build also replace Asana?

Yes. Trello and Asana both solve the same core job: make current work visible and easy to move from idea to done. The scoped v1 on this page covers what most people use either of them for, so one focused build replaces whichever you currently pay for.

Is Kan really free?

Yes. Kan is open source: the code is public and installing it costs nothing. At most you pay for hosting if you put it on a server, often a few euros a month. Trello, on the other hand, costs €5 a month.

Do I need to code to install Kan?

No. The level is intermediate and the install takes about 15 minutes with the prompt from the page: Claude does the work, and you answer its questions.

How is it different from Trello?

Kan does most of what Trello does, with no subscription, and your data stays with you. The point-by-point comparison is on the page.

Do I own my data?

Yes. With an open source tool installed on your side, your files stay on your machine or your server. Nobody can close your account or change the price.

Browse all 22 apps →

No time to do it?

We'll build it for you.

If you'd rather have someone install it, connect it to your tools and keep it running, that is exactly what we do at Aurelio.

Book an Automation Audit