Add the filter by customer on the invoice list
Project work driven by AI agents
Your projects move forward.
You stay in charge.
HaikoDev is a board of cards. You describe what you want in plain language; an AI agent picks up the card, works in its own branch, runs the tests and hands back a report. Publishing, however, stays a human gesture.
One card, one agentOne branch per cardNothing is sent before you start itThe report is in plain languageYou publish, not the machineOne card, one agentOne branch per cardNothing is sent before you start itThe report is in plain languageYou publish, not the machineOne card, one agentOne branch per cardNothing is sent before you start itThe report is in plain languageYou publish, not the machineOne card, one agentOne branch per cardNothing is sent before you start itThe report is in plain languageYou publish, not the machineOne card, one agentOne branch per cardNothing is sent before you start itThe report is in plain languageYou publish, not the machineOne card, one agentOne branch per cardNothing is sent before you start itThe report is in plain languageYou publish, not the machineOne card, one agentOne branch per cardNothing is sent before you start itThe report is in plain languageYou publish, not the machineOne card, one agentOne branch per cardNothing is sent before you start itThe report is in plain languageYou publish, not the machine
The app itself
Here is the board. Help yourself.
This is not a picture: it is the HaikoDev interface, with made-up projects and made-up cards. Switch projects, move a card, ask the orchestrator for something — it will propose a card, and you can start it.
Demo — nothing you do here leaves your browser.
Planned2Fix the PDF export cutting off the last line
Running1Rebuild the sign-in page for phones
Done1Translate the interface into German
To deploy1Replace the main menu icons
Orchestrator
Hello. Tell me what you want for this project, in plain language: I read back through the thread, go and read what I need, and propose a short card.📎⌸ PlanClaude · Claude Opus 5 · Medium thinking
What HaikoDev does
A board where every card is taken over by an agent
You already know how a column board works. HaikoDev keeps that simplicity and adds one thing: any card can be handed to an AI agent that really deals with it — it reads the project, edits the code, runs the tests, and hands you a written account.
You explain
In plain language, in the project conversation: what is wrong, or what you would like. No syntax to learn.
The orchestrator proposes
It reads back through the thread, writes a short card and picks the thinking level. Ambiguous case? It offers both routes.
The agent works
Its own branch, its own copy of the project, its task list ticking off. It reads, edits, tests, then hands back its report and its estimate.
You decide
You read it over, drag the card into “To deploy”, and publish whenever suits you. The batch goes out in one piece.
The five columns
Every column has its character
These are the very same faces you see inside the tool: one glance tells you where each card stands, without reading a single label. And above all, who is allowed to move it.
Planned
Every card is born here. It carries a short request, a thinking level and, if you want, a start date. Nothing has gone to the engine yet: while the card sleeps, it costs nothing.
Running
An agent has taken the card. It has its own branch and its own copy of the project; it reads, edits, tests and shows you its task list ticking off live. A question from the agent stops everything until you answer.
Done
The agent has handed in its report: what it understood, what it did, the consequences, and the outcome of the checks — failures included. The card lands here on its own; nobody pushes it.
To deploy
You have read it over and you approve. Cards pile up here as one batch, ready to go out together. No agent walks through this door: publishing is a human gesture, always.
Archived
What is settled leaves the board without disappearing. The history, the branches, the reports and the estimates stay readable — and only reopen on your gesture.
ClaudeCodexCursorGitHub built inMemory by topicQuotas trackedInstallable on your phoneClaudeCodexCursorGitHub built inMemory by topicQuotas trackedInstallable on your phoneClaudeCodexCursorGitHub built inMemory by topicQuotas trackedInstallable on your phoneClaudeCodexCursorGitHub built inMemory by topicQuotas trackedInstallable on your phoneClaudeCodexCursorGitHub built inMemory by topicQuotas trackedInstallable on your phoneClaudeCodexCursorGitHub built inMemory by topicQuotas trackedInstallable on your phoneClaudeCodexCursorGitHub built inMemory by topicQuotas trackedInstallable on your phoneClaudeCodexCursorGitHub built inMemory by topicQuotas trackedInstallable on your phone
The features
Everything you need to hand over work without regretting it
An agent that writes code is only half the story. The other half is knowing what it is doing, what it costs, and where its power stops.
A board, not a queue of commands
Your projects, your cards and your agents fit on a single screen. You drag a card from one column to the next; the work follows.
An orchestrator that writes the cards
You describe the need in plain language. The orchestrator reads back through the conversation, cuts it into short cards and picks the thinking level of each agent.
A plan mode before a single line is written
On delicate topics, the agent proposes a plan first, which you refine back and forth. Nothing starts until the plan suits you.
One branch and one folder per card
Every agent works in its own copy of the project, on its own branch. Two cards started together never tread on each other.
Three engines, your pick
Claude, Codex and Cursor all run on the command line behind the same interface. Work is sent to whichever account has the most room left.
A project memory that actually earns its place
Lasting rules and facts are filed by topic. When a card starts, only the passages that answer the request are sent — not the whole folder.
The benefits
Why it holds up over time
The safeguards are not options: they sit in the engine, and agents cannot remove them.
You keep control of publishing
No agent ever publishes on its own initiative. Code gets written, committed and pushed by itself, but it waits in “To deploy” until you click. It is the hardest rule in the tool, and there is no way around it.
You follow the work without reading code
Every agent announces its task list and ticks it off in front of you, then hands back a report in plain language: what it understood, what it did, what it changes. Failed tests are written there too — a failed check is never hushed up.
You do not pay for nothing
A sleeping card burns no tokens. Memory only sends the useful passages, the orchestrator does not pay for a heavy model just to sort, and what goes to the engine is measured, not assumed.
Nothing gets stuck
A run that ends closes its card, a passing outage is retried, a run cut short by an account limit starts again, and a sweep catches forgotten cards. A card in “Running” always says what is still going on.
Your rules outlive the agents
Whatever an agent learns that is useful goes into the project memory, filed by topic. The next agent finds it again, without you repeating yourself. A delivery log is kept separately, and never clutters the engine.
You stay at home
HaikoDev runs on your server, with your accounts and your repositories. Your project code does not leave your machine other than through the engines you chose.
3
engines drivable behind one interface: Claude, Codex, Cursor
7
board columns, five of which you handle every day
12
display palettes — six moods, in light and dark
5
interface languages, set per project
The blog
To install it and to use it
The HaikoDev code lives on GitHub. The first article explains, step by step, how to pull the repository, install it on your machine and keep it running permanently.
Pull HaikoDev from GitHub and install it on your own server
The repository lives on GitHub: you pull it, install it and keep it running permanently on your own server. The steps, one by one, assuming nothing.
19 August 2026
Your first card, from request to release
One sentence in the conversation, a card proposed, an agent at work, a report to read over, one click to publish. The whole journey, told once.
19 August 2026
Understanding the five columns of the board
Planned, Running, Done, To deploy, Archived: who is allowed to move what, and why some doors only open for you.
19 August 2026
Install it on your own server
Pull the repository, install it on your server, plug in your accounts. The guide skips no step.