What is tuckit?

If you have ever had an AI build something for you, this will be familiar.

Yesterday you spent a few hours with it and got a feature working. Along the way you agreed to fix one thing later, and you told it never to touch another. Today you open a fresh window. It remembers none of that.

tuckit is a web page where those things get written down. You can open it and read it. Your AI opens the same page and writes to it directly.

Here is what it looks like

A board split into four columns: Needs design, Needs steps, In progress, Ready to ship, with cards in each.

Everything you are building sits here as a card. The further right, the closer to finished.

Needs design: you have decided to do it, but not what to build
Needs steps: you know what to build, but haven’t broken it up
In progress: working through the steps
Ready to ship: the steps are done and someone needs to say so

You cannot drag these cards. When the contents change, tuckit moves them. So you never have to wonder whether a card is in the right column: nothing put it there except what is inside it.

Open one card

One card in detail: Stage, Area, progress and tags at the top, then Spec, Constraints, and a Steps checklist marked done, doing and todo.

A card is one piece of work. tuckit calls it a slice (Slice). The name does not matter much; what is inside it does. There are three boxes.

What we’re building. Labelled Spec on screen. Leave it empty if you haven’t decided yet. Empty is the signal that says nobody has worked this out. Filling it in to make the card look finished just teaches your AI that the thinking is done.

What must not break. Labelled Constraints. Sentences like “don’t touch the payment code” or “leave the login screen design alone”. This is the first thing an AI reads when it picks the work up.

Steps. Labelled Steps. The work broken into an ordered list. Usually the AI writes these and ticks them off as it goes. You can add your own.

Underneath, a running log (Activity) collects what actually happened: what was tried, what broke, where it landed.

When you don’t know where something belongs

The Inbox: four items with no area set, each with a “Choose area…” dropdown beside it.

Sometimes you notice something and have no idea where to file it. Type a title and leave it. It lands in the Inbox and you can sort it later, or unsort it again. Nothing here is one-way.

What changes

When you ask your AI to do something, it reads this board before it starts. What has been built, what was decided, what must not break: it is all written down, so you don’t explain it again.

When it finishes, it writes back. What it did, what blocked it, what it agreed to do next. Close the window and it is still there. Open a different AI tomorrow and it reads the same board.

Both sides can do both. Anything the AI can write, you can write on the web page, and the other way round. Neither one hands off to the other; you are working on the same surface.

Two words this site keeps using

Coding agent. An AI that edits your code directly. Claude Code, Codex CLI, Antigravity and others. It doesn’t just show you code in a chat window; it opens your files, changes them, and runs things. This site shortens it to “agent”.

MCP. The name of the standard those agents use to reach tools outside themselves. tuckit follows it, which is why an agent can read and write your board without anyone building an integration first. Knowing the name is enough; you never have to learn how it works.

Past those two, there is not much new to learn. If you only ever use the web page, you need neither.

Where to go

Just show meSign up, attach an agent, and watch it fill in your first card. About ten minutes.

I'm running several sessions at onceWhen you can't tell what each window did, and showing anyone what you built makes you nervous.

I'm evaluating this for a teamEverything your teammates would have to learn, and everything they'd lose.

We use JiraWhat maps onto what, what you give up, and when staying on Jira is the right call.

What tuckit isn’t

Not a memory feature. Nothing here belongs to one conversation or one vendor’s app. Switch which AI you use and the board is unchanged.
Not a general issue tracker. No sprints, no due dates, no estimates. Coming from Jira lists everything that’s missing.
Not agent-only. The web page is a real product surface, not a debug view.

Not written yet

So you don’t go looking:

A full install guide for running it yourself. What is documented today is the handful of settings that silently break agent connections, under Self-hosting.
A changelog. Releases are tagged on GitHub.

If you want the pitch rather than the manual, tuckit.dev is the place for that.

Something here wrong or missing? Open an issue. A broken install command counts as a bug.