Kanban for coding agents
A kanban board where the cards build themselves.
Drop a card on the board and agents carry it across: planning, implementing, testing, reviewing, merging. Drag to reprioritize, answer what's blocked on you, and watch the work move. One line connects a worker on your laptop or in the cloud.
A kanban board with four lanes — Ideating, Planning, Building and Shipping — carrying tasks from a fresh idea through to a pull request waiting for review.
Have a poke around
The board is the product
Invented data, real mechanics. A card's column is its state. Press Start on a card and watch it walk itself across the lanes — refined, then planned — until its plan comes back to you.
Scroll a little further to load the demo
The board
Every piece of work, at the exact stage it's in. Positions aren't decoration — a card's column IS its state.
The inbox
One queue of everything blocked on you, each ask carrying the plan, the diff and the transcript behind it.
Activity
Who's working right now, on what, and what each run cost — live, with every finished run still on the record.
Engineer from anywhere
Start a card from anywhere
The board fits in your pocket. Press Start on the card that's next, and an agent picks it up, plans it and builds it while you're out — the board moves on its own until something needs you.
From a beach chair
Scroll a little further to load the demo
Have a poke around
One-click setup, then your board
Connect a repo or start from a template, add the repos agents should read for context, run one command to connect a worker, and approve the onboarding pull request. Then the board is yours.
- 1Start from
- 2Repos
- 3Read the repo
- 4Connect a worker
- 5Onboarding PR
- 6Your factory
Where does this factory start?
Turnkey
Set up in minutes, not a weekend
One-line workers
Paste one command on a laptop or a cloud server and it starts taking cards. Add more workers whenever you want more running at once.
Drag to steer
Drag cards to reorder priorities or move work between Next, Soon and the Backlog. Agents pick up whatever is at the top.
Live cards
A pulsing dot means an agent is mid-turn on that card. Open it to see the plan, the history and the transcript.
No workflow to configure
The lanes are a proven engineering process out of the box. Your repo's own rules customize what each agent does.
The lifecycle
A process, not another chat window
A chat forgets everything the moment you close the tab, which is why it can't be trusted with anything longer than an afternoon. ampm keeps a real database instead: every task is a row with its plan attached, its history intact, and its place in the tree of work it came from. Retries don't overwrite anything — they land beside the last attempt, because you should be able to ask what happened last time.
Plan before you build, test and review before you merge — that discipline wasn't invented here. It's how the best San Francisco engineering orgs actually ship, distilled from fifteen years as an engineer inside them and codified into machinery. You get the institutional knowledge it takes a career to absorb, working for you from day one — and holding the bar even on the nights you wouldn't have bothered.
- Planningyour call
- Implementing
- Testing
- Reviewing code
- Mergingyour call
Questions
How long does setup take?
Minutes. Paste one command on a laptop or a cloud server to connect a worker, connect your GitHub repo, and start dropping cards on the board.
Can I reorder work?
Yes. Drag cards between Next, Soon and the Backlog; agents pick up whatever is at the top.
Which coding agents does ampm work with?
Claude Code and Codex. ampm runs them on the subscription you already pay for — no API keys and no second bill for tokens — and when one account hits its usage limit, work moves to a backup account without losing anything.
Does ampm merge code on its own?
Nothing merges unless you want it to. Plans, questions and merges wait in your inbox with the plan, diff, pull request and full transcript attached, and you decide which decisions to keep and which to hand off.
Where does the code run, and is my repo safe?
Every task runs in an isolated sandbox on its own worktree, on workers you choose — your laptop, a server you own, or a cloud machine — and can only push to a branch. The output is always a pull request into your repo.
How is this different from chatting with a coding agent?
A chat forgets everything when you close the tab and needs you watching it. ampm keeps every task in a database with its plan and history, runs a real process — plan, implement, test, review, merge — and only asks you when a decision is actually yours.
Can one workspace cover several repos?
Yes. Add the repos agents should change, and add more as read-only context — a design system, an API they call, product docs — so their work matches what's around it. One change can span several repos as one piece of work.
How do I get access?
Join the wait list with Google or GitHub. We're letting people in a few at a time, in the order they joined, and we'll email you when it's your turn.
Early access
Get your board
We're letting people in a few at a time. Join the wait list with Google or GitHub and we'll email you when it's your turn. Run it on our cloud or on infrastructure you control — your repos, your subscriptions, workers on machines you choose.