For freelancers and agencies
Ship client work in parallel, with receipts your clients can read.
Each client gets an isolated workspace with its own repos and its own rules. Agents build their backlogs at the same time, every change arrives as a reviewed pull request, and every run keeps its transcript and its cost — so a status update is a link, not an afternoon.
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
Two clients, two factories
Invented data, real mechanics. Switch workspaces from the top-left: each client has its own repo, board and inbox, and their work keeps moving while you look at the other.
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.
Signals from the outside world
Client emails and site health become tasks
Requests are split out of client emails and filed per client; Lighthouse and uptime checks catch regressions. You approve what gets built.
Processes
- Split each email into requests
- →File in that client's workspace
- →Suggest tasks
- Keep scores that dropped
- →Name the page and the cause
- →Suggest tasks
Suggested tasks
Suggestions arrive once signals come in.
Sent tasks land here.
Engineer from anywhere
Answer the client, not the laptop
A client's question doesn't wait for you to get back to your desk. Every client's inbox is on your phone — make the call between site visits, and their workspace keeps building.
From a beach chair
Scroll a little further to load the demo
Have a poke around
Onboard a new client in minutes
Connect the client's repos, add their brand kit and your studio's standards as read-only context, connect a worker, and approve the onboarding pull request. A new factory, ready for their backlog.
- 1Start from
- 2Repos
- 3Read the repo
- 4Connect a worker
- 5Onboarding PR
- 6Your factory
Where does this factory start?
Client-ready
More clients without more late nights
Isolated per client
Each client's repos, rules and credentials live in their own workspace — the repos you change, plus their brand kit or API as read-only context. Nothing crosses between clients.
Each client's conventions
Agents follow each repo's own AGENTS.md and style, so client A's code doesn't start looking like client B's.
Receipts for every change
Plans, review rounds, transcripts and cost per task — the evidence behind every invoice line.
Their release process, followed
Merged work ships the way each client deploys, because the deploy step reads that repo's instructions.
The lifecycle
The same professional process on every client's code
Plan, build, test, review, merge, release — the way the best engineering teams ship, applied to every task for every client, whether or not you had time to check that night.
- Planningyour call
- Implementing
- Testing
- Reviewing code
- Mergingyour call
- Releasing
- Done
Questions
Are clients isolated from each other?
Yes. Each client gets their own workspace with its own repos, rules and credentials. Nothing crosses between them.
Can I show clients what was done?
Every task keeps its plan, review rounds, full transcript and cost — a link you can share instead of a status meeting.
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
Take on the next client
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.