Start here

What “AI memory” actually is.

Your AI is only just learning to remember.

Until recently, assistants forgot everything the moment you closed the chat. Now Claude, ChatGPT and Gemini keep a little memory — a preference here, a project there. It’s a real step forward, but it’s a short list of notes kept on the company’s servers, and it only works inside that one app. Captain Fleet is a deeper memory that’s yours: it keeps far more than a handful of notes, works across every AI tool you use, and lives on your own device instead of someone else’s cloud.

Never repeat yourself again.

With a memory, you stop repeating yourself. Your AI holds on to your preferences, the details of what you’re working on, and the decisions you’ve already made — so every conversation starts where the last one left off, not cold. Begin something on your laptop in the afternoon and finish it on your phone that night. It’s the same memory, so your AI already knows the whole story.

The usual way

Their memory sits in the company’s cloud and works only in that one app.

Captain Fleet

Yours, on your own device, shared across every AI tool — and no one else can read it.

One shared memory across Claude Code · Codex · Gemini · Antigravity · Cursor · Kimi · opencode · Copilot · JetBrains — ten and counting.

How it works

A whole team, one shared memory.

You don’t have to stop at one assistant. You can have a few — one in the Claude app on your phone, one on your laptop, and (if you have one) an extra computer at home you leave switched on — and connect them all to the same memory. What any one of them learns, the rest of them know. No re-briefing, no catching each other up.

What one learns, they all know

Tell the assistant on your phone about a project, and the one on your laptop already knows when you ask it later. They share a single memory, so you never explain the same thing twice.

Each one lives on its own device

Put one on your laptop and, if you like, another on a computer at home that never sleeps. The memory follows you and your work — not any single machine, so it doesn’t matter which one you reach for.

III

They hand work off to each other

One assistant can start a task on another, or pass it to your phone so you can watch it finish while you’re out. Nothing gets copied over or restarted from scratch, and if a computer restarts in the middle, the work simply carries on.

Works on any kind of computer

Mac, Windows, or Linux computers — plus the Claude apps on your phone, tablet, and desktop. They all join the same team and share the same memory.

the memory engine is open source →

It tidies itself while you sleep

A memory that only ever grows gets harder to search, not easier. So every so often your fleet goes back over what it has collected and folds the notes that belong together into one clearer note — keeping the originals underneath, in case you ever want the detail back. It decides what belongs together from what you actually look up together, which is why it groups things by topic rather than by wording. This part is called dreaming.

how dreaming works →

Your own memory always comes first

Once several machines share a memory, something has to decide whose note wins when two disagree. The rule here is simple: your own memory is never re-ordered by the fleet. A note that arrives from another machine is treated as testimony rather than fact — it counts for a little less than your own, and it fades faster, losing about half its weight over a month while your own notes are left exactly as they are. So a busy machine somewhere else can never push your own answer down the list, and you can give any particular machine more or less weight if you come to trust it more.

how recall ranks a search →

Privacy

Only you can read it.

Your memory lives right on your own device. Anything your assistants share with each other gets scrambled on your device first — turned into gibberish that only the assistant you’re sending it to can turn back into words. The connecting service — the part in the middle that links your team together — just passes that scrambled text along. It can’t unscramble it, and it keeps no copy of anything. And you can keep separate projects in separate teams that never see each other, so work for one client never leaks into another.

Only the receiver can read it. Anything your team shares is scrambled on your device first, and only the assistant you send it to can turn it back into words (X25519).
Only you can give orders. Your own device holds a secret proof that it’s really you, so no one else can pretend to be you and change your setup (Ed25519).
Safe the whole way there. Everything travels over the same kind of secure connection your bank uses (TLS 1.3).

What the connecting service sees Scrambled

9bKQ2mXr7vTLpZ0eNcA1wYhF8sjUMP4iR6gD3oQlV5cBu2Xn8kEzWt0mYpYh4WsRf7iL9aQxH3pN6gQlD5cBu2Xr9kVcT0mZpA1wYhF8sjUMP4iR6gD3oQlVZ4Tn8Lx2vK9wEoR1cdH7sYbF0jAuMP3iN6gQlD5cBu2Xr9kVcT0mZpYh4WsK7QeR2pX9mLvNcA1wYhF8sjUMP4iR6gD3oQlV5cBu2Xn8kEzWt0mYpYh4WsRf7iL9aQxH3pN6gQlD5cBu2Xr9kVcT0mZpA1wYhF8sjUMP4iR6gD3oQlVZ4Tn8Lx2vK9wEoR1cdH7sYbF0jAuMP3iN6g==

to the receiver X25519signed by you Ed25519on the wire TLS 1.3

Now live

From your phone. No setup needed.

You don’t need to be a developer. Open the Claude app on your phone, or any web browser, and you can start a task, watch your assistants work, and pick things back up later — no fiddly setup, nothing to install. If you can use a chat app, you can use this.

Open your control panel →

A real moment

One quiet night.

It’s late, and I’ve got two assistants going. One’s on my work laptop, deep in a client’s billing code. The other’s on the computer at home, poking at a hobby project nobody’s paying for — and I keep the two on separate teams on purpose. I’ve been burned before: a different AI once dredged up a client’s private note while I was messing about on a weekend, and it still makes me wince. So tonight I test it. I ask the home one whether it knows anything at all about that client’s billing. Nothing comes back. Not hidden, not filtered — it genuinely never had it. Two projects, kept completely apart, exactly the way it should be.

One way a memory keeps your worlds apart

Go deeper

The long version, if you want it.

Captain Fleet runs on Captain Memo, the open-source memory engine. Rather than restate its documentation here, these are the pages that explain each piece properly — the same words its own users read, kept in one place so they never drift apart.

How recall works → How dreaming works → Every stat, explained → The memory engine →

Get started

Give your AI a memory of its own.

Captain Fleet is sailing its first wave — entry is by invitation for now, with public sign-ups to follow. If you were invited, come aboard and set up your own private memory, then connect every one of your assistants to it. The part that stores your memory is open, so if you’re the technical type — or have a friend who is — you can check exactly how it works, line by line.

Have an invite? Come aboard →Already have an account? Sign in For developers: read the code