Your work stays on your computer.

Your prompts travel. The whole map on one page: what stays, what leaves, and what we keep.

What we don't do.

  • We don't read your conversations
  • We don't train models on your data
  • We don't sell or share your information with third parties
  • We don't store conversation content on our servers
  • Your agent reaches local files with no cloud connection
  • Your agent's model-catalog refresh and its startup update check are both switched off in your configuration
  • No favicon fetching, no location requests, no triggers running until you set them up

What one request does.

Your team works on your machine. When it needs to think, one request goes out and the answer comes back.

Every item, in two columns.

Stays on your computer

  • Conversations: everything you say to your team and everything it says back
  • Files your agents read, write, or process
  • Team memory: what they have learned about your preferences, patterns, and priorities
  • Agent configuration, skills, and personalisation
  • Workspace data: emails fetched, calendar entries cached, research compiled
  • Prompts to a model that runs on this computer, when you choose one for an agent in Settings

Unless you grant a time-limited support session, we can't see, access, or retrieve any of it.

Leaves your computer

  • Prompts, routed through our proxy to the model provider: your message, the relevant conversation history, the task instructions, excerpts of your local data when the task needs them, and what the tools and APIs the agent calls return, when those results are in the conversation
  • Account and billing: name, email address, plan tier. Stripe holds the card, and we don't see the full number
  • Usage metadata: model name, serving provider, token counts, cost, time, plan tier and technical fingerprints of each call, including a short digest of each earlier message, buffered up to 7 days. Not content
  • Service metadata: deployment status, agent health checks, error logs. No conversation content
  • Diagnostics: whether setup finished, which model answered, which screen you were on, which marketplace item you installed. Never message, prompt, or file content, and you can turn them off
  • Relay, only if you pair a phone or connect a chat platform that delivers by webhook: messages for your phone pass through it in an end-to-end encrypted envelope it cannot read, and wait there for up to 7 days when your computer is offline. A Teams or Google Chat message passes through it in transit and is not stored
  • App connections, only for the apps you connect under More work apps: their sign-ins are held for Maxiful by our connections provider in the United States, and what each app action sent and returned is kept there for up to a year. Maxiful itself keeps none of it

The minimum needed to run the service.

The thinking happens in the cloud.

An AI team has to reason, and that runs on models far too large for a laptop. So the prompt leaves. This is how every cloud AI works. The difference is that we draw you the map.

  • Routed, not stored. Calls pass through our infrastructure for authentication and usage management. We don't store their content.
  • No training by default. Through our model proxy we use only providers that don't train on customer data, unless the workspace owner allows providers that may train, which Maxiful holds off once a Google account has been connected. Cheaper routes exist through providers with weaker policies, and by default we don't take them: when privacy and price pull apart, we pay the difference. An assistant on one of your own subscriptions (ChatGPT or Codex, Grok, or Claude) sends its prompts to that provider under your own account and its terms instead, and with a model on your computer the prompt stays there.
  • Metadata, not content. Model name, serving provider, token counts, cost, time, plan tier and technical fingerprints of each call, including a short digest of each earlier message, buffered up to 7 days, so your dashboard works. A digest cannot be turned back into the message.

The rest of it, in short.

  • No standing accessWe can't reach your computer. If support needs to see your agent's configuration or logs, we ask first, and only for a time-limited session.
  • If you leaveYour local data stays on your computer, whether you uninstall or not. We delete your account information within 6 months. Billing records are kept for 7 years, as the Swedish Bookkeeping Act requires.
  • Where it runsOur cloud services and CDN run on Cloudflare's global network, and we operate no data centres of our own. Some providers sit outside the EU/EEA; where personal data is transferred, we rely on Standard Contractual Clauses.
  • On your computerCredentials are written with restricted file permissions. Your Maxiful session sits in your operating system's credential store; some connected tools keep their own login in their own file on your machine. Skills run with the permissions you set, and you can set any agent to ask you before it runs something new.
  • Welcome emailWhen setup finishes, your email address goes once to our welcome-email service, which sends you a getting-started email.
  • Background work that spends your AI budgetThree features run on their own, without a prompt from you, and each is on by default. Self-learning reviews long conversations, and once a week the skills each assistant made, looking for lessons worth keeping (off switch: skills.workshop.autonomous.mode). While an assistant works with you, it can correct a skill it made itself, and it folds your correction into the skill it used, asking you first unless you let it. A session observer writes a short status note after each session, using the cheapest model in your configuration (off switch: gateway.controlUi.sessionObserver). Memory dreaming is set to run a nightly consolidation pass at 03:00 local time (off switch: plugins.entries.memory-core.config.dreaming.enabled); see Local memory search below for how it runs on your own machine. All three call the same model provider as your normal conversations and are billed the same way. No new destination for your data.
  • Personal recallPersonal recall is on by default on an install used by one person, so your agent can draw on your other private conversations with it when it answers you. See Local memory search below for how that recall runs on your own machine. On an install several people share with the same agent, it's off by default, so one member's conversations don't surface in another's.
  • A few messages still say OpenClawMaxiful runs on OpenClaw, and a handful of failure messages your agent posts into chat, for example about a full disk or a broken credential store, currently name OpenClaw instead of Maxiful. We've accepted that for now.
  • Local memory searchYour install downloads a 340 MB local embedding model once, so your agent's memory is searchable on your own machine. On most machines, memory content never leaves it. On machines with less than 8 GB of memory or 2 GB of free disk, memory search runs through the same model provider that already answers your agent's conversations, and the app tells you when that is the case.
  • Web searchYour agent searches the web only when it decides a question needs it. The query text then goes to Perplexity through OpenRouter, and the search is billed to your existing OpenRouter allowance like any other call.
  • Inviting a colleagueWhen you invite a colleague by email, their email address is sent to Maxiful so the invitation can be delivered, and their membership is recorded there. No conversation, no file and no other detail about them leaves the machine. A colleague invited through your team's own chat workspace has nothing sent at all.
  • Shared-machine memory indexingIf the built-in memory index cannot run on a machine that several people use, conversations, including your colleagues', are sent for indexing to the same provider that already answers them.
  • A colleague's new deviceEach new device of a colleague waits until the owner lets it in on the Team page, under People. Nothing is sent to Maxiful for that; the approval happens on the owner's machine.
  • Connecting another assistantAn assistant you connect can ask your assistant about anything it knows, on this machine; nothing about it is sent to Maxiful.
  • EncryptionWhat travels between your computer and us goes over an encrypted connection. What we hold sits on Cloudflare's platform, which encrypts it at rest. What stays on your computer sits on your own disk, under your own disk encryption, in files written with restricted permissions.
  • Voice notesA voice note sent to your agents is written out by your computer's own speech recognition first. One it cannot make out goes through Maxiful's model proxy to the model provider to be written out, and is billed to your allowance like any other call. In the app, Transcribe voice notes turns that off, and Keep conversations on this computer keeps every voice note on your machine; either way, your agent is told when it could not hear one.

The formal version.

Our privacy policy covers the same ground in legal language.

Read the privacy policy See what runs where

Maxiful is a product of Maxiful AB, a data controller under UK and EU GDPR.