It does not forget.

Memory sounds like a feature. It is closer to the entire point. Without memory, an assistant is a stranger you reintroduce yourself to every time: name, situation, preferences, context. The cost of that is hidden but enormous. You stop using it for things that matter because the warm-up is too expensive.

1Presence inverts that. You explain something once. Forever after, it knows. Not just the last few exchanges — the entire arc of your work, the people in it, the way you like things done. Tell it on Monday that Tuesday mornings are your planning time and three months later it will respect that.

This is what makes a tool feel like a presence. Not the quality of any single answer — the absence of having to set the scene.

1Presence keeps three different kinds of memory, each suited to a different shape of information. They work together so that asking a simple question can quietly draw on all of them.

1Presence pays attention to the things that tend to matter later: people, projects, preferences, decisions, recurring patterns, deadlines, commitments, opinions you have expressed. It tends to ignore the ephemeral — passing references, one-off questions, throwaway lines. A standing preference — how you like to be written to, what to skip — is handled with more care: before it keeps one, it shows you the exact words it would store, with Save and Not now, and saves only when you say so, for that agent.

What stays private is a real control, not a hope. An agent you seal keeps its memory to itself — nothing it learns reaches the shared picture. A folder you keep to one agent is read by that agent alone. And you can tell it to forget anything, at any time, in plain language: "forget that I mentioned X" is a real command.

Memory is usually a closed feature. 1Presence treats it as a first-class artefact. You can:

• Open the memory view and browse every wing, room and drawer 1Presence has filed away.
• Search the knowledge graph and the memory map for any person, project or event — even with a typo or a half-remembered name.
• Ask 1Presence to explain what it knows about a topic — and which conversations and sources contributed.
• Correct or remove anything that's wrong just by telling 1Presence — the change carries into every future answer.

The product is more trustworthy when you can see it working.

When you start creating specialist agents, memory gets a clean structure. You decide how much each agent shares: its memory can be open to the others; private in what it writes (it reads the shared picture, but its own notes stay its own); contributing (it reads only its own, but what it learns flows up to the rest); or isolated — a separate memory, sealed from every other agent. So an inbox-keeper's notes need not pollute your researcher's context, while facts about your world — your projects, the people you work with, decisions you have made — stay in shared knowledge every agent can draw on. Reaching into another agent's past conversations works the same way: the agent asks, you answer once, and the answer is kept on its Access tab — and no grant ever opens an agent you sealed.

Presence, your starter agent, is the relationship holder. It captures personal detail exhaustively. Specialist agents only file what is relevant to their role. The result is a memory system that scales as you bring in more agents, instead of getting noisier. A team workspace gets a memory zone of its own, kept apart from yours.

Everything in memory is yours to take. On any memory screen — the map, the knowledge graph, the agent diary — tap Export. You get one JSON file holding all three: the filed notes, the facts and relationships, and the diary. Readable in any editor. Your vault is plain markdown you already hold. If you ever leave, your memory leaves with you.