A portrait, not a transcript

Every AI assistant either forgets you between sessions or keeps a chat log. Neither of those is knowing you.

We read dozens of essays on self-organisation and took apart two dozen competitors. For almost all of them "memory" is either nothing, or a RAG search over your own notes that rebuilds every few minutes. The closest in spirit is Morgen with its Frames - but Frames are planning templates, not an understanding of the person.

What we accumulate

Memory at three levels - you, your spheres and your projects. You can save "mornings work better for me" or "this project is waiting for a contractor to reply". These notes are available to read and correct, with previous versions preserved when you change them.

The portrait changes behaviour, not just tone

Save a preference such as "do not plan in the evening". The assistant takes it into account in advice and suggestions for your plan and tasks. You can read, edit or remove it in memory.

That is adaptivity. But our way: a readable, editable fact, not a hidden weight adjustment inside a black box. We do not switch methodologies - one system for everyone, what adapts is the contents of the memory.