Memory

Dropstone keeps a persistent memory that follows your account across chat, the CLI, and the SDK. Correct it once and it should not need correcting again, anywhere you use it.

Dropstone keeps two kinds of memory. Standing rules apply to every task without being searched for. Facts are recalled only when they are relevant. Here is why the difference matters and how it decides.

Dropstone is a self-learning agent. It records what it learns from corrections, from finished work, and from sources you ask it to study, and it uses that the next time without being told. Here is the loop.

Dropstone memory belongs to your account, not to one app. A rule you set in the CLI applies in chat, and something learned in chat is available to the SDK. One memory, every surface.

Ask Dropstone what it remembers and it lists everything, standing rules separately from facts. You can also ask what memory it used on a specific reply. Nothing is hidden from you.

Tell Dropstone to forget something and it stops applying it. Tell it a fact should be a rule, or a rule is too broad, and it adjusts. Only you can remove a memory. It never forgets on its own.

In a Dropstone organization, memory has three levels. Private is yours alone. Team is shared with one team. Organization is shared with everyone. Nothing is shared unless its author decides to share it.

What Dropstone memory stores, what it never stores, who can see it, and how to keep something out of it. Memory is private to your account and you can see and remove all of it.