Skip to main content

Updated 2026-09-10 View as Markdown

Memory

Everything the workspace remembers, as folders and notes you can open and read.

Memory is the part that makes a workspace different from a chat window. What it learns is written down, filed, and still there next month.

It is not a hidden index. Open Memory and you are looking at the same notes the agent reads when it answers you.

The Memory page of a workspace, listing two folders: Concepts with 28 items, and People with 2 items.
Folders first, then notes. The tree grows out of the work. A workspace reading company material ends up with folders for people and projects; one reading research ends up with concepts.

What is in there

Folders group notes by what they are about. The agent makes them as it goes; you can ask it to reorganize, split, or rename in chat.

Notes are the unit. One note is one thing worth remembering: a person, an idea, a decision, a document it read. Each is a plain file, so nothing is locked in a format only we can open.

A single memory note. It shows the note's path, its title, a concept tag, a metadata block with created and ingested dates, then the body: a quotation, two paragraphs, and a source line naming where it came from.
A note carries its provenance. When it was written, how it got in, and at the bottom, where it came from. That last line is what makes an answer checkable.

How things get in

You tell it. Anything you say in chat that is worth keeping, it keeps. “Remember that Ana runs procurement” is enough.

It reads what you give it. Paste a document, drop a file, or point it at a page and it takes notes on what it read.

Skills write. A skill that researches a person or works through an inbox leaves its findings in memory, so the next run starts from the last one.

Scheduled work tidies. Overnight the workspace files what came in, links it to what it already knew, and cleans up after itself. That is why a workspace you have been feeding for a month answers better than one you set up yesterday.

Reading it well

Ask it to look. “Search your memory and tell me what we decided about pricing” beats “what did we decide about pricing.” A casual question can get answered from general knowledge rather than your material, and it sounds equally confident either way.

Ask for the note. An answer it cannot source is an answer you should not repeat. It will name the note, and you can open it.

Correct it in chat. If a note is wrong, say so. It will fix the note, not just the answer, so the correction survives the conversation.

Reading it from somewhere else

Memory is not only for chat here. Claude, ChatGPT and OpenClaw can search it and add to it through one address, with you choosing whether they may write. Use your memory from other assistants.

What it does not do

Memory is per workspace, and everyone in that workspace sees all of it. There is no per person view inside one, and no way to hide part of a workspace from someone who has access to it. If a group should see a different set of material, give them their own copy.