# Memory: documents, canvases and files that write themselves with you. Source: https://www.onsecondbrain.com/guide/memory Language: en Spanish version: https://www.onsecondbrain.com/guide/memory.es.md --- This is the part of the workspace where knowledge stops being a daily note and becomes something you consult. A document tree with a full editor, real-time collaboration, Miro-style canvases with Apple Pencil, files with inline preview, and an AI that generates and rewrites using your own material as context. ## Documents ### The document tree Documents are organized in a tree of folders and sub-documents, in the order you give them — by dragging — rather than the one a date imposes. - Free nesting: a document can have children, and those children can have their own. - Moving a document takes its whole branch with it. - Trash with restore for documents, canvases, recaps and clips. Files, on the other hand, are deleted for good. - With Move to workspace (right-click), a document goes to another of your workspaces with everything that hangs from it. Its Atlas tags do not travel: each workspace has its own Atlas. > **"Move to…": when dragging is not enough** > > Dragging works to move something two rows down. It does not work to send it to a folder four levels and three hundred pixels of scroll away, with both open at once: that is an arm-wrestle. > > So the right-click menu — and press-and-hold on the phone — has Move to…, which opens the two ways of finding a folder: browsing the tree, when you know where it goes but not what it is called, and searching by name, when you know the name and don't want to walk down by hand. Searching doesn't move: it takes you there, and the destination is confirmed from the path — two documents can share a name. > > It works for everything that lives in Memory, not just documents: a recap, a canvas, a file, a clip or an artifact all move the same way. ![A document open in the editor, with its tree alongside](https://www.onsecondbrain.com/screens/guide/doc.png) _The tree on the left, the document on the right. Under the title sits its parent: that is where it hangs, and how it moves._ ### The editor It is the same editor as the daily note, with all the formatting a real document needs. - **Full formatting** — Headings, lists, checkboxes, tables, quotes, code blocks, images, audio, video and attachments. Any block can be dragged to reorder it. - **Markdown, Mermaid and LaTeX** — Write in Markdown if that is faster for you, draw diagrams with Mermaid and set formulas with LaTeX. It all renders in the document. - **Knowledge intellisense** — As you type, the name of a person, project, organization or tag from your Atlas completes with Tab, spelled exactly as stored, and stays highlighted. The document shows up on that entity's entry. - **Attachments** — Files you upload hang from the document: images show in the text, and everything else opens in its viewer with a click. In the document's ⋯ menu, Version history takes it back to a saved version; and the Export button at the top gets it out as PDF, Markdown or a ZIP with its whole tree. ### Real-time collaboration A document is written by several people at once, live, each with their own cursor and without clobbering each other; it is shared with another account to edit or just view — with its whole branch, if you want — or published as a read-only link. How, in Secondbrain Teams. ![Two people editing the same document live, each with their own cursor](https://www.onsecondbrain.com/screens/loops/colaborando.jpg) _A document, live: two people typing, with cursors and presence._ ### Generating and editing with AI · Hobby What sets this apart from pasting your request into a generic chat is context: here the AI works on your material — your documents, your recaps, your files — and not on whatever you manage to paste into a chat. - **A full document from context** — You pick the type — Brief, Unify, Contents or Actions — and which sources, and it writes the whole document. - **Your own types** — Besides the fixed ones, up to two of your own with New type, so the output always comes out in your format. - **Create from an image · Pro** — A photo of a whiteboard or a sketch on paper becomes a structured document, with the text transcribed and the original image embedded. - **Rewrite a selection** — Select some text, Rewrite with AI, and tell it what to do: shorten it, make it formal, translate it. You see the before and after, and only the selection changes. ![A document's AI generation panel](https://www.onsecondbrain.com/screens/guide/doc-ai.png) _Generating means choosing what context goes in — child documents, recaps, files — and what kind. It writes from your material, not from what the AI remembers._ ## Beyond text ### Canvases An infinite Miro-style space for what does not fit in text: maps, architectures, relationship diagrams, sketches. - Shapes, arrows, text, sticky notes and frames, plus templates — retro, kanban, SWOT, mind map… — so you do not start from scratch. - Freehand drawing with Apple Pencil on iPad, with stroke pressure. - A canvas is shared or published inside a document, with its branch: it has no share of its own. - On the phone they open in a read-only viewer, with zoom and pan. ![Freehand drawing on a canvas with Apple Pencil, on iPad](https://www.onsecondbrain.com/screens/loops/canvas.jpg) _The same desktop workspace runs on the iPad: that is where the canvas gets drawn by hand, with the Pencil._ ### Files Everything you upload — to a document, with Upload file or through WhatsApp and Telegram — lands in Files. - Inline preview of PDF, Word, Excel, HTML and images, without downloading anything or leaving the app. - Rename, move, crop images and delete, with your storage usage in view. - A type filter at the top right — Docs, Recaps, Canvas, Artifacts, Clips, PDF, Images, Audio, Video, Documents, Spreadsheets — that only shows the types present in the open folder. - On the phone, any file opens in its own viewer. - Next to it, in Clips, live the pages and emails you saved with the Clipper. ![The workspace's file grid](https://www.onsecondbrain.com/screens/guide/files.png) _Everything you uploaded and everything the product generated, in one grid._ ### Artifacts from Claude, ChatGPT and Gemini What you build in an AI chat — a prototype, a deck, a document, a diagram — is saved here as an artifact: an exact copy that looks the same as in the chat, with every version kept, and that can be published with a link. It opens in Docs with three tabs, View, Code and Versions, and hangs under a document like anything else. They come in two ways: the Web Clipper, which spots them in the conversation and keeps them up to date on its own, and the MCP connector, when you ask the model to save one. ## Search and connect ### Search: one box ⌘K (Ctrl+K) searches documents, daily notes, recaps, tasks and the Atlas. What literally says what you typed comes first, highlighted; Similar results — the same thing in other words — only show up when nothing matches literally. ### Integrations - **MCP** — External AI clients (Claude, ChatGPT, Gemini and others) can query and operate your workspace over the MCP protocol, only with the token you generate. Over MCP, an external AI client can list your tree, read a document, create a new one, update it, move it, search across all of them and link it to Atlas entities. See MCP.