​

Brain

Upload documents to build searchable knowledge graphs. The Brain page (route /datasets) lists all the brains in your workspace. A brain is a container for documents and all subsequent operations. See Datasets for the underlying concept; the API, SDK, route names, and analytics events continue to use “dataset” (“Brains” in analytics), while the UI uses the singular Brain.

​

Brain list

The page uses a Finder-style two-column layout:

• The left column lists your brains. Each brain shows a status dot, its document count, and Share and Delete actions.
• The right column lists the documents in the currently selected brain.

Select a brain in the left column to load its documents on the right.

​

Status dots

The status dot reflects the brain’s processing state: A brain whose graph is outdated (its config changed after files were processed) also shows an amber dot.

​

Create a brain

Click New brain to open the Create brain modal, enter a name, and click Create brain. Names cannot contain spaces or periods — otherwise you’ll see the error Dataset name cannot contain spaces or periods. Names are lowercased on create. The name field uses the placeholder e.g. product-docs, sec-filings…. Newly created brains are automatically granted tenant-level read and write permissions, so every member of the current tenant can see and write to them. To restrict a brain to specific users, revoke the tenant grant and assign per-user permissions through the permissions API.

​

Manage documents

The documents column header includes two actions:

• Add files — Browse and upload files. Supported formats: PDF, CSV, TXT, Markdown, JSON, DOCX.
• Paste text — Open a textarea modal and paste raw text. The text is saved as pasted-text-{timestamp}.txt.

You can also drag files anywhere onto the documents column — a Drop to upload overlay appears while dragging. Each document row shows a file-type badge (PDF, DOC, MD, TXT, CSV, JSON), the file size, the upload date, and a Delete button (confirm dialog Delete document). Uploaded files appear in the document list automatically — no manual page refresh is needed. Because the background ingestion step can save document records a few moments after the upload call returns, the page keeps polling for the new documents and updates the list as soon as they are available. After upload, the add and cognify pipeline runs in the background.

​

Refresh and polling

Click Refresh to re-poll dataset statuses on demand. The page also polls automatically every 5 seconds while any brain is in a pending or running state, updating the status dots as processing completes.

​

Brain detail

The brain detail page (route /datasets/[id]) shows a single brain. The header displays the dataset name (with a Default badge for default_dataset), the document count, and a status pill: Header actions:

• Sync — Re-runs cognify. Appears only for connected (integration) sources.
• Delete — Removes the brain. Hidden for default_dataset.
• Share — Manage access.
• Upload files — Add documents.

Per-brain config (graph model, prompt, ontology) is set here and on the Memory Schema page. Changing config when a brain already has files marks the brain Outdated until it is re-processed.

​

Sync a brain

For brains connected to an external (integration) source, the brain detail header includes a Sync button that re-runs the cognify pipeline against the current contents. Use this to rebuild the knowledge graph after source data changes without uploading new files again. Brains without a connected source do not show this button.

​

Share a brain

Use the Share action (on a brain in the left column or in the brain detail header) to open the Share brain modal. From here you can:

• Share with your whole workspace — Grant access to Everyone in workspace, which covers all current and future members. Choose Can edit (read and write — members can query the brain and run cognify on it) or Can view (read-only). This grants the permission to the workspace (tenant) principal, so newly added members are included automatically without any per-member step.
• Share with individual agents and users — Grant read-only access to a specific agent or user from the list.

Sharing is applied immediately for the current session. The modal does not yet list shares granted previously; to manage grants in detail, use the permissions API.

​

Brain selector

The brain selector appears on the pages where filtering by brain is relevant: Search, Mindmap (knowledge graph), Memory Schema, Overview (dashboard), and the brain detail page. On other pages the breadcrumb shows only the workspace and current page name. Selecting a brain is global — it filters content across all applicable pages:

• The Search page queries only that brain.
• The Mindmap page visualizes only that brain’s graph.
• The Overview dashboard scopes metrics and search to that brain.

To search or visualize across all brains, set the selector back to All datasets.

​

Empty state

When you have no brains yet, the page shows No brains yet with a Create brain call to action.

​

Delete a brain

Use the Delete action on a brain (in the left column or the brain detail header). The confirm dialog warns that this will permanently remove the dataset and all its files. This action cannot be undone. The default_dataset brain cannot be deleted: it has no Delete button and shows a Default badge on its detail page.