Ingest

Ingestion gives Supermemory the source material it uses to build searchable context and memories. Add new content or update an existing source without creating a disconnected copy.

Operation	Purpose
`POST /ns/{namespace}/document`	Add text or a URL; reuse an ID to build on an existing document
`POST /ns/{namespace}/document/batch`	Bring in up to 600 documents together
`POST /ns/{namespace}/document/file`	Turn an uploaded file into searchable memory
`PATCH /ns/{namespace}/document/{id}`	Update metadata or replace canonical content
`POST /ns/{namespace}/document/file/{id}`	Completely replace a file-backed document
`PATCH /ns/{namespace}/document/file/{id}`	Refresh selected file details or its source

const { id, status } = await supermemory.add("user_1", {
  content: "The user prefers concise project updates",
  id: "conv_1",
  metadata: { source: "chat" },
  dreaming: "instant",
})

curl -X POST "https://api.supermemory.ai/ns/user_1/document?dreaming=instant" \
  -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content":"The user prefers concise project updates","id":"conv_1","metadata":{"source":"chat"}}'

The dynamic processing mode (default) groups related documents together so memories form from coherent, logical units rather than one isolated entry at a time. Use instant to process each document on its own right away; it bills one extra operation per document. Memories appear quickly only with dreaming: "instant". With the default dynamic mode, a fresh namespace can show zero memories and an empty profile for several minutes while extraction is batched. Use instant in quickstarts and tests. Every request is scoped to a namespace, keeping each user, project, or tenant isolated. See document write migration.

Content Management

Search

Profiles

Namespaces

Connectors

Organization

Ingest