Skip to main content
These v4 endpoints operate on extracted memories (not raw documents). SDK support coming soon — use fetch or cURL for now.For document management (list, get, update, delete), see Document Operations. For ingesting raw content (text, files, URLs) through the processing pipeline, see Add Context.

​
Create Memories

Create memories directly without going through the document ingestion workflow. Memories are embedded and immediately searchable. This is useful for storing user preferences, traits, or any structured facts where you already know the exact memory content. 
const response = await fetch("https://api.supermemory.ai/v4/memories", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    memories: [
      {
        content: "John prefers dark mode",
        isStatic: false,
        metadata: { source: "user_preference" }
      },
      {
        content: "John is from Seattle",
        isStatic: true
      }
    ],
    containerTag: "user_123"
  })
});

const data = await response.json();
// {
//   documentId: "abc123",
//   memories: [
//     { id: "mem_1", memory: "John prefers dark mode", isStatic: false, createdAt: "2025-..." },
//     { id: "mem_2", memory: "John is from Seattle", isStatic: true, createdAt: "2025-..." }
//   ]
// }

​
Parameters

ParameterTypeRequiredDescription
memoriesarrayyesArray of memory objects (1–100 items)
memories[].contentstringyesThe memory text (max 10,000 chars). Should be entity-centric, e.g. “John prefers dark mode”
memories[].isStaticbooleannotrue for permanent identity traits (name, hometown). Defaults to false
memories[].metadataobjectnoKey-value metadata (strings, numbers, booleans)
containerTagstringyesSpace / container tag these memories belong to

​
Response

{
  "documentId": "abc123",
  "memories": [
    {
      "id": "mem_1",
      "memory": "John prefers dark mode",
      "isStatic": false,
      "createdAt": "2025-01-15T10:30:00.000Z"
    }
  ]
}
FieldTypeDescription
documentIdstring | nullID of the lightweight source document created for traceability
memoriesarrayThe created memory entries
memories[].idstringUnique memory ID
memories[].memorystringThe memory content
memories[].isStaticbooleanWhether this is a permanent trait
memories[].createdAtstringISO 8601 timestamp
When to use this vs Add Context?Use Create Memories when you already know the exact facts to store (user preferences, traits, structured data). Use Add Context when you have raw content (conversations, documents, URLs) that Supermemory should process and extract memories from.

​
Forget Memory

Soft-delete a memory — excluded from search results but preserved in the system. Use this when you might want to restore later. 
await fetch("https://api.supermemory.ai/v4/memories/mem_abc123/forget", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${API_KEY}`
  }
});
The memory will no longer appear in search results but remains in the database.

​
Update Memory (Versioned)

Update a memory by creating a new version. The original is preserved with isLatest=false. 
await fetch("https://api.supermemory.ai/v4/memories", {
  method: "PATCH",
  headers: {
    "Authorization": `Bearer ${API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    // Identify by ID or content
    id: "mem_abc123",
    // content: "Original content to match",

    newContent: "Updated content goes here",
    metadata: {
      tags: ["updated"]
    }
  })
});

​
Parameters

ParameterTypeRequiredDescription
idstring*Memory ID to update
contentstring*Original content to match (alternative to ID)
newContentstringyesNew content for the memory
metadataobjectnoUpdated metadata
* Either id or content must be provided.

​
Next Steps