Detailed parameter documentation for adding memories to Supermemory.

​
Request Parameters

​
Required Parameters

​
content
string
required
The content to process into memories. Can be:
  • Plain text content
  • URL to process
  • HTML content
  • Markdown text
{
  "content": "Machine learning is a subset of AI..."
}
URL Examples:
{
  "content": "https://youtube.com/watch?v=dQw4w9WgXcQ"
}

​
Optional Parameters

​
containerTag
string
Recommended. Single tag to group related memories. Improves search performance.Default: "sm_project_default"
{
  "containerTag": "project_alpha"
}
Use containerTag (singular) for better performance than containerTags (array).
​
metadata
object
Additional metadata as key-value pairs. Values must be strings, numbers, or booleans.
{
  "metadata": {
    "source": "research-paper",
    "author": "John Doe",
    "priority": 1,
    "reviewed": true
  }
}
Restrictions:
  • No nested objects
  • No arrays as values
  • Keys must be strings
  • Values: string, number, or boolean only
​
customId
string
Your own identifier for the document. Enables deduplication and updates.Maximum length: 255 characters
{
  "customId": "doc_2024_01_research_ml"
}
Use cases:
  • Prevent duplicate uploads
  • Update existing documents
  • Sync with external systems
​
raw
string
Raw content to store alongside processed content. Useful for preserving original formatting.
{
  "content": "# Machine Learning\n\nML is a subset of AI...",
  "raw": "# Machine Learning\n\nML is a subset of AI..."
}

​
File Upload Parameters

For POST /v3/documents/file endpoint:
​
file
file
required
The file to upload. Supported formats:
  • Documents: PDF, DOC, DOCX, TXT, MD
  • Images: JPG, PNG, GIF, WebP
  • Videos: MP4, WebM, AVI
Maximum size: 50MB
​
containerTags
string
Container tag for the uploaded file (sent as form field).
curl -X POST "https://api.supermemory.ai/v3/documents/file" \
  -F "[email protected]" \
  -F "containerTags=research"

​
Container Tag Patterns

// By user
"user_123"

// By project
"project_alpha"

// By organization and type
"org_456_research"

// By time period
"2024_q1_reports"

// By data source
"slack_channel_general"

​
Performance Considerations

// ✅ FAST: Single tag
{ "containerTag": "project_alpha" }

// ⚠️ SLOWER: Multiple tags
{ "containerTags": ["project_alpha", "backend", "auth"] }

// ❌ AVOID: Too many tags
{ "containerTags": ["tag1", "tag2", "tag3", "tag4", "tag5"] }