Supermemory
App · 20 actions
Store documents, search memories, and read profiles from Supermemory.
Actions
| Action | What it does |
|---|---|
| Add document | Add document in Supermemory. |
| Add documents | Add documents in Supermemory. |
| Count document memories | Count document memories in Supermemory. |
| Delete documents | Delete documents in Supermemory. |
| Delete profile buckets | Delete profile buckets in Supermemory. |
| Forget memories | Forget memories in Supermemory. |
| Get connector | Retrieve connector from Supermemory. |
| Get document | Retrieve document from Supermemory. |
| Get memory | Retrieve memory from Supermemory. |
| Get namespace | Retrieve namespace from Supermemory. |
| Get organization | Retrieve organization from Supermemory. |
| Get profile | Retrieve profile from Supermemory. |
| List connectors | Retrieve a page of connectors from Supermemory. |
| List documents | Retrieve a page of documents from Supermemory. |
| List namespaces | Retrieve a page of namespaces from Supermemory. |
| List profile buckets | Retrieve a page of profile buckets from Supermemory. |
| Search memories | Search memories in Supermemory. |
| Sync connector | Sync connector in Supermemory. |
| Update document | Update document in Supermemory. |
| Update namespace | Update namespace in Supermemory. |
Add document
Add document in Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents.
- Content
contenttextRequired - The content to process. This may be plaintext or a URL to supported rich content.
- Record ID
record_idtext - An optional caller-defined document ID.
- Supporting context
supporting_contexttext - Context used to guide memory extraction within this namespace. Max 1500 characters.
- Metadata
metadataobject - Arbitrary metadata attached to the document and derived data.
- Group
groupobject - Metadata values that isolate related context within the namespace.
- Date
datetext - When the source content is from, in ISO 8601 format.
- Task type
task_typetext - Processing pipeline. "memory" builds durable learned context; "superrag" optimizes the document for retrieval without generating memories.One of:
memory,superrag. - Dreaming
dreamingtext - Dreaming.One of:
dynamic,instant.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"id": "example",
"status": "unknown"
}
}Add documents
Add documents in Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents.
- Documents
documentslistRequired - Documents to ingest or append in one request.
- Task type
task_typetext - Processing pipeline. "memory" builds durable learned context; "superrag" optimizes the document for retrieval without generating memories.One of:
memory,superrag. - Dreaming
dreamingtext - Dreaming.One of:
dynamic,instant.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"count": 1,
"failed": 1,
"results": []
}
}Count document memories
Count document memories in Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents.
- Ids
idslistRequired - Ids.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"counts": []
}
}Delete documents
Delete documents in Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents.
- Ids
idslistRequired - Document identifiers to permanently delete from this namespace.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"count": 1,
"errors": []
}
}Delete profile buckets
Delete profile buckets in Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace to search. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope memories.
- Buckets
bucketslistRequired - Namespace-owned bucket names to delete. Organization-level buckets are protected and cannot be removed here.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"buckets": {}
}
}Forget memories
Forget memories in Supermemory.
Inputs
- Namespace
namespacetextRequired - Namespace containing the memories to forget. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope memories.
- Ids
idslistRequired - Memory identifiers to remove from normal recall.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"count": 1,
"errors": [],
"matches": []
}
}Get connector
Retrieve connector from Supermemory.
Inputs
- Namespace
namespacetextRequired - Namespace identifier. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents and memories.
- Connector ID
connector_idtextRequired - Connector identifier returned when the connector was created.
- Include
includelist - Comma-separated extras. syncs: the 10 most recent sync runs with their failed items. picker: a one-time hosted picker URL.One or more of:
syncs,picker.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"account": "example",
"authorization": {
"expiresAt": "example",
"url": "example"
},
"capabilities": {
"selectable": false,
"webhooks": false
},
"config": {},
"documentCount": 1.0,
"documentLimit": 1.0,
"id": "example",
"latestRun": {},
"namespace": "example",
"picker": {},
"provider": "notion",
"selection": {},
"syncs": [],
"system": {
"createdAt": "example",
"lastSuccessfulSyncAt": "example",
"status": "pending_authorization"
}
}
}Get document
Retrieve document from Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents.
- Document ID
document_idtextRequired - The public document ID.
- Include
includelist - Comma-separated child resources to include: chunks, memories, or both.One or more of:
chunks,memories.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"chunks": [],
"content": "example",
"id": "example",
"memories": [],
"metadata": {},
"summary": "example",
"system": {
"createdAt": "example",
"dreamingStatus": "dreaming",
"source": "example",
"status": "unknown",
"updatedAt": "example"
},
"title": "example",
"type": "example"
}
}Get memory
Retrieve memory from Supermemory.
Inputs
- Namespace
namespacetextRequired - Namespace containing the memories to forget. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope memories.
- Memory ID
memory_idtextRequired - Memory identifier.
- Include
includelist - Comma-separated extras. related: the memory's version history and connected memories. documents: the source document, also attached to each related memory when both are requested.One or more of:
related,documents. - Related limit
related_limitnumber - Related limit.From 1 to 100.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"id": "example",
"included": {
"document": {
"id": "example",
"metadata": {},
"summary": "example",
"system": {
"createdAt": "example",
"updatedAt": "example"
},
"title": "example",
"type": "example"
},
"related": {
"children": [],
"parents": [],
"siblings": []
}
},
"isForgotten": false,
"isInference": false,
"isLatest": false,
"isStatic": false,
"memory": "example",
"metadata": {},
"system": {
"createdAt": "example",
"updatedAt": "example"
},
"version": 1
}
}Get namespace
Retrieve namespace from Supermemory.
Inputs
- Namespace
namespacetextRequired - Namespace identifier. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents and memories.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"namespace": "example",
"supportingContext": "example",
"system": {
"createdAt": "example",
"updatedAt": "example"
}
}
}Get organization
Retrieve organization from Supermemory.
Inputs
None.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"namespaceCount": 1,
"organizationalContext": "example"
}
}Get profile
Retrieve profile from Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace to search. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope memories.
- Filter
filtertext - Type-safe metadata conditions that limit which memories contribute to the profile.
- Buckets
bucketslist - Custom buckets to return. Omit to return every effective bucket.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"profile": {
"buckets": {},
"dynamic": [],
"static": []
}
}
}List connectors
Retrieve a page of connectors from Supermemory.
Inputs
- Namespace
namespacetextRequired - Namespace identifier. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents and memories.
- Provider
providertext - Only return connectors for this provider.One of:
notion,google-drive,onedrive,gmail,github,web-crawler,s3,granola. - Page
pagenumber - One-based page number.From 1 to 9007199254740991.
- Limit
limitnumber - Maximum connectors to return per page.From 1 to 100.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"connectors": [],
"pagination": {
"currentPage": 1.0,
"hasMore": false,
"limit": 1.0,
"nextCursor": "example",
"totalItems": 1.0,
"totalPages": 1.0
}
}
}List documents
Retrieve a page of documents from Supermemory.
Inputs
- Namespace
namespacetextRequired - Namespace containing the resources to list. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope resources.
- Cursor
cursortext - Cursor.
- Limit
limitnumber - Maximum resources to return per page.From 1 to 100.
- Sort
sorttext - Field used to order results. Position is available only when listing chunks.One of:
createdAt,updatedAt,position. - Order
ordertext - Ascending or descending sort direction.One of:
asc,desc. - Filter
filtertext - Type-safe metadata conditions applied before pagination.
- Include
includeobject - Optional extras.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"documents": [],
"pagination": {
"currentPage": 1.0,
"hasMore": false,
"limit": 1.0,
"nextCursor": "example",
"totalItems": 1.0,
"totalPages": 1.0
}
}
}List namespaces
Retrieve a page of namespaces from Supermemory.
Inputs
- Page
pagenumber - One-based page number.From 1 to 9007199254740991.
- Limit
limitnumber - Maximum namespaces to return per page.From 1 to 100.
- Q
qtext - Case-insensitive substring to match against namespace names.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"namespaces": [],
"pagination": {
"currentPage": 1.0,
"hasMore": false,
"limit": 1.0,
"nextCursor": "example",
"totalItems": 1.0,
"totalPages": 1.0
}
}
}List profile buckets
Retrieve a page of profile buckets from Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace to search. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope memories.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"buckets": {}
}
}Search memories
Search memories in Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace to search. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope memories.
- Query
querytextRequired - Natural-language question, topic, or phrase to retrieve relevant context for. Replaces the v4 `q` field.
- Filter
filtertext - Type-safe metadata conditions applied before ranking results. Replaces the v4 `filters` field and unifies both legacy filter formats into one expression type.
- Search mode
search_modetext - Search surface. "hybrid" combines learned memories with source chunks, "memories" returns learned context, and "chunks" returns source passages.One of:
hybrid,memories,chunks. - Limit
limitnumber - Maximum number of results to return.From 1 to 100.
- Include
includeobject - Optional context to include alongside each matching result.
- Threshold
thresholdnumber - Minimum relevance score from 0 to 1. Raise it for precision (fewer, accurate results) or lower it for broader recall (more results).From 0 to 1.
- Rerank
reranktext - Rerank.One of:
none,order,aggregate. - Rewrite query
rewrite_querytrue/false - Expand and clarify the query before retrieval to improve recall for conversational or underspecified prompts. This increases the latency by about 400ms.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"results": [],
"searchTime": 1.0
}
}Sync connector
Sync connector in Supermemory.
Inputs
- Namespace
namespacetextRequired - Namespace identifier. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents and memories.
- Connector ID
connector_idtextRequired - Connector identifier returned when the connector was created.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"id": "example",
"status": "example"
}
}Update document
Update document in Supermemory.
Inputs
- Namespace
namespacetextRequired - The isolated namespace. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents.
- Document ID
document_idtextRequired - The public document ID.
- Content
contenttext - The content to process. This may be plaintext or a URL to supported rich content.
- Supporting context
supporting_contexttext - Context used to guide memory extraction within this namespace. Max 1500 characters.
- Metadata
metadataobject - Arbitrary metadata attached to the document and derived data.
- Group
groupobject - Metadata values that isolate related context within the namespace.
- Date
datetext - When the source content is from, in ISO 8601 format.
- Task type
task_typetext - Processing pipeline. "memory" builds durable learned context; "superrag" optimizes the document for retrieval without generating memories.One of:
memory,superrag. - Dreaming
dreamingtext - Dreaming.One of:
dynamic,instant.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"id": "example",
"status": "unknown"
}
}Update namespace
Update namespace in Supermemory.
Inputs
- Namespace
namespacetextRequired - Namespace identifier. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents and memories.
- Supporting context
supporting_contexttext - Background that guides how Supermemory interprets documents and forms memories. Max 1500 characters. Set null to clear it.
Outputs
dataobject- The result returned by Supermemory.
Example output
{
"data": {
"namespace": "example",
"supportingContext": "example",
"system": {
"createdAt": "example",
"updatedAt": "example"
}
}
}