> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Supermemory

> Supermemory is a memory and context API for ingesting, organizing, searching, and recalling information across applications.

![Supermemory logo](https://mintcdn.com/composio-preview/IA0_SoMcsWt17HEC/images/toolkits/supermemory.svg?fit=max\&auto=format\&n=IA0_SoMcsWt17HEC\&q=85\&s=eff4f9570dc1f5fc0f34847ba666a6ad)

* **Category:** artificial intelligence
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 86
* **Triggers:** 0
* **Slug:** `SUPERMEMORY`
* **Version:** 20261101\_00

## Tools

> [accordion] Add Document
>
> **Slug:** `SUPERMEMORY_ADD_DOCUMENT`
>
> Ingest text or a public URL as a Supermemory document and return its document ID and initial processing status.
>
> #### Input Parameters
>
> **content** `string` *required*
>
> Plain text or a public URL to ingest.
>
> **dreaming** `string ("instant" | "dynamic")`
>
> Processing mode; instant processes this document alone and may consume an extra operation.
>
> **metadata** `object`
>
> Flat metadata values: strings, numbers, booleans, or string arrays. Nested objects are not supported.
>
> **custom\_id** `string`
>
> Caller-defined stable document ID for deduplication or lookup.
>
> **task\_type** `string ("memory" | "superrag")`
>
> Use memory for the full context layer or superrag for managed document retrieval.
>
> **container\_tag** `string`
>
> Container tag used to isolate this document's memories. Letters, numbers, underscores, colons, and hyphens only.
>
> **entity\_context** `string`
>
> Context about the container entity that should guide memory extraction (maximum 1500 characters).
>
> **filter\_by\_metadata** `object`
>
> Flat metadata filter limiting existing memories used as ingestion context. Values may be strings, numbers, booleans, or string arrays.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Add Documents
>
> **Slug:** `SUPERMEMORY_ADD_DOCUMENTS`
>
> Add 1 to 600 documents in one request, with per-document metadata and processing options. Inspect counts and results for partial failures; the tool raises an error if all documents fail, and the API does not guarantee atomicity or result ordering.
>
> #### Input Parameters
>
> **dreaming** `string ("instant" | "dynamic")`
>
> Processing mode applied to the whole batch: dynamic groups related documents; instant processes documents independently and bills one extra operation per document.
>
> **documents** `array` *required*
>
> One to 600 documents to ingest. Set each document's optional processing fields explicitly when its behavior must differ from provider defaults.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Add Namespace Document
>
> **Slug:** `SUPERMEMORY_ADD_NAMESPACE_DOCUMENT`
>
> Add text or a supported URL as searchable, evolving memory in an isolated namespace. Supply a new document ID to create a document, or reuse an existing ID to append information while preserving history. Ingestion is asynchronous: inspect the returned processing status and retrieve the document to check completion.
>
> #### Input Parameters
>
> **id** `string`
>
> Optional caller-defined document ID. A new ID creates a document; reusing an existing ID appends information while preserving history.
>
> **date** `string`
>
> Optional source-content date in ISO 8601 format.
>
> **group** `object`
>
> Optional metadata values isolating related context within the namespace; values may be strings, numbers, booleans, or string arrays.
>
> **content** `string` *required*
>
> Plain text or a URL to supported rich content to process.
>
> **dreaming** `string ("dynamic" | "instant")`
>
> Optional processing mode: dynamic (provider default) groups related documents; instant processes independently right away and bills one extra operation per document.
>
> **metadata** `object`
>
> Optional flat document metadata with string, number, boolean, or string-array values; nested objects are not supported.
>
> **namespace** `string` *required*
>
> Isolated namespace for a user, project, or other context; at most 100 letters, digits, underscores, colons, or hyphens.
>
> **task\_type** `string ("memory" | "superrag")`
>
> Optional processing pipeline: memory builds durable learned context; superrag supports retrieval without generating memories.
>
> **supporting\_context** `string`
>
> Optional context guiding memory extraction within this namespace, up to 1500 characters.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Add Namespace Documents
>
> **Slug:** `SUPERMEMORY_ADD_NAMESPACE_DOCUMENTS`
>
> Ingest 1 to 600 text or URL documents in an isolated namespace. Existing caller-defined IDs append information with single-document ingestion semantics. Acceptance is asynchronous, not completed processing. HTTP 200 may contain partial failures: inspect count, failed, and each result's error, details, and url. Accepted results precede failures; match by id or failed-item url, not position. An all-failed batch raises an error.
>
> #### Input Parameters
>
> **dreaming** `string ("dynamic" | "instant")`
>
> Batch processing mode: dynamic (provider default) groups related documents; instant processes independently and bills one extra operation per document.
>
> **taskType** `string ("memory" | "superrag")`
>
> Batch processing pipeline: memory builds learned context; superrag optimizes retrieval without generating memories.
>
> **documents** `array` *required*
>
> One to 600 documents to ingest or append.
>
> **namespace** `string` *required*
>
> Isolated user, project, or other namespace, up to 100 letters, digits, underscores, colons, or hyphens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Bulk Delete Documents
>
> **Slug:** `SUPERMEMORY_BULK_DELETE_DOCUMENTS`
>
> Deprecated provider v3 endpoint; shuts down December 31, 2026. Use v5 namespace document deletion (DELETE /ns/\{namespace}/document) instead. Delete up to 100 documents by ID, all documents in selected container tags, or documents matching a filepath. Container-tag and filepath selectors can delete many documents. Inspect success, deleted\_count, and errors for the actual outcome; an HTTP 200 alone does not prove every document was deleted.
>
> #### Input Parameters
>
> **ids** `array`
>
> One to 100 document IDs to delete.
>
> **filepath** `string`
>
> Delete documents matching this filepath. Full paths match exactly; a trailing / selects a path prefix.
>
> **container\_tags** `array`
>
> Deprecated selector: delete all documents in these containers. Each tag is at most 100 characters and uses letters, numbers, \_, :, or - only.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Configure Automatic Top-Ups
>
> **Slug:** `SUPERMEMORY_CONFIGURE_AUTOMATIC_TOPUPS`
>
> Deprecated legacy v3 API, scheduled to shut down December 31, 2026. Configure automatic paid USD credit purchases for the connected organization. Enabling reloads can cause financial charges when the credit balance is low. Requires an unscoped organization API key with admin or owner access; paid-plan and saved-payment-method requirements apply when enabling. Supply the full console configuration explicitly, including when disabling. Purchase limits do not cap total usage or the full invoice.
>
> #### Input Parameters
>
> **enabled** `boolean` *required*
>
> Whether to enable automatic paid credit top-ups.
>
> **quantity** `number` *required*
>
> USD credits to purchase per reload; the console minimum is 0.01.
>
> **threshold** `number` *required*
>
> USD balance threshold for automatic reloads; the console minimum is 0.
>
> **purchaseLimit** `object` *required*
>
> Explicit automatic purchase limit configuration. The console submits this object even when disabling reloads. No financial defaults are applied.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Configure Connection
>
> **Slug:** `SUPERMEMORY_CONFIGURE_CONNECTION`
>
> Deprecated by the provider: the legacy v3 API shuts down December 31, 2026. Use the v5 namespace connectors API for new integrations. Configure selected resources for an existing legacy connection; currently only GitHub supports resource configuration. Returns the provider's success flag, outcome message, and optional registered-webhook count.
>
> #### Input Parameters
>
> **resources** `array` *required*
>
> Resources selected for this connection, using the provider-defined resource objects returned by List Connection Resources. Currently supported for GitHub only; resource object fields are unrestricted in the provider schema.
>
> **connectionId** `string` *required*
>
> ID of the existing connection to configure.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Count Namespace Document Memories
>
> **Slug:** `SUPERMEMORY_COUNT_NAMESPACE_DOCUMENT_MEMORIES`
>
> Count live memories in a namespace for up to 100 public document IDs. Missing or inaccessible documents are omitted, not reported as zero.
>
> #### Input Parameters
>
> **ids** `array` *required*
>
> One to 100 public document IDs, each between 1 and 255 characters.
>
> **namespace** `string` *required*
>
> Isolated namespace identifying the user, project, or document scope.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Connection
>
> **Slug:** `SUPERMEMORY_CREATE_CONNECTION`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Use CREATE\_CONNECTOR for v5 namespace-scoped connectors. Initialize a provider connection and return its ID and any authorization URL. This does not open the URL or complete user authorization; the user must authorize separately before the connection can import documents.
>
> #### Input Parameters
>
> **metadata** `object`
>
> Optional flat metadata with string, numeric, or boolean values; may explicitly be null.
>
> **provider** `string ("notion" | "google-drive" | "onedrive" | "gmail" | "github" | "web-crawler" | "s3" | "granola")` *required*
>
> Provider for which to initialize a connection.
>
> **redirectUrl** `string`
>
> Optional URL to redirect the user to after provider authorization.
>
> **containerTag** `string`
>
> Optional container tag: up to 100 letters, numbers, underscores, colons, or hyphens.
>
> **containerTags** `array`
>
> Optional container tags, each up to 100 letters, numbers, underscores, colons, or hyphens.
>
> **documentLimit** `integer`
>
> Optional maximum number of documents to import, from 1 to 10000.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Connector
>
> **Slug:** `SUPERMEMORY_CREATE_CONNECTOR`
>
> Connect an external source to a namespace. Choose the provider-specific connector settings. OAuth providers return an authorization URL to send the user to; config-authenticated providers start syncing immediately.
>
> #### Input Parameters
>
> **connector** `string` *required*
>
> Provider-specific connector settings; provider selects the allowed config.
>
> **namespace** `string` *required*
>
> Namespace identifier scoping documents and memories, such as a user or project ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Memory
>
> **Slug:** `SUPERMEMORY_CREATE_MEMORY`
>
> Deprecated by the provider; v3/v4 APIs shut down on December 31, 2026. Use v5 namespace document ingestion for new integrations. Create 1 to 100 memories directly in an existing container, bypassing document ingestion. Generates embeddings and makes the memories immediately searchable.
>
> #### Input Parameters
>
> **memories** `array` *required*
>
> One to 100 memories to create directly.
>
> **containerTag** `string` *required*
>
> Existing space's container tag, up to 100 letters, digits, underscores, colons, or hyphens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Scoped Key
>
> **Slug:** `SUPERMEMORY_CREATE_SCOPED_KEY`
>
> Deprecated legacy v3 route; provider shutdown is December 31, 2026. No v5 scoped-key creation alternative is documented. Create an API key restricted to one namespace or a fixed list of namespaces, using an organization API key; scoped keys cannot mint further keys. Writable scoped keys can update and delete content within their namespaces. Returns a secret credential: store it securely and do not log it.
>
> #### Input Parameters
>
> **name** `string`
>
> Key display name. If omitted, the provider defaults to scoped\_\{containerTag}.
>
> **containerTag** `string`
>
> Namespace for the key; required unless containerTags is supplied. Up to 100 letters, numbers, hyphens, underscores, or colons.
>
> **rateLimitMax** `integer`
>
> Maximum requests per rate-limit window, from 1 to 10000. Provider default: 500.
>
> **containerTags** `array`
>
> Namespaces for the key. Takes precedence over containerTag when both are supplied.
>
> **expiresInDays** `integer`
>
> Optional key lifetime in days, from 1 to 365.
>
> **rateLimitTimeWindow** `integer`
>
> Rate-limit window in milliseconds, from 1 to 3600000. Provider default: 60000.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Connection
>
> **Slug:** `SUPERMEMORY_DELETE_CONNECTION`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Use DELETE\_CONNECTOR for v5 namespace-scoped connector deletion instead. Delete a specific connection by ID. By default this also deletes documents imported by the connection; set deleteDocuments to 'false' to retain them. Returns deleted connection IDs and providers.
>
> #### Input Parameters
>
> **connectionId** `string` *required*
>
> ID of the connection to delete.
>
> **deleteDocuments** `string`
>
> Whether to also delete documents imported by this connection. Defaults to the string 'true'; pass 'false' to retain imported documents.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Connector
>
> **Slug:** `SUPERMEMORY_DELETE_CONNECTOR`
>
> Disconnect a connector in a namespace and stop its webhooks. Imported documents are also deleted by default. Set deleteDocuments to false to preserve those documents.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Connector identifier returned when the connector was created.
>
> **namespace** `string` *required*
>
> Namespace identifying the user, project, or other connector scope.
>
> **deleteDocuments** `boolean`
>
> Also delete documents imported by this connector. Defaults to true; set false to preserve imported documents.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Container Tag
>
> **Slug:** `SUPERMEMORY_DELETE_CONTAINER_TAG`
>
> Deprecated by the provider: the legacy v3 API shuts down on December 31, 2026. Use v5 DELETE /ns/\{namespace} to delete a namespace instead. Delete a container tag and all its documents and memories. Only organization owners and admins can perform this destructive action.
>
> #### Input Parameters
>
> **container\_tag** `string` *required*
>
> Container tag to delete, together with all its documents and memories.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Document
>
> **Slug:** `SUPERMEMORY_DELETE_DOCUMENT`
>
> Permanently delete one document by ID. This does not remove the document's container-tag settings record.
>
> #### Input Parameters
>
> **document\_id** `string` *required*
>
> Supermemory document ID to permanently delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Namespace
>
> **Slug:** `SUPERMEMORY_DELETE_NAMESPACE`
>
> Retire a namespace and permanently delete its documents and memories. Optionally set moveTo to preserve its content by moving everything into another namespace first. A queued response only acknowledges an asynchronous move, not completed deletion; a deleted response confirms permanent removal.
>
> #### Input Parameters
>
> **moveTo** `string`
>
> Destination namespace receiving the content before deletion. Omit to permanently delete the content. Moves are asynchronous.
>
> **namespace** `string` *required*
>
> Namespace identifier to retire, such as a user or project ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Namespace Documents
>
> **Slug:** `SUPERMEMORY_DELETE_NAMESPACE_DOCUMENTS`
>
> Permanently delete 1 to 100 documents and their derived knowledge from a namespace by document ID or caller-defined ID. Each identifier is handled independently; successful deletions are preserved if others fail. Inspect count and every errors entry: HTTP 200 does not mean all documents were deleted.
>
> #### Input Parameters
>
> **ids** `array` *required*
>
> One to 100 document IDs or caller-defined IDs to permanently delete from this namespace. Each identifier is 1 to 255 characters.
>
> **namespace** `string` *required*
>
> Isolated namespace containing the documents, such as a user or project ID. At most 100 letters, numbers, underscores, colons, or hyphens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Namespace Profile Buckets
>
> **Slug:** `SUPERMEMORY_DELETE_NAMESPACE_PROFILE_BUCKETS`
>
> Remove 1 to 50 profile bucket categories created specifically for a namespace and return its updated effective bucket definitions. Unknown names are safely ignored. Organization-wide buckets are protected and cannot be removed with this action. Requires namespace write access.
>
> #### Input Parameters
>
> **buckets** `array` *required*
>
> One to 50 namespace-owned bucket slugs to delete. Each slug is 1 to 64 lowercase letters, digits, underscores, or hyphens, starting with a letter or digit. Organization-level buckets cannot be deleted here.
>
> **namespace** `string` *required*
>
> Isolated user or project namespace whose profile buckets to delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Provider Connection
>
> **Slug:** `SUPERMEMORY_DELETE_PROVIDER_CONNECTION`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Use DELETE\_CONNECTOR for v5 namespace-scoped connector deletion by connector ID instead. Delete connections for a specific provider and container tags. Returns the deleted connection IDs and providers.
>
> #### Input Parameters
>
> **provider** `string ("notion" | "google-drive" | "onedrive" | "gmail" | "github" | "web-crawler" | "s3" | "granola")` *required*
>
> Provider whose connections to delete.
>
> **containerTags** `array` *required*
>
> Required array of container tags used to select connections for deletion. Each tag is at most 100 characters and contains only letters, numbers, underscores, colons, or hyphens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Forget Matching Memories
>
> **Slug:** `SUPERMEMORY_FORGET_MATCHING_MEMORIES`
>
> Deprecated by Supermemory: legacy v3/v4 APIs shut down December 31, 2026. Use v5 DELETE /ns/\{namespace}/memories/semantic for semantic forgetting, or DELETE /ns/\{namespace}/memories for exact IDs. Soft-delete memories in one container matching a natural-language instruction or exact IDs. Set dry\_run=true to preview first; omission defaults to real forgetting. Semantic matches may change between preview and apply; use exact IDs for a reviewable selection.
>
> #### Input Parameters
>
> **ids** `array`
>
> Exact memory IDs to forget without semantic search. Unknown IDs and IDs outside the container are ignored. Provide either ids or query.
>
> **query** `string`
>
> Natural-language instruction or topic to forget. Provide either query or ids.
>
> **reason** `string`
>
> Optional reason stored as forgetReason on each forgotten memory.
>
> **dry\_run** `boolean`
>
> Preview matching memories without mutation when true. Defaults to false, which forgets for real.
>
> **threshold** `number`
>
> Minimum cosine similarity for semantic matches, from 0 to 1. Lower values match more broadly; default 0.5.
>
> **max\_forget** `integer`
>
> Maximum memories this call may forget, from 1 to 500; default 100.
>
> **container\_tag** `string` *required*
>
> Container tag or space to which the forget operation is scoped.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Forget Memory
>
> **Slug:** `SUPERMEMORY_FORGET_MEMORY`
>
> Deprecated by the provider; v3/v4 APIs shut down on December 31, 2026. Use v5 DELETE /ns/\{namespace}/memories for new integrations. Soft-delete a memory by ID or exact content within a required container tag. The memory is marked as forgotten, not permanently deleted.
>
> #### Input Parameters
>
> **id** `string`
>
> ID of the memory to forget. Provide this or an exact content match.
>
> **reason** `string`
>
> Optional reason for forgetting this memory.
>
> **content** `string`
>
> Exact memory content to match when the memory ID is unavailable.
>
> **containerTag** `string` *required*
>
> Required container tag scoping the operation; up to 100 letters, digits, underscores, colons, or hyphens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Forget Namespace Memories
>
> **Slug:** `SUPERMEMORY_FORGET_NAMESPACE_MEMORIES`
>
> Remove 1 to 500 exact memories from normal recall in a namespace by stable memory ID, preserving their audit history. Each ID is handled independently: missing or ineligible memories are reported without rolling back successful changes. Inspect count, errors, and matches; HTTP 200 does not mean every requested memory was forgotten.
>
> #### Input Parameters
>
> **ids** `array` *required*
>
> One to 500 non-empty stable memory identifiers to remove from normal recall.
>
> **namespace** `string` *required*
>
> Namespace containing the memories to forget, such as a user or project ID. At most 100 letters, numbers, underscores, colons, or hyphens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Forget Namespace Memories Semantically
>
> **Slug:** `SUPERMEMORY_FORGET_NAMESPACE_MEMORIES_SEMANTICALLY`
>
> Preview or forget memories in a namespace using a natural-language query. Explicitly set dryRun to true to preview or false to apply forgetting. For a reviewable, drift-free workflow, preview here and pass the returned memory IDs to the exact-ID forget action instead of rerunning the query. Inspect count, matches, and errors for the provider-reported outcome.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Natural-language description of the memories that should be forgotten.
>
> **dryRun** `boolean` *required*
>
> Required choice: true previews matching memories without changing their recall state; false applies forgetting to the matching set.
>
> **namespace** `string` *required*
>
> Namespace containing the memories to forget, such as a user or project ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Account Status
>
> **Slug:** `SUPERMEMORY_GET_ACCOUNT_STATUS`
>
> Return the connected Supermemory organization's plan, credit balance, high-level usage, and reset date.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Automatic Top-Ups
>
> **Slug:** `SUPERMEMORY_GET_AUTOMATIC_TOPUPS`
>
> Deprecated legacy v3 API, scheduled to shut down December 31, 2026. Get the connected organization's automatic credit top-up configuration and payment-method availability without changing billing settings or purchasing credits. Requires an unscoped organization API key; scoped API keys cannot read billing.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Billing Usage
>
> **Slug:** `SUPERMEMORY_GET_BILLING_USAGE`
>
> Deprecated legacy v3 API; provider shutdown is December 31, 2026. Retrieve the connected organization's per-feature billing usage, limits, units, and period bounds when available. Requires an organization API key; scoped API keys cannot read billing. Console usage estimates are not authoritative invoices.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Billing Usage Events
>
> **Slug:** `SUPERMEMORY_GET_BILLING_USAGE_EVENTS`
>
> Deprecated legacy v3 API, scheduled to shut down December 31, 2026. Get daily billing meter events for the connected organization, including per-feature consumption and Memory versus SuperRAG token totals. Optional ISO 8601 start and end override the billing period. Requires an organization API key; scoped API keys cannot read billing. Console usage is an estimate; invoice line items are authoritative.
>
> #### Input Parameters
>
> **end** `string`
>
> ISO 8601 end of the usage window; omit to use the billing period.
>
> **start** `string`
>
> ISO 8601 start of the usage window; omit to use the billing period.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Connection
>
> **Slug:** `SUPERMEMORY_GET_CONNECTION`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down December 31, 2026. Use the v5 GET /ns/\{namespace}/connectors/\{id} endpoint for new integrations. Retrieve a legacy connection by ID, including available provider metadata and the latest sync run status.
>
> #### Input Parameters
>
> **connectionId** `string` *required*
>
> ID of the connection to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Connector
>
> **Slug:** `SUPERMEMORY_GET_CONNECTOR`
>
> Read a connector in a namespace, including its setup, selection, and latest sync status. Optionally include the 10 most recent sync runs with failed items or a one-time hosted picker URL. Requesting picker requires admin write access because the link allows changing what syncs.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Connector identifier returned when the connector was created.
>
> **include** `array`
>
> Optional extras: syncs returns the 10 most recent sync runs with failed items; picker returns a one-time hosted picker URL and requires admin write access because it allows changing what syncs.
>
> **namespace** `string` *required*
>
> Namespace identifying the user, project, or other connector scope.
>
> **returnUrl** `string`
>
> URI where the hosted picker sends the user when finished.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Container Tag
>
> **Slug:** `SUPERMEMORY_GET_CONTAINER_TAG`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Use v5 GET /ns/\{namespace} for namespace settings instead. Get a container tag's display name, entity context, memory filesystem paths, profile buckets, and creation and update timestamps.
>
> #### Input Parameters
>
> **containerTag** `string` *required*
>
> Container tag identifier whose settings to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Container Tag Merge
>
> **Slug:** `SUPERMEMORY_GET_CONTAINER_TAG_MERGE`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Get the status and progress of a queued container tag merge by its merge job ID, including copied rows, renamed custom IDs, and the last error. This read does not start or retry a merge.
>
> #### Input Parameters
>
> **mergeId** `string` *required*
>
> Merge job ID returned when queuing a container tag merge.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Document
>
> **Slug:** `SUPERMEMORY_GET_DOCUMENT`
>
> Get one document's content, metadata, source details, and processing status by document ID.
>
> #### Input Parameters
>
> **document\_id** `string` *required*
>
> Supermemory document ID returned by Add Document or List Documents.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Document Chunks
>
> **Slug:** `SUPERMEMORY_GET_DOCUMENT_CHUNKS`
>
> Return the ordered extracted chunks for one processed document.
>
> #### Input Parameters
>
> **document\_id** `string` *required*
>
> Processed Supermemory document ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Document File URL
>
> **Slug:** `SUPERMEMORY_GET_DOCUMENT_FILE_URL`
>
> Deprecated by the provider: this legacy endpoint shuts down December 31, 2026. Get a fresh presigned download URL for a document's uploaded file. The URL is valid for 24 hours. Returns an error if the document does not exist or has no file.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> ID of the Supermemory document whose uploaded file URL to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Error Analytics
>
> **Slug:** `SUPERMEMORY_GET_ERROR_ANALYTICS`
>
> Deprecated legacy v3 endpoint scheduled to shut down December 31, 2026. Retrieve organization-wide error analytics, including request-type summaries, HTTP error breakdowns, hourly trends, and per-key metrics for a time window. Returns one page; increment page using the returned pagination metadata.
>
> #### Input Parameters
>
> **to** `string`
>
> ISO 8601 end date/time for the analytics period.
>
> **page** `integer`
>
> Page number, starting at 1.
>
> **limit** `integer`
>
> Items per page (1-100); defaults to 20.
>
> **period** `string ("24h" | "7d" | "30d" | "all")`
>
> Relative time window, as an alternative to from\_date; use date bounds for other windows.
>
> **from\_date** `string`
>
> ISO 8601 start date/time for the analytics period.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Namespace Settings
>
> **Slug:** `SUPERMEMORY_GET_NAMESPACE`
>
> Read a namespace's supporting context and lifecycle timestamps. Supporting context helps Supermemory understand content and form better memories inside this namespace.
>
> #### Input Parameters
>
> **namespace** `string` *required*
>
> Namespace identifier used to scope documents and memories, such as a user or project ID. Maximum 100 characters; letters, numbers, underscores, colons, and hyphens only.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Namespace Document
>
> **Slug:** `SUPERMEMORY_GET_NAMESPACE_DOCUMENT`
>
> Retrieve a document's canonical content, metadata, and processing state by document ID or caller-defined ID within a namespace. Optionally include source chunks, derived memories, or both. Processing status done does not necessarily mean memory generation is complete; inspect dreamingStatus separately.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Public document ID or caller-defined document ID.
>
> **include** `array`
>
> Child resources to include: chunks, memories, or both. Omit for document only.
>
> **namespace** `string` *required*
>
> Isolated namespace identifying a user, project, or other document scope.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Namespace Memory
>
> **Slug:** `SUPERMEMORY_GET_NAMESPACE_MEMORY`
>
> Retrieve one memory by ID within a namespace, including its text, metadata, version, and recall flags. Optionally include version history up to three steps away (nearest first), direct extends and derives links, and source documents. relatedLimit caps each related list separately.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Memory identifier.
>
> **include** `array`
>
> Extras to retrieve: related includes version history and connected memories; documents includes the source document and, with related, their documents.
>
> **namespace** `string` *required*
>
> Namespace identifying the user, project, or other memory scope.
>
> **relatedLimit** `integer`
>
> Maximum entries per parents, children, and siblings list (1-100; default 10).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Namespace Profile
>
> **Slug:** `SUPERMEMORY_GET_NAMESPACE_PROFILE`
>
> Read the continuously maintained profile of a namespace's subject without a search query. Returns stable facts, evolving context, and custom buckets; optionally restrict contributing memories with metadata filters or select buckets.
>
> #### Input Parameters
>
> **filter** `string`
>
> Type-safe metadata conditions limiting which memories contribute to the profile.
>
> **buckets** `array`
>
> Up to 50 custom bucket slugs to return. Omit to return every effective bucket.
>
> **namespace** `string` *required*
>
> Isolated namespace identifying the subject, user, or project to profile.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Namespace Profile Buckets
>
> **Slug:** `SUPERMEMORY_GET_NAMESPACE_PROFILE_BUCKETS`
>
> Inspect the profile taxonomy active in a Supermemory namespace. Returns a name-to-description map combining organization-wide profile buckets with namespace-owned additions.
>
> #### Input Parameters
>
> **namespace** `string` *required*
>
> Namespace whose effective profile bucket definitions to retrieve. Use a user, project, or other identifier of at most 100 characters, containing only letters, numbers, underscores, colons, and hyphens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Organization
>
> **Slug:** `SUPERMEMORY_GET_ORGANIZATION`
>
> Read the connected organization's shared background that guides memory formation across all namespaces, together with its active namespace count. This action takes no parameters and does not change organization settings.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Profile
>
> **Slug:** `SUPERMEMORY_GET_PROFILE`
>
> Retrieve the static, dynamic, or bucketed profile learned for one container tag, optionally with matching search results.
>
> #### Input Parameters
>
> **query** `string`
>
> Optional query that also returns matching profile search results.
>
> **buckets** `array`
>
> Specific profile bucket keys to return when buckets are included.
>
> **filters** `object`
>
> Root metadata filter. Choose AND or OR, never both; operands may be conditions or one nested AND/OR group containing conditions. Deeper groups are unsupported.
>
> **include** `array`
>
> Profile sections to return: static, dynamic, or buckets. Omit this field to return all available sections.
>
> **threshold** `number`
>
> Minimum score from 0 to 1 for optional search results.
>
> **container\_tag** `string` *required*
>
> Container tag whose learned profile should be returned.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Profile Buckets
>
> **Slug:** `SUPERMEMORY_GET_PROFILE_BUCKETS`
>
> Deprecated by the provider: this legacy v4 endpoint shuts down on December 31, 2026. Use v5 GET /ns/\{namespace}/profile/buckets instead. Return the effective profile bucket definitions for a container tag, merging organization-level buckets with container-tag-level additions.
>
> #### Input Parameters
>
> **containerTag** `string` *required*
>
> Tag to resolve effective bucket definitions for. Can be a user ID, project ID, or any identifier used to scope memories.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Provider Connection
>
> **Slug:** `SUPERMEMORY_GET_PROVIDER_CONNECTION`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Use v5 LIST\_CONNECTORS to find namespace connectors and GET\_CONNECTOR to retrieve one by ID. Retrieve a legacy connection by provider and container tags, including its latest synchronization status when available. This POST only reads connection details.
>
> #### Input Parameters
>
> **provider** `string ("notion" | "google-drive" | "onedrive" | "gmail" | "github" | "web-crawler" | "s3" | "granola")` *required*
>
> Provider whose connection should be retrieved.
>
> **containerTags** `array` *required*
>
> One or more container tags that identify the provider connection.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Settings
>
> **Slug:** `SUPERMEMORY_GET_SETTINGS`
>
> Deprecated legacy v3 API, scheduled to shut down December 31, 2026. Use the v5 organization and namespace settings APIs for new integrations. Retrieve the connected organization's ingestion filters, connector OAuth configuration, chunk size, and profile buckets. Connector client secrets are omitted from the response.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Usage Analytics
>
> **Slug:** `SUPERMEMORY_GET_USAGE_ANALYTICS`
>
> Deprecated legacy v3 API, scheduled to shut down December 31, 2026. Get organization-wide request usage analytics, including counts by request type, hourly performance, per-API-key metrics, and total memories. Filter by a relative period or ISO 8601 from\_ and to bounds. Returns one page; use pagination to request further pages. Recorded tokensUsed is not the billable ingestion-token meter.
>
> #### Input Parameters
>
> **to** `string`
>
> ISO 8601 end date/time for the analytics window.
>
> **page** `integer`
>
> Page number, starting at 1.
>
> **from\_** `string`
>
> ISO 8601 start date/time; alternative to period.
>
> **limit** `integer`
>
> Items per page, from 1 to 100; defaults to 20.
>
> **period** `string ("24h" | "7d" | "30d" | "all")`
>
> Relative time window, as an alternative to from\_.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Ingest Conversation
>
> **Slug:** `SUPERMEMORY_INGEST_CONVERSATION`
>
> Deprecated by the provider: the v3/v4 API shuts down December 31, 2026. For new integrations, ingest a conversation transcript through v5 POST /ns/\{namespace}/document instead. Ingest or update a conversation by its conversationId using structured messages, optional container tags, and metadata. Returns the backing document ID and processing status, not a guarantee that asynchronous processing has finished.
>
> #### Input Parameters
>
> **messages** `array` *required*
>
> One or more structured conversation messages to ingest.
>
> **metadata** `object`
>
> Flat conversation metadata with string, numeric, or boolean values.
>
> **containerTags** `array`
>
> Container tags grouping the conversation; each is at most 100 letters, digits, underscores, colons, or hyphens.
>
> **conversationId** `string` *required*
>
> Caller-supplied conversation identifier used to ingest or update a conversation.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List All Connectors
>
> **Slug:** `SUPERMEMORY_LIST_ALL_CONNECTORS`
>
> List one page of connectors across every namespace the API key can read, optionally filtered by provider. Use for admin views spanning users or projects. Pending connectors are not listed. Increment page up to pagination.totalPages to retrieve subsequent pages.
>
> #### Input Parameters
>
> **page** `integer`
>
> One-based page number.
>
> **limit** `integer`
>
> Maximum connectors to return per page (1-100).
>
> **provider** `string ("notion" | "google-drive" | "onedrive" | "gmail" | "github" | "web-crawler" | "s3" | "granola")`
>
> Only return connectors for this provider.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Connection Documents
>
> **Slug:** `SUPERMEMORY_LIST_CONNECTION_DOCUMENTS`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. For v5 document listing, use LIST\_NAMESPACE\_RESOURCES with type documents; v5 connectors are namespace-scoped. List documents indexed for a connected provider, optionally filtered by container tags. Returns document IDs, processing statuses, titles, summaries, types, and timestamps.
>
> #### Input Parameters
>
> **provider** `string ("notion" | "google-drive" | "onedrive" | "gmail" | "github" | "web-crawler" | "s3" | "granola")` *required*
>
> Connected provider whose indexed documents to list.
>
> **containerTags** `array`
>
> Optional array of container tags to filter documents by. Each tag is at most 100 characters and contains only letters, numbers, underscores, colons, or hyphens. Omit to list without a container-tag filter.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Connection Resources
>
> **Slug:** `SUPERMEMORY_LIST_CONNECTION_RESOURCES`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. List one page of accessible resources for a connection; only GitHub is currently documented as supported. Use page and per\_page to request additional pages, and parent\_id to scope resources to a parent.
>
> #### Input Parameters
>
> **page** `string`
>
> Page of accessible resources to fetch; defaults to 1.
>
> **per\_page** `string`
>
> Number of resources per page; defaults to 30.
>
> **parent\_id** `string`
>
> Optional parent resource ID to fetch resources beneath.
>
> **connection\_id** `string` *required*
>
> ID of the connection whose accessible resources to fetch.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Connections
>
> **Slug:** `SUPERMEMORY_LIST_CONNECTIONS`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Use v5 LIST\_CONNECTORS for namespace connectors or LIST\_ALL\_CONNECTORS across namespaces. List all legacy connections, optionally filtered by container tags, including the latest synchronization status when available.
>
> #### Input Parameters
>
> **containerTags** `array`
>
> Optional container tags to filter connections by.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Connectors
>
> **Slug:** `SUPERMEMORY_LIST_CONNECTORS`
>
> List one page of connectors that sync into a namespace, optionally filtered by provider. Pending authorization connectors are not listed. Use page and limit with the returned pagination metadata to retrieve subsequent pages.
>
> #### Input Parameters
>
> **page** `integer`
>
> One-based page number to retrieve.
>
> **limit** `integer`
>
> Maximum connectors per page, from 1 to 100.
>
> **provider** `string ("notion" | "google-drive" | "onedrive" | "gmail" | "github" | "web-crawler" | "s3" | "granola")`
>
> Only return connectors for this external provider.
>
> **namespace** `string` *required*
>
> Namespace identifier that scopes the connectors, up to 100 characters.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Container Tags
>
> **Slug:** `SUPERMEMORY_LIST_CONTAINER_TAGS`
>
> Deprecated by the provider: the legacy v3 API shuts down December 31, 2026. Use the v5 namespace listing API for new integrations. List all container tags, optionally restricted by a comma-separated filter, including summaries, Nova flags, document and memory counts, and active merge details.
>
> #### Input Parameters
>
> **containerTags** `string`
>
> Comma-separated container tags to limit the list to; omit to list all tags.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Documents
>
> **Slug:** `SUPERMEMORY_LIST_DOCUMENTS`
>
> List documents, optionally filtered by containers, metadata, or filepath, one page at a time.
>
> #### Input Parameters
>
> **sort** `string ("createdAt" | "updatedAt")`
>
> Timestamp field used for sorting.
>
> **limit** `integer`
>
> Maximum documents to return in this page (1-1100).
>
> **order** `string ("asc" | "desc")`
>
> Sort direction.
>
> **filters** `object`
>
> Root metadata filter. Choose AND or OR, never both; operands may be conditions or one nested AND/OR group containing conditions. Deeper groups are unsupported.
>
> **filepath** `string`
>
> Exact filepath, or a directory prefix ending in /, used to filter documents.
>
> **next\_cursor** `string`
>
> Opaque cursor returned by the previous call; omit for the first page.
>
> **container\_tags** `array`
>
> Only return documents in any of these container tags.
>
> **include\_content** `boolean`
>
> Include full document content. Leave false unless content is needed because responses can become large.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Inferred Memories
>
> **Slug:** `SUPERMEMORY_LIST_INFERRED_MEMORIES`
>
> List a namespace's inferred memories awaiting review. This review route is still served under v3; pass the namespace as containerTag. Returns up to 50 memories ordered by parentCount descending, then createdAt descending, excluding forgotten, expired, or reviewed memories. No pagination is documented; total can exceed the returned count. Unknown or empty namespaces return an empty list and zero total. No v5 replacement is documented.
>
> #### Input Parameters
>
> **containerTag** `string` *required*
>
> Namespace whose inferred-memory review queue to read.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Invoices
>
> **Slug:** `SUPERMEMORY_LIST_INVOICES`
>
> Deprecated legacy v3 API, scheduled to shut down December 31, 2026. List the connected Supermemory organization's billing invoices without changing billing settings or purchasing credits. Requires an unscoped organization API key; scoped API keys cannot read billing.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Memories
>
> **Slug:** `SUPERMEMORY_LIST_MEMORIES`
>
> List extracted memory entries for one or more container tags, one page at a time.
>
> #### Input Parameters
>
> **sort** `string ("createdAt" | "updatedAt")`
>
> Timestamp field used for sorting.
>
> **limit** `integer`
>
> Maximum memories to return in this page (1-1100).
>
> **order** `string ("asc" | "desc")`
>
> Sort direction.
>
> **filters** `object`
>
> Root metadata filter. Choose AND or OR, never both; operands may be conditions or one nested AND/OR group containing conditions. Deeper groups are unsupported.
>
> **next\_cursor** `string`
>
> Opaque cursor returned by the previous call; omit for the first page.
>
> **container\_tags** `array` *required*
>
> One or more container tags whose memory entries should be returned.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Namespace Resources
>
> **Slug:** `SUPERMEMORY_LIST_NAMESPACE_RESOURCES`
>
> Browse one page of documents, extracted chunks, or learned memories in a namespace. The other collection arrays are empty. Use pagination.totalPages and page to retrieve further pages. Position sorting is for chunks only; include.content and include.memoryCount apply to documents, and include.forgotten applies to memories.
>
> #### Input Parameters
>
> **page** `integer`
>
> One-based page number.
>
> **sort** `string ("createdAt" | "updatedAt" | "position")`
>
> Sort field; position is available only for chunks.
>
> **type** `string ("documents" | "chunks" | "memories")` *required*
>
> Resource collection to list.
>
> **limit** `integer`
>
> Maximum resources per page, from 1 to 100.
>
> **order** `string ("asc" | "desc")`
>
> Ascending or descending sort direction.
>
> **filter** `string`
>
> Metadata conditions before pagination; at most five levels.
>
> **include** `object`
>
> Optional document content/counts or forgotten memories.
>
> **namespace** `string` *required*
>
> User or project namespace, up to 100 letters, digits, underscores, colons, or hyphens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Namespaces
>
> **Slug:** `SUPERMEMORY_LIST_NAMESPACES`
>
> List namespaces available to the caller, newest first, including their purpose, document and memory counts, and lifecycle timestamps. Optionally filter names with q. Returns one page; use page and the returned pagination to fetch more.
>
> #### Input Parameters
>
> **q** `string`
>
> Case-insensitive substring to match against namespace names (up to 100 characters).
>
> **page** `integer`
>
> One-based page number.
>
> **limit** `integer`
>
> Maximum namespaces to return per page (1-100).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Processing Documents
>
> **Slug:** `SUPERMEMORY_LIST_PROCESSING_DOCUMENTS`
>
> Deprecated by the provider: the legacy v3 API shuts down December 31, 2026. Use the v5 namespace document listing API for new integrations. List the live processing queue, all unfinished documents, or unfinished and failed documents. For view=all, fetch subsequent pages using page and limit and inspect the returned pagination information.
>
> #### Input Parameters
>
> **page** `string`
>
> Page number for view=all, as a number or digit-only string.
>
> **view** `string ("active" | "pending" | "all")`
>
> active returns in-flight documents updated in the last four hours; pending returns all unfinished, non-failed documents without a time cutoff; all also includes failed documents and supports pagination.
>
> **limit** `string`
>
> Items per page for view=all, as a number or digit-only string.
>
> **containerTags** `string`
>
> Comma-separated container tags to filter by.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Request Logs
>
> **Slug:** `SUPERMEMORY_LIST_REQUEST_LOGS`
>
> Deprecated legacy v3 endpoint scheduled to shut down December 31, 2026. List one page of organization-wide request logs filtered by time. Use pagination metadata and increment page to continue. Outputs are compacted and may be truncated. The ordinary tracker skips HTTP 402, 404, and 500 responses, so logs are not a complete audit trail. Historical retention is not guaranteed. Request type, status code, and API key filters are not supported.
>
> #### Input Parameters
>
> **to** `string`
>
> ISO 8601 end date/time for the log window.
>
> **page** `integer`
>
> Page number, starting at 1.
>
> **limit** `integer`
>
> Logs per page (1-100); defaults to 20.
>
> **period** `string ("24h" | "7d" | "30d" | "all")`
>
> Relative time window instead of from\_date; use date bounds for other windows.
>
> **from\_date** `string`
>
> ISO 8601 start date/time for the log window.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Merge Container Tags
>
> **Slug:** `SUPERMEMORY_MERGE_CONTAINER_TAGS`
>
> Deprecated by the provider: the legacy v3 API shuts down December 31, 2026. Queue a merge of exactly two container tags into a target tag. All source documents are updated to reference the target, and source tags are deleted after a successful merge. Requires an organization admin or owner. The response confirms queuing, not completion; use GET\_CONTAINER\_TAG\_MERGE with the returned mergeId to check progress.
>
> #### Input Parameters
>
> **containerTags** `array` *required*
>
> Exactly two container tags whose documents will be merged into the target.
>
> **targetContainerTag** `string` *required*
>
> Target container tag. Must be one of containerTags or a new tag that does not already exist in the organization.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Replace Namespace File
>
> **Slug:** `SUPERMEMORY_REPLACE_NAMESPACE_FILE`
>
> Replace an existing document with a new file within an isolated namespace, keeping its stable document ID. Content and caller metadata are overwritten and the document is reprocessed asynchronously. The returned status reports processing state, not guaranteed completion. Requires namespace write access.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Public ID of the existing document to replace.
>
> **date** `string`
>
> When the source content is from, in ISO 8601 format.
>
> **file** `object` *required*
>
> New file contents to replace the document.
>
> **group** `string`
>
> JSON-encoded metadata keeping related context isolated during processing and recall.
>
> **dreaming** `string ("dynamic" | "instant")`
>
> Processing mode: dynamic (provider default) groups related documents; instant processes independently right away and bills one extra operation per document.
>
> **metadata** `string`
>
> JSON-encoded metadata to attach to the document and its derived memories; replaces caller metadata.
>
> **file\_type** `string ("text" | "pdf" | "image" | "video" | "audio")`
>
> Explicit source type when automatic inference is insufficient.
>
> **mime\_type** `string`
>
> Explicit MIME type when upload metadata is insufficient.
>
> **namespace** `string` *required*
>
> Isolated namespace containing the document, such as a user or project ID.
>
> **task\_type** `string ("memory" | "superrag")`
>
> Processing pipeline: memory builds durable learned context; superrag optimizes retrieval without generating memories.
>
> **supporting\_context** `string`
>
> Context guiding memory extraction within this namespace, up to 1500 characters.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Reset Organization Data
>
> **Slug:** `SUPERMEMORY_RESET_ORGANIZATION_DATA`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Destructively reset the ENTIRE connected organization's content: delete documents, memories, spaces except the default project, connections, and organization settings, and clear the default space context. Preserves the organization itself, members, and billing. This is not scoped to an individual document, container tag, or namespace. Only call with explicit authorization to delete the entire organization's data.
>
> #### Input Parameters
>
> **confirmation** `string` *required*
>
> Required nonempty confirmation string for the destructive entire-organization reset. The provider does not document the required confirmation value; obtain it from Supermemory before calling.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Review Inferred Memory
>
> **Slug:** `SUPERMEMORY_REVIEW_INFERRED_MEMORY`
>
> Provider deprecation notice: legacy v3/v4 APIs are scheduled to shut down December 31, 2026. These review routes still serve namespaces under v3; no v5 replacement is documented. Approve, decline, or undo a review of one inferred memory in a namespace. Approve confirms the fact; decline forgets it and removes it from search; undo restores the unreviewed inferred state, including un-forgetting a declined memory. Requires a key with write access to the namespace. A non-reviewable memory or an undo without a prior review returns 409.
>
> #### Input Parameters
>
> **action** `string ("approve" | "decline" | "undo")` *required*
>
> approve confirms the inferred fact; decline forgets it and removes it from search; undo clears a prior review and un-forgets the memory, returning it to the review queue. There is no reject or skip action.
>
> **memoryId** `string` *required*
>
> Memory entry ID returned by the inferred-memory review queue.
>
> **containerTag** `string` *required*
>
> Namespace the inferred memory belongs to; passed as the legacy containerTag path parameter.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Revoke Scoped Key
>
> **Slug:** `SUPERMEMORY_REVOKE_SCOPED_KEY`
>
> Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026. Revoke a scoped API key using the ID returned at creation. Subsequent requests using the revoked key receive 401. Memories and namespaces are not deleted. Authenticate with an organization API key, not a scoped key.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> ID returned when the scoped API key was created, not the secret key value.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Memory
>
> **Slug:** `SUPERMEMORY_SEARCH_CONTEXT`
>
> Semantically search Supermemory memories, document chunks, or both, with optional container and metadata filters.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum results to return (1-100); this endpoint has no continuation token.
>
> **query** `string` *required*
>
> Natural-language search query.
>
> **rerank** `boolean`
>
> Rerank matches for improved relevance.
>
> **filters** `object`
>
> Root metadata filter. Choose AND or OR, never both; operands may be conditions or one nested AND/OR group containing conditions. Deeper groups are unsupported.
>
> **include** `object`
>
> Optional associated content to include: documents, summaries, related memories, and forgotten memories.
>
> **aggregate** `boolean`
>
> Synthesize information across matches; intended to be used with reranking.
>
> **threshold** `number`
>
> Minimum relevance threshold from 0 to 1; higher values return fewer, stricter matches.
>
> **search\_mode** `string ("memories" | "hybrid" | "documents")`
>
> Search memories, document chunks, or both.
>
> **rewrite\_query** `boolean`
>
> Rewrite the query for retrieval at additional latency.
>
> **container\_tags** `array`
>
> Restrict search to memories under these container tags.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Documents
>
> **Slug:** `SUPERMEMORY_SEARCH_DOCUMENTS`
>
> Deprecated by the provider: legacy v3/v4 APIs shut down December 31, 2026. Use v5 namespace search (POST /ns/\{namespace}/search) for new integrations. Search documents and their content chunks with optional container, document, metadata, and filepath filters. Returns one bounded result set with relevance scores and optional full content or summaries.
>
> #### Input Parameters
>
> **q** `string` *required*
>
> Nonempty search query string.
>
> **docId** `string`
>
> Document ID to restrict chunk search to one document.
>
> **limit** `integer`
>
> Maximum document results (1-100); defaults to 10.
>
> **rerank** `boolean`
>
> Rerank results for the query; defaults to false.
>
> **filters** `string`
>
> Root AND/OR filter object, or its JSON string representation.
>
> **filepath** `string`
>
> Filter by exact filepath, or by prefix when ending with /.
>
> **containerTag** `string`
>
> Single container tag to search; use this or containerTags.
>
> **rewriteQuery** `boolean`
>
> Rewrite the query for retrieval; defaults to false and adds about 400ms latency when enabled.
>
> **containerTags** `array`
>
> Container tags used to scope the document search.
>
> **chunkThreshold** `number`
>
> Chunk selection sensitivity, from 0 (most chunks, default) to 1 (most selective).
>
> **includeSummary** `boolean`
>
> Include document summaries; defaults to false.
>
> **includeFullDocs** `boolean`
>
> Include full document content; defaults to false.
>
> **categoriesFilter** `array`
>
> Deprecated optional category filters.
>
> **documentThreshold** `number`
>
> Deprecated and ignored by v3 search; use chunkThreshold instead. Provider default is 0.
>
> **onlyMatchingChunks** `boolean`
>
> Return only matching chunks (default true); false also includes surrounding context.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Namespace
>
> **Slug:** `SUPERMEMORY_SEARCH_NAMESPACE`
>
> Recall relevant learned context and source passages from an isolated namespace. Hybrid search combines memories and document chunks by default. Supports typed metadata filters (up to five levels), query rewriting, reranking, and optional source documents and related memories.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum results, from 1 to 100.
>
> **query** `string` *required*
>
> Natural-language question, topic, or phrase to retrieve context for.
>
> **filter** `string`
>
> Type-safe metadata filter; at most five expression levels.
>
> **rerank** `string ("none" | "order" | "aggregate")`
>
> No reranking, improved ordering, or ordering plus overlapping-context aggregation.
>
> **include** `object`
>
> Supporting context and forgotten-memory options; all default false.
>
> **namespace** `string` *required*
>
> Isolated user or project namespace; up to 100 letters, digits, underscores, colons, or hyphens.
>
> **threshold** `number`
>
> Minimum relevance from 0 to 1; higher favors precision.
>
> **searchMode** `string ("hybrid" | "memories" | "chunks")`
>
> Search learned memories, source chunks, or both (hybrid).
>
> **rewriteQuery** `boolean`
>
> Expand and clarify the query; adds about 400ms latency.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Send Feedback
>
> **Slug:** `SUPERMEMORY_SEND_FEEDBACK`
>
> Send a bug report, feature request, documentation problem, or other feedback to the Supermemory team. This contacts real engineers and consumes the organization's quota of three submissions per UTC day, subject to a shared authenticated pool of 200 per day. Do not automatically retry uncertain deliveries, including HTTP 502: delivery may already have occurred.
>
> #### Input Parameters
>
> **type** `string ("bug" | "feature_request" | "docs" | "other")` *required*
>
> Kind of feedback to send to the Supermemory team.
>
> **title** `string` *required*
>
> One-line summary of the feedback.
>
> **actual** `string`
>
> What actually happened.
>
> **client** `string`
>
> Agent, tool, or SDK sending the feedback.
>
> **endpoint** `string`
>
> API operation the feedback is about.
>
> **expected** `string`
>
> What you expected to happen.
>
> **requestId** `string`
>
> Request ID of a failing call, if available.
>
> **description** `string` *required*
>
> What happened, with enough detail for an engineer to act on it.
>
> **contactEmail** `string`
>
> Email address where the Supermemory team can reach you about this feedback.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Suggest Profile Buckets
>
> **Slug:** `SUPERMEMORY_SUGGEST_PROFILE_BUCKETS`
>
> Deprecated by the provider: the legacy v3 API shuts down December 31, 2026. Suggest profile bucket definitions using the organization's saved context prompt. Returns 3 to 6 suggestions tailored to that context without saving bucket definitions. Fails when no organization context is available.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Sync Connection
>
> **Slug:** `SUPERMEMORY_SYNC_CONNECTION`
>
> Deprecated provider v3 API; shuts down December 31, 2026. For v5, use SYNC\_CONNECTOR with a namespace and connector ID instead. Initiate a manual sync of connections for a provider, optionally filtered by container tags. The acknowledgement means importing was accepted, not that sync has finished.
>
> #### Input Parameters
>
> **provider** `string ("notion" | "google-drive" | "onedrive" | "gmail" | "github" | "web-crawler" | "s3" | "granola")` *required*
>
> Provider whose connections should be manually synced.
>
> **container\_tags** `array`
>
> Optional array of container tags to filter connections by. Each tag allows letters, numbers, underscores, colons, and hyphens, up to 100 characters. Omit to sync without a container-tag filter.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Sync Connector
>
> **Slug:** `SUPERMEMORY_SYNC_CONNECTOR`
>
> Start a sync now for a connector in a namespace. Returns the connector ID and queued status, not a completed sync result. Returns a conflict if a sync for this connector is already running. Use Get Connector to inspect sync progress and results.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Connector identifier returned when the connector was created.
>
> **namespace** `string` *required*
>
> Namespace identifying the user, project, or other connector scope.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Connector
>
> **Slug:** `SUPERMEMORY_UPDATE_CONNECTOR`
>
> Change what a connector syncs in a namespace or its maximum document count. A supplied selection replaces the old selection and starts a sync. Only send selection for providers that support choosing resources. Returns the updated connector and its latest sync status.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Connector identifier returned when the connector was created.
>
> **namespace** `string` *required*
>
> Namespace identifying the user, project, or other connector scope.
>
> **selection** `object`
>
> Resource IDs grouped by kind. Replaces the entire current selection and starts a sync. GitHub uses repos, Gmail labels, Google Drive files and folders, and OneDrive folders. Omit to retain the current selection.
>
> **document\_limit** `integer`
>
> Maximum documents this connector imports, from 1 to 10000; omit to retain.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Container Tag
>
> **Slug:** `SUPERMEMORY_UPDATE_CONTAINER_TAG`
>
> Deprecated by the provider: the legacy v3 API shuts down December 31, 2026. Use the v5 namespace settings API (PATCH /ns/\{namespace}) for new integrations. Update an existing container tag's display name, document processing context, memory filesystem paths, or tag-level profile buckets. Omitted fields remain unchanged; explicit nulls are sent for fields that support them.
>
> #### Input Parameters
>
> **name** `string`
>
> Display name, from 1 to 100 characters; does not change the tag identifier.
>
> **containerTag** `string` *required*
>
> Identifier of the existing container tag whose settings should change.
>
> **entityContext** `string`
>
> Context prompt for processing documents, up to 1500 characters; null clears it.
>
> **profileBuckets** `array`
>
> Up to 50 tag-level profile buckets. Replaces this tag's own list, adding on top of organization buckets without overriding or removing them.
>
> **memoryFilesystemPaths** `array`
>
> Filesystem path allowlist for memory generation on mount-ingested documents. Nonmatching documents use superrag without memory extraction; accepts null.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Document
>
> **Slug:** `SUPERMEMORY_UPDATE_DOCUMENT`
>
> Update the content, metadata, container, or processing configuration of one existing document. When metadata is supplied, it completely replaces the document's metadata, so omitted metadata keys are removed.
>
> #### Input Parameters
>
> **content** `string`
>
> Replacement text or public URL to process.
>
> **metadata** `object`
>
> Complete replacement metadata object; omitted keys are removed.
>
> **custom\_id** `string`
>
> Replacement caller-defined document ID.
>
> **task\_type** `string ("memory" | "superrag")`
>
> Replacement processing task type.
>
> **document\_id** `string` *required*
>
> Supermemory document ID returned by Add Document or List Documents.
>
> **container\_tag** `string`
>
> Replacement container tag, up to 100 characters. Use only letters, numbers, underscores, colons, and hyphens.
>
> **filter\_by\_metadata** `object`
>
> Replacement flat metadata filter for contextual memories.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Memory
>
> **Slug:** `SUPERMEMORY_UPDATE_MEMORY`
>
> Deprecated by the provider; v3/v4 APIs shut down on December 31, 2026. Use v5 namespace document updates for document-backed memory changes in new integrations. Update a memory by ID or exact content within a container, creating a new version. The original memory is preserved with isLatest=false. Omitted metadata and expiry inherit from the previous version; explicit null forgetAfter clears the expiry.
>
> #### Input Parameters
>
> **id** `string`
>
> ID of the memory to update. Supply this or an exact content match.
>
> **content** `string`
>
> Exact content of the memory to update when its ID is unavailable.
>
> **metadata** `object`
>
> Flat metadata with string, number, boolean, or string-array values. Omit to inherit the previous version's metadata.
>
> **newContent** `string` *required*
>
> Nonempty replacement text for the new memory version.
>
> **forgetAfter** `string`
>
> ISO 8601 expiry datetime. Omit to inherit the previous expiry; pass null to clear it and its reason.
>
> **containerTag** `string` *required*
>
> Container tag scoping the operation; up to 100 letters, digits, underscores, colons, or hyphens.
>
> **forgetReason** `string`
>
> Reason for scheduled forgetting, or null. Cleared automatically when forgetAfter is null.
>
> **temporalContext** `object`
>
> Structured temporal context merged into metadata. Omit to preserve existing temporal context.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Namespace
>
> **Slug:** `SUPERMEMORY_UPDATE_NAMESPACE`
>
> Update the background context used during ingestion and memory formation in an existing namespace. Omit supportingContext to leave it unchanged, or explicitly set it to null to clear it. Requires write access.
>
> #### Input Parameters
>
> **namespace** `string` *required*
>
> Namespace identifier used to scope documents and memories, up to 100 characters.
>
> **supportingContext** `string`
>
> Background guiding document interpretation and memory formation, up to 1500 characters. Set null to clear it; omit to leave it unchanged.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Namespace Document
>
> **Slug:** `SUPERMEMORY_UPDATE_NAMESPACE_DOCUMENT`
>
> Partially update an existing document in an isolated namespace without changing its stable ID. Supplied content replaces canonical content and is reprocessed; omitted fields remain unchanged. Returns the document ID and processing state, not a guarantee of completed processing.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Public document ID to update without changing its stable identity.
>
> **date** `string`
>
> Source content date in ISO 8601 format; omit to leave unchanged.
>
> **group** `object`
>
> Metadata values isolating related context within the namespace. Values may be strings, numbers, booleans, or string arrays.
>
> **content** `string`
>
> Replacement plaintext or URL to supported rich content. Supplied content is reprocessed; omitted content remains unchanged.
>
> **dreaming** `string ("dynamic" | "instant")`
>
> Processing mode: dynamic (provider default) groups related documents; instant processes each independently and bills one extra operation per document.
>
> **metadata** `object`
>
> Metadata attached to the document and derived data. Values may be strings, numbers, booleans, or string arrays; omit to leave unchanged.
>
> **namespace** `string` *required*
>
> Isolated namespace containing the document, such as a user or project ID.
>
> **task\_type** `string ("memory" | "superrag")`
>
> Processing pipeline: memory builds durable learned context; superrag optimizes retrieval without generating memories. Omit to leave unchanged.
>
> **supporting\_context** `string`
>
> Context guiding memory extraction within this namespace, up to 1500 characters. Omit to leave unchanged.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Namespace File
>
> **Slug:** `SUPERMEMORY_UPDATE_NAMESPACE_FILE`
>
> Partially update a file-backed document in an isolated namespace. Supply a file to replace canonical content, or update metadata and processing context without a file. Omitted metadata and processing context remain unchanged. Returns the document ID and current processing state, not a guarantee of completed processing.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Public document ID to update.
>
> **date** `string`
>
> Source content date in ISO 8601 format.
>
> **file** `object`
>
> Optional replacement file. Supplying it replaces the canonical content.
>
> **group** `string`
>
> JSON-encoded metadata keeping related context isolated during processing and recall.
>
> **dreaming** `string ("dynamic" | "instant")`
>
> Processing mode: dynamic groups related documents; instant processes independently and bills one extra operation. Omit to retain provider behavior.
>
> **metadata** `string`
>
> JSON-encoded metadata to attach to the document and derived memories; omitted metadata remains unchanged.
>
> **file\_type** `string ("text" | "pdf" | "image" | "video" | "audio")`
>
> Explicit source type when automatic inference is insufficient.
>
> **mime\_type** `string`
>
> Explicit MIME type when upload metadata is insufficient, such as application/pdf.
>
> **namespace** `string` *required*
>
> Isolated namespace containing the document, such as a user or project ID.
>
> **task\_type** `string ("memory" | "superrag")`
>
> Processing pipeline: memory builds learned context; superrag optimizes retrieval without generating memories.
>
> **supporting\_context** `string`
>
> Context guiding memory extraction within this namespace; omitted context remains unchanged.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Organization
>
> **Slug:** `SUPERMEMORY_UPDATE_ORGANIZATION`
>
> Update organization-wide background that guides content interpretation and memory formation across every namespace. Provide organizationalContext as a nonempty string to set it, or null to remove the existing context. Requires admin access.
>
> #### Input Parameters
>
> **organizationalContext** `string` *required*
>
> Shared background guiding memory formation across every namespace. Provide a nonempty string to set it, or null to clear it.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Settings
>
> **Slug:** `SUPERMEMORY_UPDATE_SETTINGS`
>
> Deprecated by the provider: the legacy v3 API shuts down December 31, 2026. Use v5 organization and namespace settings APIs for new integrations. Update the connected organization's settings, including filtering, custom connector OAuth credentials, chunk size, and profile buckets. Omitted fields are unchanged; explicit nulls are sent to the provider. This changes live organization configuration. Connector client secrets are accepted as input but omitted from the response.
>
> #### Input Parameters
>
> **chunkSize** `integer`
>
> Organization chunk size, a signed 32-bit integer, or null to clear it.
>
> **excludeItems** `string`
>
> Provider-defined JSON exclusion configuration; null clears it.
>
> **filterPrompt** `string`
>
> Organization filtering prompt; null clears it. Enable shouldLLMFilter to set a nonempty prompt.
>
> **includeItems** `string`
>
> Provider-defined JSON inclusion configuration; null clears it.
>
> **githubClientId** `string`
>
> Custom GitHub OAuth client ID; null clears it.
>
> **notionClientId** `string`
>
> Custom Notion OAuth client ID; null clears it.
>
> **profileBuckets** `array`
>
> Up to 50 profile bucket definitions; an empty list removes all buckets.
>
> **shouldLLMFilter** `boolean`
>
> Whether LLM-based filtering is enabled. Required for nonempty filterPrompt, includeItems, or excludeItems settings.
>
> **onedriveClientId** `string`
>
> Custom OneDrive OAuth client ID; null clears it.
>
> **githubClientSecret** `string`
>
> Custom GitHub OAuth client secret; null clears it.
>
> **notionClientSecret** `string`
>
> Custom Notion OAuth client secret; null clears it.
>
> **googleDriveClientId** `string`
>
> Custom Google Drive OAuth client ID; null clears it.
>
> **onedriveClientSecret** `string`
>
> Custom OneDrive OAuth client secret; null clears it.
>
> **githubCustomKeyEnabled** `boolean`
>
> Whether custom GitHub OAuth credentials are enabled.
>
> **notionCustomKeyEnabled** `boolean`
>
> Whether custom Notion OAuth credentials are enabled.
>
> **googleDriveClientSecret** `string`
>
> Custom Google Drive OAuth client secret; null clears it.
>
> **onedriveCustomKeyEnabled** `boolean`
>
> Whether custom OneDrive OAuth credentials are enabled.
>
> **googleDriveCustomKeyEnabled** `boolean`
>
> Whether custom Google Drive OAuth credentials are enabled.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload Document File
>
> **Slug:** `SUPERMEMORY_UPLOAD_DOCUMENT_FILE`
>
> Deprecated by the provider: this legacy endpoint shuts down December 31, 2026. Use the v5 namespace file upload endpoint POST /ns/\{namespace}/document/file for new integrations. Upload a file as a document for processing, with optional container tags, metadata, and extraction settings. The returned status reports processing state and does not guarantee processing has finished.
>
> #### Input Parameters
>
> **file** `object` *required*
>
> File to upload and process.
>
> **dreaming** `string ("instant" | "dynamic")`
>
> Processing mode: dynamic (provider default) groups related documents; instant processes this document independently and bills one extra operation.
>
> **filepath** `string`
>
> Optional filesystem mapping path, such as /documents/reports/file.pdf.
>
> **metadata** `string`
>
> Document metadata as a JSON object string; values may be strings, numbers, or booleans.
>
> **custom\_id** `string`
>
> Caller-defined document ID, at most 100 characters using letters, numbers, hyphens, underscores, and colons only.
>
> **file\_type** `string ("text" | "pdf" | "tweet" | "google_doc" | "google_slide" | "google_sheet" | "image" | "video" | "notion_doc" | "webpage" | "onedrive")`
>
> Optional override forcing a specific file processing type.
>
> **mime\_type** `string`
>
> Exact MIME type, required when file\_type is image or video (for example image/png or video/mp4).
>
> **task\_type** `string ("memory" | "superrag")`
>
> Processing task: memory (provider default) for the full context layer, or superrag for managed retrieval.
>
> **container\_tag** `string`
>
> Single container tag used to group the uploaded document.
>
> **container\_tags** `string`
>
> Deprecated: use container\_tag. A single tag or a JSON array string of tags.
>
> **entity\_context** `string`
>
> Context about the container entity to guide memory extraction, at most 1500 characters.
>
> **filter\_by\_metadata** `string`
>
> Metadata filter as a JSON object string, scoping existing memories used as ingestion context. Keys combine with AND; array values match ANY value.
>
> **use\_advanced\_processing** `string`
>
> Deprecated and ignored by the provider; advanced PDF processing is now automatic. Accepted as a string for backward compatibility.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload Namespace File
>
> **Slug:** `SUPERMEMORY_UPLOAD_NAMESPACE_FILE`
>
> Upload a file into an isolated Supermemory namespace to form searchable knowledge and learned memory. Ingestion returns once safely queued; extraction and memory formation continue asynchronously. The returned status is the document's current processing state, not a guarantee that processing has completed. Use task\_type=superrag for retrieval without generating memories.
>
> #### Input Parameters
>
> **date** `string`
>
> When the source content is from, in ISO 8601 format.
>
> **file** `object` *required*
>
> File contents to upload and process.
>
> **group** `string`
>
> JSON-encoded metadata keeping related context isolated during processing and recall.
>
> **dreaming** `string ("dynamic" | "instant")`
>
> Processing mode: dynamic (provider default) groups related documents; instant processes each document independently right away and bills one extra operation per document.
>
> **metadata** `string`
>
> JSON-encoded metadata to attach to the document and its derived memories.
>
> **file\_type** `string ("text" | "pdf" | "image" | "video" | "audio")`
>
> Explicit source type used when automatic inference is insufficient.
>
> **mime\_type** `string`
>
> Explicit MIME type used when upload metadata is insufficient, such as application/pdf.
>
> **namespace** `string` *required*
>
> Isolated namespace identifying the user or project whose documents to ingest.
>
> **task\_type** `string ("memory" | "superrag")`
>
> Processing pipeline: memory builds durable learned context; superrag optimizes retrieval without generating memories.
>
> **supporting\_context** `string`
>
> Context guiding memory extraction within this namespace, up to 1500 characters.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Add or Update Namespace Profile Buckets
>
> **Slug:** `SUPERMEMORY_UPSERT_NAMESPACE_PROFILE_BUCKETS`
>
> Add or update namespace-owned profile bucket definitions that guide memory classification. Omitted buckets remain unchanged. Organization-wide buckets are protected and cannot be changed. Returns the effective definitions, including organization buckets. Requires namespace write access.
>
> #### Input Parameters
>
> **buckets** `object` *required*
>
> Namespace-owned bucket names mapped to descriptions guiding memory classification. Names are 1-64 lowercase letters, digits, underscores, or hyphens, starting with a letter or digit. Descriptions have at most 2000 characters. Existing names are updated; new names are added.
>
> **namespace** `string` *required*
>
> Namespace identifier that scopes the profile bucket definitions.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
