Skip to content
Changelog

Report a bug

Mem0 integration: operations for AI agents

Mem0 connects to Type.com as an integration. This page lists the 68 operations documented for Claude and Codex in Type.com: 36 read, 17 write, 15 destructive.

About Mem0

Mem0 is an universal, self-improving memory layer for LLM applications.

Categories: Developer Tools & IT

How to connect Mem0 to Type.com

Connect
API key
Access
Organization connection: one shared account for the workspace.

To add the connection, follow the steps in Space connections.

Documented operations

68 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

68 operations listed.

Agents

  • Write

    Agents create

    Create a new Agent.

    POST /v1/agents/

Apps

  • Write

    Apps create

    Create a new App.

    POST /v1/apps/

Entities

  • Read

    Entities list

    GET /v1/entities/

    GET /v1/entities/

  • Read

    Entities filters list

    GET /v1/entities/filters/

    GET /v1/entities/filters/

  • Read

    Entities read

    GET /v2/entities/{entity_type}/{entity_id}/

    GET /v2/entities/{entity_type}/{entity_id}/

  • Destructive

    Entities delete v1 (deprecated)

    Delete an entity by its numeric ID. Deprecated in favor of `DELETE /v2/entities/{entity_type}/{entity_id}/`, which takes the entity's string name instead of this numeric ID.

    DELETE /v1/entities/{entity_type}/{entity_id}/

  • Destructive

    Entities delete

    DELETE /v2/entities/{entity_type}/{entity_id}/

    DELETE /v2/entities/{entity_type}/{entity_id}/

Events

  • Read

    Retrieve all events for current organization and project.

    Retrieve all events for current organization and project.

    GET /v1/events/

  • Read

    Retrieve details of a specific event by its ID.

    Retrieve details of a specific event by its ID.

    GET /v1/event/{event_id}/

Exports

  • Read

    Export data based on filters

    Get the latest memory export.

    POST /v1/exports/get/

  • Write

    Create an export job with schema

    Create a structured export of memories based on a provided schema.

    POST /v1/exports/

Memories

  • Read

    Memories list (deprecated)

    Get all memories.

    GET /v1/memories/

  • Read

    Memories list v2 (deprecated)

    Get all memories.

    POST /v2/memories/

  • Read

    Memories events list

    Despite the endpoint name, this returns memory history entries (the same shape as `GET /v1/memories/{memory_id}/history/`), not event/ingestion-job records. For event/ingestion-job status, use `GET /v1/event/{event_id}/`.

    GET /v1/memories/events/

  • Read

    Memories search create (deprecated)

    Perform a semantic search on memories.

    POST /v1/memories/search/

  • Read

    Memories search v2 (deprecated)

    Search memories based on a query and filters.

    POST /v2/memories/search/

  • Read

    Get all memories (V3, paginated)

    List memories scoped by filters, paginated. Entity IDs **must** be passed inside the `filters` object. Top-level `user_id` / `agent_id` / `run_id` are rejected with 400. `filters` supports the same operator set as V2 search (`AND`, `OR`, `NOT`, `in`, `gte`, `lte`, etc.). Response is a paginated envelope; pass `page` and `page_size` as query parameters to step through results.

    POST /v3/memories/

  • Read

    Search memories (V3)

    Relevance-ranked search across stored memories. V3 uses hybrid retrieval and can also apply temporal reasoning for time-aware queries. Entity IDs **must** be passed inside the `filters` object. Top-level `user_id` / `agent_id` / `run_id` are rejected with 400. At least one entity ID is required.

    POST /v3/memories/search/

  • Read

    Memories entity read

    Returns a paginated list of memories belonging to the given entity.

    GET /v1/memories/{entity_type}/{entity_id}/

  • Read

    Memories read

    Get a memory.

    GET /v1/memories/{memory_id}/

  • Read

    Memories history list

    Retrieve the history of a memory.

    GET /v1/memories/{memory_id}/history/

  • Read

    Get a summary of memories matching the given filters.

    Backs the Python SDK's `client.get_summary()`. Not currently exposed by the TypeScript SDK.

    POST /v1/summary/

  • Write

    Memories create (deprecated)

    Add memories.

    POST /v1/memories/

  • Write

    Add memories (V3)

    Extract and store memories from a conversation using the V3 additive pipeline. Entity IDs (`user_id` / `agent_id` / `run_id`) are accepted at the top level. At least one entity ID is required so the memory is scoped to a session.

    POST /v3/memories/add/

  • Destructive

    Memories delete all

    Delete memories by filter. At least one filter is required. Previously, omitting all filters silently deleted everything; now it returns a validation error.

    DELETE /v1/memories/

  • Destructive

    Memories update

    Update a memory's text, metadata, or expiration date.

    PUT /v1/memories/{memory_id}/

  • Destructive

    Memories delete

    Delete a memory.

    DELETE /v1/memories/{memory_id}/

  • Destructive

    Memories batch update

    Batch update multiple memories (up to 1000) in a single API call.

    PUT /v1/batch/

  • Destructive

    Memories batch delete

    Batch delete multiple memories (up to 1000) in a single API call.

    DELETE /v1/batch/

Runs

  • Write

    Runs create

    Create a new Agent Run.

    POST /v1/runs/

Stats

  • Read

    Retrieve memory-related statistics for the authenticated user.

    This endpoint returns the following statistics: - Total number of memories created - Total number of search events - Total number of add events

    GET /v1/stats/

  • Read

    Check API key validity and resolve organization/project context.

    Both the Python and TypeScript SDKs call this endpoint on client construction to validate the API key and resolve the default `org_id` and `project_id`.

    GET /v1/ping/

Users

  • Write

    Users create

    Create a new User.

    POST /v1/users/

Feedback

  • Write

    Submit feedback

    Submit feedback for a memory.

    POST /v1/feedback/

Organizations

  • Read

    Organizations read

    GET /api/v1/orgs/organizations/

    GET /api/v1/orgs/organizations/

  • Read

    Get organization

    Get a organization.

    GET /api/v1/orgs/organizations/{org_id}/

  • Read

    Get organization members

    Retrieve a list of members for a specific organization.

    GET /api/v1/orgs/organizations/{org_id}/members/

  • Write

    Create organization

    Create a new organization.

    POST /api/v1/orgs/organizations/

  • Write

    Add organization member

    Add a new member to a specific organization.

    POST /api/v1/orgs/organizations/{org_id}/members/

  • Destructive

    Delete an organization

    Delete an organization by its ID.

    DELETE /api/v1/orgs/organizations/{org_id}/

  • Destructive

    Update organization member role

    Update the role of an existing member in a specific organization.

    PUT /api/v1/orgs/organizations/{org_id}/members/

  • Destructive

    Remove a member from the organization

    Remove a member from the organization

    DELETE /api/v1/orgs/organizations/{org_id}/members/

Projects

  • Read

    Get projects

    Retrieve a list of projects for a specific organization.

    GET /api/v1/orgs/organizations/{org_id}/projects/

  • Read

    Get project details

    Retrieve details of a specific project within an organization.

    GET /api/v1/orgs/organizations/{org_id}/projects/{project_id}/

  • Read

    Get Project Members

    Retrieve a list of members for a specific project.

    GET /api/v1/orgs/organizations/{org_id}/projects/{project_id}/members/

  • Write

    Create project

    Create a new project within an organization.

    POST /api/v1/orgs/organizations/{org_id}/projects/

  • Write

    Update Project

    Update a specific project's settings.

    PATCH /api/v1/orgs/organizations/{org_id}/projects/{project_id}/

  • Write

    Add member to project

    Add a new member to a specific project within an organization.

    POST /api/v1/orgs/organizations/{org_id}/projects/{project_id}/members/

  • Destructive

    Delete Project

    Delete a specific project and its related data.

    DELETE /api/v1/orgs/organizations/{org_id}/projects/{project_id}/

  • Destructive

    Update project member role

    Update the role of a member in a specific project within an organization.

    PUT /api/v1/orgs/organizations/{org_id}/projects/{project_id}/members/

Project

  • Destructive

    Delete Project Member

    Delete Project Member

    DELETE /api/v1/orgs/organizations/{org_id}/projects/{project_id}/members/

Webhooks

  • Read

    Get Project Webhooks

    Retrieve all webhooks for a specific project

    GET /api/v1/webhooks/projects/{project_id}/

  • Write

    Create Webhook

    Create a new webhook for a specific project

    POST /api/v1/webhooks/projects/{project_id}/

  • Destructive

    Update Webhook

    Update an existing webhook

    PUT /api/v1/webhooks/{webhook_id}/

  • Destructive

    Delete Webhook

    Delete an existing webhook

    DELETE /api/v1/webhooks/{webhook_id}/

Dream

  • Read

    Get Dream configuration

    Retrieve the project's Dream (memory synthesis) configuration together with the plan entitlement snapshot. Dream automatically supersedes/merges memories on the add path; **Synthesis** (reflection) is the opt-in part controlled by `reflection_enabled`.

    GET /api/v1/orgs/organizations/{org_id}/projects/{project_id}/dream/config/

  • Read

    Get Dream stats

    Lifecycle + synthesis counts for the project's Dream dashboard, plus reflection freshness. Requires a Pro or Enterprise (CUSTOM) plan.

    GET /api/v1/orgs/organizations/{org_id}/projects/{project_id}/dream/stats/

  • Read

    Get Dream activity

    Supersede/merge activity feed (newest first), keyset-paginated. Synthesis output is not included here — see the runs endpoint.

    GET /api/v1/orgs/organizations/{org_id}/projects/{project_id}/dream/activity/

  • Read

    Get Dream synthesis runs

    Synthesis activity grouped per run (newest first), keyset-paginated. Each run inlines its first page of synthesized memories with their sources; larger runs page the rest via the run-memories endpoint.

    GET /api/v1/orgs/organizations/{org_id}/projects/{project_id}/dream/runs/

  • Read

    Get memories in a Dream run

    Keyset page of the synthesized memories within a single run (for runs whose `has_more` is true).

    GET /api/v1/orgs/organizations/{org_id}/projects/{project_id}/dream/runs/{run_id}/memories/

  • Read

    Get a synthesized memory's sources

    The source memories a synthesized (pattern) memory was distilled from, for the memory drawer's provenance panel.

    GET /api/v1/orgs/organizations/{org_id}/projects/{project_id}/dream/memory/{memory_id}/sources/

  • Read

    Preview Dream scope

    A no-write preview of the scope Dream synthesis would analyze for the project (a capped sample plus the count of users with enough memories to benefit). Never runs the LLM and never mutates anything.

    POST /api/v1/orgs/organizations/{org_id}/projects/{project_id}/dream/preview/

  • Write

    Update Dream configuration

    Enable or disable Synthesis (reflection) for the project, or change the reflection mode. Requires a Pro or Enterprise (CUSTOM) plan and organization-owner permission. Synthesis is forward-only: after enabling, it only synthesizes memories added from that point on.

    PATCH /api/v1/orgs/organizations/{org_id}/projects/{project_id}/dream/config/

Profiles

  • Read

    Get an entity's profile

    Return the memory profile for one user. Generation is asynchronous, so a known entity that has no profile yet is a normal 200 carrying a `status`. A 404 means only that no such entity exists.

    GET /v2/entities/{entity_type}/{entity_id}/profile/

  • Read

    Get profile settings

    Return the profile settings for the project the API key is scoped to.

    GET /v2/profiles/settings/

  • Read

    Read a generation job

    The job nests under `job`. `total` is null until `enumeration_complete`, and `completed` is `succeeded + failed + skipped`.

    GET /v2/profiles/jobs/{job_id}/

  • Write

    Update profile settings

    Update the project's profile settings. Only the fields present in the body are written, so one setting can change without re-sending the others.

    POST /v2/profiles/settings/

  • Write

    Generate profiles

    Start one generation. `operation` says what to build: - `sample` — up to 10 real entities, so a schema can be judged before it is used widely. These are real profiles: they are saved to those entities and count toward usage. - `trigger` — one entity, named by `entity_id`. Send an `Idempotency-Key` header. Replaying the same key returns the same job instead of charging twice. Poll `status_url` from the response until the status is terminal.

    POST /v2/profiles/jobs/

See How connections work for access and permissions, or browse all integrations.