Skip to content

Knowledge Management

Mem0
API integration

Ship Knowledge Management features without building the integration. Full Mem0 API access via Proxy and 30+ MCP-ready tools for AI agents — extend models and mappings to fit your product.

Talk to us
Mem0

Use Cases

Why integrate with Mem0

Common scenarios for SaaS companies building Mem0 integrations for their customers.

01

Add persistent memory to your AI product

Let your customers connect Mem0 so your AI features remember user preferences, past interactions, and context across sessions — without you building a memory layer from scratch.

02

Offer customers control over their AI's memory

Give end users a settings panel to view, edit, and delete what the AI remembers about them, backed by Mem0's memory history and update APIs for transparency and compliance.

03

Sync AI-derived facts into your core data model

Use Mem0 exports and webhooks to pull structured insights (preferences, traits, recurring issues) out of conversations and into your CRM, helpdesk, or analytics tables automatically.

04

Power multi-tenant AI agents with isolated memory

Provision a Mem0 organization or project per customer so each tenant's agent memory is partitioned, governed, and scoped — useful for support copilots, sales assistants, and vertical AI tools.

05

Improve retrieval quality with in-product feedback loops

Wire thumbs up/down or correction signals from your UI into Mem0 feedback so the memory layer gets smarter the more your customers' users interact with it.

What You Can Build

Ship these features with Truto + Mem0

Concrete product features your team can ship faster by leveraging Truto’s Mem0 integration instead of building from scratch.

01

Context pre-fetch on every AI call

Search relevant memories by user, agent, or run before each LLM generation and inject them into the system prompt for personalized responses.

02

Post-conversation memory ingestion pipeline

Push completed chat transcripts into Mem0 after each session and track async extraction status via event IDs without blocking your main app.

03

End-user memory management dashboard

Render a list of stored memories with history, edit, and bulk-delete controls so users can curate what the AI knows about them.

04

Structured export to your database

Trigger schema-driven exports to convert unstructured memories into typed JSON and sync fields into your own tables, CRM records, or analytics views.

05

Per-tenant project provisioning

Automatically create Mem0 organizations, projects, and members when a new customer signs up to keep memory data fully isolated per tenant.

06

Webhook-driven memory sync

Subscribe to Mem0 webhook events to react in real time when memories are created or updated and propagate changes to downstream systems.

SuperAI

Mem0 AI agent tools

Comprehensive AI agent toolset with fine-grained control. Integrates with MCP clients like Cursor and Claude, or frameworks like LangChain.

delete_a_mem_0_entity_by_id

Delete a user entity from mem0 by entity type and ID. Returns an empty 204 response on success. Required: entity_type, id.

list_all_mem_0_users

List all user entities stored in the mem0 platform. Returns: id.

get_single_mem_0_event_by_id

Get a specific mem0 event by id, retrieving its status and payload for tracking asynchronous memory operations such as writes submitted via the memories add endpoint. Returns: id, status, payload. Required: id.

list_all_mem_0_events

List recent mem0 events for your organization and project, useful for dashboards, alerting on FAILED events, and audit logging. Returns: id, status, payload.

create_a_mem_0_memory

Add memories to mem0 by submitting conversation messages through the V3 additive pipeline (async, ADD-only; nothing is overwritten). Returns: message, status, event_id. Required: messages, plus at least one of user_id, agent_id, app_id, or run_id.

mem_0_memories_bulk_delete

Delete multiple mem0 memories in a single batch request. Returns an empty 204 response on success.

mem_0_memories_bulk_update

Update multiple mem0 memories in a single batch request. Returns an empty 204 response on success.

delete_a_mem_0_memory_by_id

Delete a single mem0 memory by id. Returns an empty 204 response on success. Required: id.

list_all_mem_0_memories

List mem0 memories with paginated results using filter conditions including logical operators (AND, OR, NOT) and comparisons (gte, lte, in, icontains, etc.). Returns: id, memory, created_at, updated_at per record. Entity IDs (user_id, agent_id, app_id, run_id) must be nested inside the filters body object — top-level entity IDs are rejected.

get_single_mem_0_memory_by_id

Get a single mem0 memory by id. Returns: id, memory, created_at, updated_at. Required: id.

mem_0_memories_search

Search mem0 memories using hybrid retrieval (semantic, BM25 keyword, and entity matching) with relevance scoring. Returns: results containing id, memory, user_id, score, metadata, created_at, updated_at, and categories per match. Required: query and filters containing at least one entity ID.

update_a_mem_0_memory_by_id

Update the content or metadata of a single mem0 memory by id. Returns: id, memory, created_at, updated_at. Required: id.

mem_0_memories_bulk_delete_by_filter

Delete all mem0 memories matching specified filter conditions from the memory store. Returns an empty 204 response on success.

create_a_mem_0_export

Submit a mem0 export job to create a structured memory export using a customizable Pydantic schema. Returns the export job id and status. Optionally filter memories by user_id, agent_id, run_id, or session_id. Large exports may take time to complete.

get_single_mem_0_export_by_id

Retrieve the latest structured memory export from mem0 after an export job has been submitted. Returns the export id and schema-defined data. Optionally filter by user_id, run_id, session_id, or app_id.

create_a_mem_0_feedback

Submit positive or negative feedback on memory results in mem0 to help improve memory accuracy and relevance. Returns an empty 204 response on success.

create_a_mem_0_organization_member

Add a new member to a mem0 organization with a specified access role. Returns: id, user_id, role. Required: org_id, role.

list_all_mem_0_organization_members

List all members belonging to a specific mem0 organization. Returns: id, user_id, role. Required: org_id.

create_a_mem_0_organization

Create a new organization in mem0 to manage projects, members, and memory resources. Returns: id, name. Required: name.

delete_a_mem_0_organization_by_id

Permanently delete a mem0 organization and all its associated resources by id. Returns an empty 204 response on success. Required: id.

get_single_mem_0_organization_by_id

Get details of a specific mem0 organization by id. Returns: id, name. Required: id.

list_all_mem_0_organizations

List all mem0 organizations associated with your account. Returns: id, name.

get_single_mem_0_project_by_id

Get a single mem0 project by id within an organization. Returns: id, name, description, custom_categories. Required: org_id, id.

create_a_mem_0_project

Create a new mem0 project within an organization. Returns: id, name, description, custom_categories. Required: org_id, name.

update_a_mem_0_project_by_id

Update a mem0 project's configuration within an organization, including custom categories. Returns: id, name, description, custom_categories. Required: org_id, id.

delete_a_mem_0_project_by_id

Delete a mem0 project by id within an organization. This action is irreversible. Returns an empty 204 response on success. Required: org_id, id.

list_all_mem_0_projects

List all mem0 projects within an organization. Returns: id, name, description, custom_categories. Required: org_id.

list_all_mem_0_project_members

List all members of a mem0 project. Returns: email, role. Required: org_id, project_id.

create_a_mem_0_project_member

Add a new member to a mem0 project with a specified role. Returns: email, role. Required: org_id, project_id, email, role.

update_a_mem_0_project_member_by_id

Update the role of an existing member in a mem0 project. Returns: email, role. Required: org_id, project_id, email, role.

delete_a_mem_0_project_member_by_id

Remove a member from a mem0 project by email. Returns an empty 204 response on success. Required: org_id, project_id, email.

create_a_mem_0_webhook

Create a new webhook in mem0 for a project to receive real-time notifications about memory events. Returns: id, url, project_id, events. Required: project_id, url.

delete_a_mem_0_webhook_by_id

Delete a mem0 webhook by id to stop receiving memory event notifications for that endpoint. Returns an empty 204 response on success. Required: id.

get_single_mem_0_webhook_by_id

Get a mem0 webhook by id. Returns: id, url, project_id, events. Required: id.

update_a_mem_0_webhook_by_id

Update an existing mem0 webhook configuration by id, such as changing its url or event subscriptions. Returns: id, url, project_id, events. Required: id.

list_all_mem_0_webhooks

List all webhooks configured for a mem0 project. Returns: id, url, project_id, events. Required: project_id.

list_all_mem_0_memory_history

List the full change history of a specific mem0 memory to track how it has evolved over time. Returns: id, memory_id, event, prev_value, new_value, created_at, updated_at. Required: memory_id.

Why Truto

Why use Truto’s MCP server for Mem0

Other MCP servers give you a static tool list for one app. Truto gives you a managed, multi-tenant MCP infrastructure across 500+ integrations.

01

Auto-generated, always up to date

Tools are dynamically generated from curated documentation — not hand-coded. As integrations evolve, tools stay current without manual maintenance.

02

Fine-grained access control

Scope each MCP server to read-only, write-only, specific methods, or tagged tool groups. Expose only what your AI agent needs — nothing more.

03

Multi-tenant by design

Each MCP server is scoped to a single connected account with its own credentials. The URL itself is the auth token — no shared secrets, no credential leaking across tenants.

04

Works with every MCP client

Standard JSON-RPC 2.0 protocol. Paste the URL into Claude, ChatGPT, Cursor, or any MCP-compatible agent framework — tools are discovered automatically.

05

Built-in auth, rate limits, and error handling

Tool calls execute through Truto’s proxy layer with automatic OAuth refresh, rate-limit handling, and normalized error responses. No raw API plumbing in your agent.

06

Expiring and auditable servers

Create time-limited MCP servers for contractors or automated workflows. Optional dual-auth requires both the URL and a Truto API token for high-security environments.

How It Works

From zero to integrated

Go live with Mem0 in under an hour. No boilerplate, no maintenance burden.

01

Link your customer’s Mem0 account

Use Truto’s frontend SDK to connect your customer’s Mem0 account. We handle all OAuth and API key flows — you don’t need to create the OAuth app.

02

We handle authentication

Don’t spend time refreshing access tokens or figuring out secure storage. We handle it and inject credentials into every API request.

03

Call our API, we call Mem0

Truto’s Proxy API is a 1-to-1 mapping of the Mem0 API. You call us, we call Mem0, and pass the response back in the same cycle.

04

Unified response format

Every response follows a single format across all integrations. We translate Mem0’s pagination into unified cursor-based pagination. Data is always in the result attribute.

FAQs

Common questions about Mem0 on Truto

Authentication, rate limits, data freshness, and everything else you need to know before you integrate.

How does authentication work for connecting a customer's Mem0 account?

Mem0 uses API key authentication. Through Truto, your end users provide their Mem0 API key during the connection flow, and Truto securely stores and injects it on every request so you never handle credentials directly.

Can we isolate data per customer in a multi-tenant setup?

Yes. You can programmatically create Mem0 organizations and projects per tenant using the organization, project, and member endpoints, then scope memory operations with user_id, agent_id, run_id, and app_id filters.

How fresh is the data when memories are created?

Mem0's memory creation pipeline is asynchronous. The create endpoint returns immediately, and you can poll the corresponding event by ID (or list events) to confirm when extraction and storage are complete.

Which Mem0 operations are supported through Truto?

Truto exposes tools for memories (create, get, list, update, delete, bulk update, bulk delete, bulk delete by filter, search, and history), events, exports, feedback, webhooks, users, and full organization/project/member management.

Can we let end users edit or delete what the AI remembers?

Yes. You can list memories, fetch a single memory, view its history, update it, or delete individually or in bulk — making it straightforward to build user-facing memory controls for transparency and compliance.

How do we react to memory changes in real time?

Use the webhook endpoints to create and manage subscriptions in Mem0. When memories are extracted or modified, Mem0 will fire events to your endpoint so you can update downstream systems without polling.

Mem0

Get Mem0 integrated into your app

Our team understands what it takes to make a Mem0 integration successful. A short, crisp 30 minute call with folks who understand the problem.