mem0

Integrate persistent memory into AI applications using the Mem0 Platform and OSS SDKs.

2|Updated May 12, 2026
One-click install
npx skills add https://github.com/tajo9128/BioDockify-Pharma-AI --skill mem0-tajo9128
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mem0
Source: https://github.com/tajo9128/BioDockify-Pharma-AI/tree/main/.agents/skills/mem0
Command: npx skills add https://github.com/tajo9128/BioDockify-Pharma-AI --skill mem0-tajo9128

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? AI chatbots and agents forget users between sessions, forcing repetitive re-explanation and blocking personalization. This Skill guides the integration of Mem0's managed memory layer so applications can store, search, and manage long-term user memories via API. ## Core Features & Use Cases - Memory CRUD Operations: Add, search, update, delete, and batch-manage memories scoped by user, agent, app, or session using Python or TypeScript SDKs. - Framework Integrations: Ready-made patterns for LangChain, CrewAI, OpenAI Agents SDK, LangGraph, LlamaIndex, AutoGen, and Pipecat voice pipelines. - Platform Features: Hybrid semantic + BM25 retrieval, entity linking, custom categories, webhooks, memory export, and multimodal input support. - Use Case: A support chatbot retrieves a customer's past preferences with client.search(), injects them into the LLM prompt, then stores the new conversation with client.add() for future sessions. ## Quick Start Ask the assistant to set up Mem0 in your project and add persistent memory to your chatbot using the MemoryClient SDK.

Frequently Asked Questions about mem0

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add persistent memory to my AI chatbot?

Install the mem0ai package, initialize MemoryClient with your API key, then follow the retrieve-generate-store loop: call client.search() before generating a response and client.add() afterward to store the interaction under a user_id.

What is the difference between Mem0 Platform and the open-source Memory class?

Platform uses MemoryClient with an API key against the managed api.mem0.ai service, while the OSS Memory class runs locally with your own LLM, embedder, and vector store configuration. Platform adds batch operations, webhooks, exports, and project management.

Does Mem0 work with LangChain and CrewAI?

Yes, Mem0 provides integration patterns for LangChain, CrewAI, OpenAI Agents SDK, LangGraph, LlamaIndex, AutoGen, and Pipecat. CrewAI has native support via memory_config with provider set to mem0.

Why does Mem0 search return empty results after adding memories?

Memories process asynchronously in v3, so wait 2-3 seconds after add() before searching. Also verify the user_id matches exactly and pass entity IDs inside the filters object, since combining user_id and agent_id in one AND filter returns nothing.

Can I use Mem0 with TypeScript or Node.js?

Yes, install the mem0ai npm package and use MemoryClient for the Platform API or import Memory from mem0ai/oss for self-hosted usage. TypeScript uses camelCase top-level parameters like userId and topK, but snake_case keys inside filters.