Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

RAG & memoryPythonApache-2.0

mem0ai/mem0

Mem0 adds long-term memory to assistants: it extracts facts from conversations, stores them in a vector or graph store, and retrieves relevant memories on later turns. It is a practical way to make a chatbot feel continuous without stuffing the entire history into the context window.

42.0k stars4.3k forks260 contributors180 open issuesUpdated

What it does

  • Extracts and stores durable facts from conversations.
  • Retrieves relevant memories for each new request.
  • Supports vector, graph and hybrid storage backends.

Key features

  • Managed and self-hosted options.
  • User, session and agent scoped memory.
  • Framework integrations.
  • Memory inspection and deletion APIs.

How to install it

Commands are copied from the project documentation at the time of review. Check the repository for the current version.

Python
pip install mem0ai

Configure an LLM and vector store before use.

Alternatives to consider

mem0 is a strong default for rag & memory, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.

ZepLlamaIndex memoryLangChain memory

Prompts that pair with it

All prompts →
Verified Knowledge · FAQ

mem0 FAQ

Adoption questions we hear most often about this project.

Related repositories

RAG & memory · Python

A RAG engine with document parsing, chunking, retrieval and grounded citations.

64.0k6.1kApache-2.0

RAG & memory · Python

A data framework for connecting private documents to LLMs, with strong RAG and indexing primitives.

41.5k5.9kMIT