Mem0

Mem0 adds long-term memory to AI applications. Instead of treating every conversation as the first interaction, Mem0 remembers user preferences, learns from corrections, and personalizes responses over time.

What it is

Mem0 is a memory layer for AI applications that stores, retrieves, and manages user preferences and conversation history. It uses vector embeddings to find relevant memories and has built-in conflict resolution for contradictory information.

Get started

from mem0 import Memory
memory = Memory()
memory.add("I love spicy food", user_id="user123")
results = memory.search("What should I cook?", user_id="user123")

When to use something else

• Simple conversation history: built-in LLM context works fine
• Production knowledge bases: use a vector DB like Qdrant