Agent Memory

Mem0 logo

Mem0

Long-term memory layer for agents and assistants.

Open source

Best when the product needs explicit remembered facts and preference updates across conversations.

Official resources

Docs Official site

Selection advice

Evaluate Mem0 with real user-history cases, not synthetic chat logs. The key question is whether remembered facts improve future actions.

Best for

  • user memory
  • preference learning
  • agent assistants

Not ideal for

  • static document Q&A
  • workflows where memory cannot be inspected or deleted

Core concepts

memory extractionsearchfiltersgraph memory

Minimal implementation shape

Store user facts with a user id, retrieve only the top relevant memories, and show the user what the agent remembered.

Integrations

PythonTypeScriptvector databasesgraph memory

Alternatives

Zepcustom memory serviceLangGraph memory
Compare all Mem0 alternatives

Related guides

AI Agent Memory Explained

Agent memory is the product-facing layer that controls what an agent remembers across interactions.

Short-Term vs Long-Term Memory for AI Agents

Short-term memory keeps the current run coherent; long-term memory changes future runs.

Related comparisons

RAG vs Agent Memory

Choose RAG for document grounding. Choose agent memory when the product must remember user or task facts over time. Use both only after the boundary is explicit.

Related patterns

Explicit Long-Term Memory

A pattern where the product defines exactly which facts can become durable memory.

Sources