aiagents.org

Mem0

Memory layer for adding persistent, personalized context to ai agents.

Visit site

Overview

Mem0 is an open-source memory layer for AI applications and agents. It extracts and retrieves useful information across conversations, with memory scopes for users, sessions, and agents. Developers can use its SDK and memory client to store facts and preferences, then search them with scoped filters so agents can maintain context over time.

Key features

  • Persistent agent memory
  • User, session, and agent scopes
  • Memory extraction and updates
  • Semantic, keyword, and entity retrieval
  • Scoped memory search
  • Python and JavaScript SDKs

Use cases

Show all 6Show fewer

Alternatives

  • MindSearchMulti-agent web search framework that plans queries and synthesizes retrieved information.ai agent framework
  • ZepAgent memory infrastructure that builds temporal context graphs from conversations and business data.ai agent frameworkFreemium
  • ExaWeb search and retrieval API for ai agents, with search, contents, and research endpoints.AI toolFreemium
  • LinkupWeb search API for AI applications with sourced results, full-text snippets, and private deployment.ai agent
  • Multiagent DebateResearch implementation where multiple language-model agents debate answers to improve reasoning and factuality.ai agent
  • TavilyWeb access API that searches and extracts live sources for ai agents.AI toolFreemium

Last updated 2026-09-16