English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

memU: An Open-Source Memory Operating System for 24/7 AI Agents

Forum topic · 小凯 · 2026-02-27

Summary

memU is an open-source memory framework built by NevaMind AI that gives AI agents long-term, cross-session memory similar to human recall. Instead of using a flat vector store, memU organizes memory as a hierarchical, file-system-like structure with three layers: Resource (raw conversations and files), Item (extracted facts, preferences, and skills), and Category (auto-generated topic folders). The system enables proactive 24/7 agents that capture user intent, predict needs, and pre-fetch relevant context before being asked. Key features include dual-mode retrieval (fast RAG vector search for real-time queries and LLM-based deep reasoning for complex intent), significant token-cost reduction through selective memory injection, multimodal support, and both cloud (memu.so) and self-hosted deployment. Integration targets include OpenClaw, TEN Framework, and n8n. Compared with Mem0, Zep, and MemOS, memU differentiates through filesystem-style explainability, non-embedding retrieval, and self-evolving memory prioritization, with over 10,800 GitHub stars.

Key points

  • The problem it solves: Most AI assistants forget everything between sessions, forcing users to repeat context every time. memU provides persistent, cross-session memory so agents behave like companions with long-term recall.
  • What memU is: An open-source memory framework from NevaMind AI, designed for always-on (24/7) proactive AI agents. It has gained more than 10,800 GitHub stars and is positioned as memory infrastructure for the AGI era.
  • Three-layer hierarchical architecture (file-system style, not a flat vector DB):
  • Resource: raw materials such as conversations, documents, images, audio, and video.
  • Item: structured knowledge points extracted from resources (preferences, facts, learned skills).
  • Category: auto-organized topic folders forming a dynamic memory tree.
  • Why a filesystem model: memories are explainable, navigable from broad themes down to specific facts, and portable (exportable and backed up like folders).
  • Core capabilities:
  • 24/7 proactive agent that learns and updates in the background.
  • User-intent capture — e.g., mentions "business trip to Paris next week" trigger inferences about flights, hotels, restaurants, and prior food dislikes.
  • Cost efficiency via memory caching and selective context injection, avoiding linear token growth.
  • Dual-mode retrieval: fast RAG vector search for real-time responses vs. slower LLM-based reasoning for complex intent prediction.
  • Memory lifecycle: Monitor inputs → extract insights and update profile → predict user intent → proactively pre-fetch context and prepare suggestions.
  • Deployment options:
  • Cloud at memu.so (REST API): endpoints such as /api/v3/memory/memorize and /api/v3/memory/retrieve, with RAG-style queries.
  • Self-hosted via pip install memu and the MemUService Python client, suitable when data privacy is required.
  • Ecosystem integrations: originally built for OpenClaw; now used with the TEN Framework (real-time voice agents), n8n (workflow automation), and the official n8n plugin.
  • Comparison vs. alternatives:
  • memU — filesystem architecture, native proactivity, high explainability, non-embedding retrieval, self-evolving prioritization.
  • Mem0 — vector + graph, limited proactivity, medium explainability.
  • Zep — temporal graph, proactivity supported, high explainability.
  • MemOS — neural tensor, proactivity supported, lower explainability.
  • Use cases: AI companion/emotional support, personal assistant, personalized tutoring, financial advisory, and consistent customer service.
  • Philosophy: If the model represents reasoning and tools represent action, memory represents personality — identity, history, preferences, values, time awareness, behavior patterns, and a world model.
  • Reference links

  • GitHub: https://github.com/NevaMind-AI/memU
  • Cloud service: https://app.memu.so
  • Documentation: https://memu.pro/docs
  • Community: Discord

Tags

#memu#ai-memory#open-source#agent-framework#long-term-memory#llm#proactive-agent#memory-architecture

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177168617