MemOS

🎯 +43.70% Accuracy vs. OpenAI Memory 🏆 Top-tier Long-term Memory + Personalization 💰 Saves 35.24% Memory Tokens LoCoMo 75.80 • LongMemEval +40.43% • PrefEval-10 +2568% • PersonaMem +40.75%

🧠 MemOS Plugin: Persistent Memory for Your AI Agents ✨

Your lobsters and Hermes Agents now have the best memory system — choose Cloud Service or Self-hosted to get started 🏃🏻

🔌 Plugin	💡 Core Features	🧩 Resources
🧠 memos-local-plugin 2.0	One local-first memory core for Hermes Agent and OpenClaw.Self-evolving memory: L1 trace, L2 policy, L3 world model,and crystallized Skills driven by feedback.	🌐 Website · 📖 Docs · 🐙 GitHub · 📦 NPM
☁️ OpenClaw Cloud Plugin	Reduces token usage by 72%.Multi-agent memory sharing by user_id.	🖥️ MemOS Dashboard · 📖 Full Tutorial

👾 MemOS: Memory Operating System for LLM & AI Agents

MemOS is a Memory Operating System for LLMs and AI agents that unifies store / retrieve / manage for long-term memory, enabling context-aware and personalized interactions with KB, multi-modal, tool memory, and enterprise-grade optimizations built in.

Key Features

• Unified Memory API: A single API to add, retrieve, edit, and delete memory—structured as a graph, inspectable and editable by design, not a black-box embedding store.
• Multi-Modal Memory: Natively supports text, images, tool traces, and personas, retrieved and reasoned together in one memory system.
• Multi-Cube Knowledge Base Management: Manage multiple knowledge bases as composable memory cubes, enabling isolation, controlled sharing, and dynamic composition across users, projects, and agents.
• Asynchronous Ingestion via MemScheduler: Run memory operations asynchronously with millisecond-level latency for production stability under high concurrency.
• Memory Feedback & Correction: Refine memory with natural-language feedback—correcting, supplementing, or replacing existing memories over time.

News

• 2026-05-09 · 🧠 memos-local-plugin 2.0 Official local memory plugin for Hermes Agent and OpenClaw. One core powers self-evolving memory across L1 traces, L2 policies, L3 world models, and crystallized Skills, with local-first storage and feedback-driven retrieval.

---

GitHub에서 전체 내용 보기