MemTensor/MemOS
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.
This project helps AI developers build AI agents and large language models (LLMs) that can remember past interactions, skills, and knowledge over long periods. It provides a unified system for storing and retrieving diverse information like text, images, and tool usage history, allowing agents to learn from experience. AI developers can use this to create more personalized and effective AI assistants and automated systems.
6,790 stars. Actively maintained with 279 commits in the last 30 days.
Use this if you are building AI agents or LLMs and need a robust, persistent memory system that enables long-term learning, personalized interactions, and efficient management of various data types.
Not ideal if you are looking for a pre-built, end-user application or if your AI agent's memory requirements are minimal and temporary.
Stars
6,790
Forks
608
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
279
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/MemTensor/MemOS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Recent Releases
Compare
Related tools
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
volcengine/OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as...
mem0ai/mem0
Universal memory layer for AI Agents
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
agentscope-ai/ReMe
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.