MemOS
MemTensor
Self-evolving memory OS for LLMs and AI agents with tiered L1-L3 memory.
What is MemOS?
MemOS is a unified memory operating system for AI agents with L1-L3 memory layers, hybrid retrieval and cross-task skill reuse. It supports text, images, tool traces and personas, and is available self-hosted or as a managed cloud service. It claims 35% token savings via multi-cube knowledge management (project's own claim) and is backed by an arXiv paper.
Pros & Cons
Pros
- Multi-modal memory (text, images, tool traces, personas) with a tiered L1-L3 architecture
- Active cloud product with real pricing tiers and Docker self-hosting
- 30+ releases, research-paper backing and a sizeable fork base
Cons
- TypeScript-heavy codebase may feel unfamiliar to Python-first teams
- Self-hosted limits versus the cloud tier are not clearly documented
- Young org - long-term maintenance trajectory unclear
License
Apache-2.0 (OSI-open)
When it is interesting
Teams building multi-session agents that need structured, queryable long-term memory without standing up their own vector + graph stack.
When it is too early
Simple single-session chatbots where the context window already suffices.
Commercial alternative & related
- Commercial counterpart: Mem0
This repo featured in the 2026-07 edition of the Open-Source AI Radar.
claude-mem
thedotmack
Persistent memory layer across agent sessions with automatic semantic summaries and token-cost transparency.
graphify
safishamsi
AI coding skill that turns a folder of code, docs and images into a queryable knowledge graph across 20+ agents.
memU
NevaMind-AI
Memory framework for proactive AI agents - typed memory graph from chats, docs and media.