MemOS
Open-source memory operating system for LLMs and agents with a unified API for adding, retrieving, editing and deleting graph-structured, multi-modal memory.
Tags
Description
Offered self-hosted and as MemOS Cloud, with local and cloud memory plugins for agents such as OpenClaw and Hermes Agent. The Python package is published on PyPI as MemoryOS (2.0.33 as of Sep 2026; GitHub is at v2.0.34), which is unrelated to BAI-LAB's MemoryOS.
Related
- Mem0: Memory layer for AI agents and apps: drop-in persistent memory that lets agents learn from past interactions.
- Letta: Platform for stateful agents with memory, identity and the ability to learn over time (formerly MemGPT); terminal UI, App Server, desktop app and Agent SDK.
- Zep: Unified context layer that combines business data, documents and conversations into governed context and memory for agents.
- MemoryOS: Hierarchical short/mid/long-term memory system for personalized agents, as a PyPI package and an MCP server.
Guides & comparisons
- Research memory libraries compared: A-MEM vs MemoryOS vs MemOS vs LightRAG (Comparison): Four open-source memory systems that started as research papers. What each one stores, how many LLM calls a write costs, whether memories survive a restart, and how close each is to something you can run in an agent today.
Sources
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)