MemTensor/MemOS

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

About the project

MemOS is a memory operating system that stores, retrieves, and manages long-term memory for large language models and AI agents. It supports context-aware interactions by organizing text, images, tool traces, personas, and knowledge bases for reuse across tasks.

Latest release v2.0.33 — Release v2.0.33 · 3 Sept 2026

These files are MemTensor/MemOS's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.

11,200Stars on the repository
7Files it configures its agents with
3,034Tokens loaded in every session
3Agents configured

Instructions

Agents