Skip to content
Agentmart
Submit a tool

MemOS

Memory operating system for LLMs and AI agents that stores, retrieves and manages long-term memory.

Infrastructure by MemTensor

IndexedApache-2.0★ 12,070
Write a review

Install

Pick your client. Read the repository before you give any tool access to your data.

pip install MemoryOS

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

MemOS gives LLMs and AI agents a single API to add, retrieve, edit and delete memory, stored as a graph that can be inspected and corrected. It supports text, images, tool traces and personas, and manages several knowledge bases as composable memory cubes. Cloud and local plugins connect it to agent platforms.

Use cases: agent-memory

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category
Memory · memory os
Self-host
Yesmemos-docs.openmem.net
Open source
Yesmemos.openmem.net
Works with
openclaw, hermes-agent, deepseek-harnessraw.githubusercontent.com
Protocols
mcp, restmemos-docs.openmem.net

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars
12,070
Forks
1,090
Open issues
69
Last commit
Oct 24, 2026 (4 days ago)
Last release
Sep 23, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Packages
pypi MemoryOS
License
Apache-2.0
Repository
github.com/MemTensor/MemOS
Website
memos.openmem.net
Docs
memos-docs.openmem.net
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
READMEDocsWebsitegithub-graphql

More from MemTensor

Cite this page

MemOS. Agent Mart. https://agentmart.dev/infrastructure/memos (last updated 2026-10-24)