mcp-server

MemOS: Ultra-Persistent Memory

Name: MemOS: Ultra-Persistent Memory
Author: MemTensor

Get ultra-persistent memory and token savings with MemOS, for founders using LLM and AI agents, backed by 10k+ GitHub stars.

10,690 stars990 forksTypeScriptHealth Score 9/10Updated 8/12/2026100% free · open source

What it does

MemOS provides ultra-persistent memory and token savings for founders using large language models (LLMs) and AI agents, enabling efficient and cost-effective operation of these models.

Install / run

git clone https://github.com/MemTensor/MemOS.git && cd MemOS

When to use it

•When building conversational AI applications that require remembering context across multiple interactions
•When optimizing LLMs for token usage to reduce costs and improve performance
•When integrating AI agents into workflows that require persistent memory and skill reuse across tasks

Quick start

1Run `npm install` to install dependencies
2Configure the `memos.config.json` file to set up the memory and retrieval settings
3Start the MemOS server with `npm run start`
4Use the `memos_client.ts` example to test the MemOS API and demonstrate ultra-persistent memory and token savings
5Explore the `examples` directory for more advanced use cases and integrations with LLMs and AI agents

Ready-to-paste prompt

Use the following command to test the MemOS API: `node memos_client.ts -m 'What is the capital of France?'`

Heads up: Make sure to set the `HYBRID_RETRIEVAL` environment variable to enable hybrid-retrieval, which is required for ultra-persistent memory and token savings, by running `export HYBRID_RETRIEVAL=true` before starting the MemOS server

Saves to your device