Complete AI Training

MCP server · Notes

mnemos MCP server

by vishalbanwari26

Give your AI a long-term memory so it remembers what you told it days or weeks ago.

Flow diagram: you ask your AI “What did I tell you about my dog?”, on your own computer the mnemos MCP server works with your computer, and you get back A reply that remembers.

mnemos is a memory helper for AI assistants. It lets your AI remember things you told it before, like your dog's name or the tools you use at work, and bring them up later when they matter. It is handy for anyone who is tired of repeating themselves in every new chat.

What is an MCP server? The 30-second version

On its own, your AI can only chat about what is in front of it right now. An MCP server is a small helper program that gives your AI a new skill or a connection to another service. This one connects your AI to mnemos, a memory store that lives on your own computer. When you ask something, the AI can quietly check that memory and use what it finds to answer you better.

What this MCP server does

You type a message to your AI like you always do. The AI sends your message to mnemos, which looks through past conversations and saved facts to find anything related. It ranks what it finds by how similar it is to your question and how recent it is, then hands the best pieces back to the AI. The AI uses those pieces to write a reply that actually remembers your history. Over time, mnemos also tidies itself up by merging repeated facts and letting old ones fade.

Flow diagram: you ask your AI “What did I tell you about my dog?”, on your own computer the mnemos MCP server works with your computer, and you get back A reply that remembers. Click to zoom

What you can do with it

  • Remember facts you shared in earlier chats, like your preferences or your team's tools
  • Recall what was said in a past conversation and when it happened
  • Merge duplicate facts into one clean statement so your memory stays tidy
  • Let old facts fade out when they are no longer useful
  • Show which memories were used to answer a question, with scores
  • Adapt how it searches based on what works best for you

Try asking your AI

  • “What did I tell you about my dog?”
  • “Which deployment stack did we settle on last week?”
  • “Remind me what I said about my preferred Python framework.”
  • “Have I mentioned any deadlines coming up?”

What it gives back to you

You get a normal chat reply from your AI, but it is grounded in things you said before. Behind the scenes, mnemos also keeps a list of the memories it used, with scores showing how relevant each one was. If you use the dashboard, you can see counts of memories, which ones were merged or forgotten, and a log of every cleanup action.

Before you start

What you need

  • A computer where you can run commands (the README uses git clone and Docker)
  • Docker installed, or a Postgres database you can point it to
  • An API key from Anthropic or Groq (a kind of password for AI services; the site gives you one when you sign up)
  • Python 3.10 or newer and the uv tool

Good to know

This server stores personal facts about you and your conversations on your own computer, so treat that storage like a private diary and be careful who else can access it.

Install it with your AI

Add mnemos MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check mnemos MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

Developers and technically curious people who want their AI assistant to remember things across sessions, especially those comfortable running a local service.