Skip to content

Long-term memory for Claude and ChatGPT

Give Claude or ChatGPT long-term memory with MCP

Save notes once in Hjarni. Connect with MCP. In a new conversation, ask Claude or ChatGPT to retrieve the notes you need and continue from the same source.

Free to start. No credit card required.

The problem

Sound familiar?

Native memory can carry context from earlier chats. You may also want explicit notes, research and decisions you maintain yourself.

You re-explain your project, your stack, your preferences. Again. Then again tomorrow.

Your notes live in several places. Finding the right source and keeping it current takes work.

How it works

How to give Claude or ChatGPT long-term memory

Two steps. No plugins. No scripts.

01

Save notes once

Write in Markdown. Organize with notes, folders, tags. This is your knowledge base.

02

Connect with MCP

Hjarni has an official MCP server and is listed in both connector directories. Connect Claude or ChatGPT one time.

One MCP server URL
https://hjarni.com/mcp

After connecting, ask Claude or ChatGPT to search and read the relevant notes before answering. You can also ask it to save or update a note, then check the result in Hjarni. Saved notes remain available for future conversations; retrieval depends on the assistant using the connection.

What it means

What "long-term memory" actually means here

This is a persistent knowledge base your connected assistant can search and read. You decide what goes in: notes, folders, tags. You can read it, edit it, and export it any time. It is plain Markdown you own.

Set instructions per folder. Tell Claude and ChatGPT how to format, what tags to use, what tone to write in. These instructions guide the assistant's behavior; they do not guarantee retrieval or change access permissions.

Why a knowledge base

Why a knowledge base, not built-in memory

ChatGPT memory and Claude's memory can carry context from prior conversations, with settings to review and correct remembered information. They serve their own assistant environments, and do not automatically stay in sync with each other.

Hjarni gives both assistants a connection to the same maintained Markdown notes. Keep research, decisions, and team knowledge there, then ask either assistant to retrieve the source material it needs.

I use Hjarni for my thesis. Having my assistant search and edit my notes directly has completely replaced the tedious back-and-forth of pasting context into external chat windows.
Wiba

The constraint is the feature

Simple on purpose

We left features out on purpose. No databases. No kanban boards. No page builders. Just notes, folders, tags, and an MCP server that works. The constraint is the feature.

Pricing

Free to start

25 notes free. No credit card required. No trials, no hidden fees.

How do I give Claude or ChatGPT long-term memory using MCP?

Create a free Hjarni knowledge base and save a few notes in Markdown. Connect a compatible assistant through the Claude Connectors Directory, ChatGPT Apps Directory or Hjarni’s official MCP endpoint. Ask it to retrieve relevant notes before answering and save useful updates through permitted tools. The notes persist between sessions; connecting does not guarantee automatic retrieval or saving. Review the notes and their history to check the result.

Your notes on every device

Hjarni has its own native apps. Free on every plan for iPhone, iPad and Apple Silicon Mac and Android. Same account, same notes as the web. An internet connection is required.

Start here

Write once. You both remember.

25 notes free, forever. No credit card required.

5 out of 5 from 14 reviews 13,400+ notes a day read or updated by AI

Works with Claude, ChatGPT, Cursor and any MCP client.