How do you choose where your AI's long-term memory lives?

Two things actually differ between the options: what gets counted, and what the assistant can reach. Here's how to check both.

The short answer

Two things actually differ between the options: what gets counted, and what the assistant can reach. There are plenty of ways to give an AI a long-term memory, and most of them describe themselves the same way.

One: what gets counted. Some count how much you've stored. Others count how often you pull it back out. Some say "unlimited" and then sell you credits.

Two: what the assistant can reach. With some, connecting it means the assistant can see your whole workspace. With others, it only sees what you chose to keep.

Price and polish matter too, but those you can see at a glance. These two you can't.

Does this sound familiar?

Try a few and the same surprises come up: "unlimited" that isn't, a meter that moves when you read rather than when you store, and no clear way to tell what an assistant can see:

• The landing page says "unlimited", and then the pricing page is counting something else.
• You could get cut off not because you stored too much, but because you used it too often — if that's the unit, that's how it goes.
• You connect an assistant to your workspace and afterwards you're not sure what it can actually see.
• You go looking for a comparison and it's all feature lists, so you still don't know what to look at.

What actually gets counted

The unit is the thing to check: some count how much you've stored, a lot of them count how often you retrieve, and a workspace tool counts neither — there you are on its workspace plan.

A lot of them count retrieval. A free tier caps how many times a month you can look something up, or you buy credits, or it's metered by how much text gets processed. The names differ. What they have in common is that the meter moves when you use it, not when you fill it.

Which is why "unlimited" can mean two different things. Unlimited storage with a finite number of lookups is a common shape.

There's a reason it's built that way. Those services run an AI pass of their own when you save — pulling facts out of what you wrote, linking items to one another, building a graph out of them. Every one of those costs real money. When the cost lands on each operation, counting operations is the honest way to charge.

There's also a way to skip that work entirely: leave the tidying to the assistant you're already talking to. If it hands over a title and a summary already written, whatever receives it only has to hold on to it. Then the only ongoing cost is storage — so one number, how much you've stored, lines up with the cost, and there's nothing to be gained by counting lookups.

That's the side Contextick is on. One capacity number, and retrieval isn't counted.

What to check: find the unit on the pricing page before anything else. If the unit is how much you've stored, using it more doesn't cost more. If it's operations, lookups or credits, it does. Which of those is better for you comes down to how often you actually pull things back out.

What the assistant can reach

Connecting an assistant either opens your whole workspace, or only what you chose to save.

Notion opens the whole workspace. Once its MCP is connected, Notion's own documentation says the tools "can access everything you can access." There's no step where you pick which pages to open, and search reads the contents of pages, not just their titles. That's convenient — it means everything already sitting in there is usable straight away.

The other shape opens only what you left there. Nothing exists except what you saved, so that's all the assistant can see either. The trade is that you have to leave it there first.

Which one is right depends on what's in that space. If you already work in Notion and what's in there is mostly work, connecting an assistant there is the right call — the material is already in place and nothing needs moving. If there's also things in there that aren't work — personal notes, things involving other people, drafts that aren't ready — narrowing the range is easier to live with.

What to check: look for a step in the connect flow where you choose how much to open. If there isn't one, all of it is open.

Side by side, on those two axes:

What doesn't actually differ

Two things get written up as differences and aren't: working across several AIs, and how many items you can store.

"Works across several AIs" isn't ours alone. Now that MCP is a common standard, workspace tools and AI memory services alike connect to most assistants. That isn't a point of difference for us.

(Against an assistant's built-in memory it's a different story — that one works only inside that assistant, which is its own post. And what gets kept automatically isn't the same as what you chose to keep: the automatic side keeps getting broader, but you don't decide all of what stays.)

"How many items can I store" mostly doesn't differ either. Counting items is rare now. That's how old note apps worked, and comparing on it means looking at the wrong thing.

So which one fits you

How often you pull things back out is what decides it. The Notion side got answered above.

If you retrieve rarely and mostly want to put a lot in, a service that counts lookups is fine. The free tier will feel generous.

If you want an assistant referring to it several times a day, check the unit. That's the usage pattern where per-lookup pricing shows up fastest.

If you'd rather not spend time filing things, and you want what the assistant can see limited to what you left there, what you want is a knowledge layer — a store kept outside any single assistant — and Contextick is one. You connect it to the assistant you already use and say "remember this"; later, when it's relevant, that assistant brings it back. One number gets measured.

When this isn't for you

If you already work in Notion, if you enjoy organizing, or if you use one AI and don't plan to switch, this isn't for you:

If you already work in Notion, or something like it. Your material is there and your team is there, and adding a second store is usually a net loss. Connect an assistant to that instead.

If you enjoy organizing. If splitting things into folders and tagging them is satisfying, or you need that structure before you can settle, we have nothing to offer you — there are no folders and no tags in our store. It was built to make that unnecessary.

If you use one AI and don't plan to switch. Built-in memory keeps getting broader. If you're not moving between assistants, the reason to keep this outside is weak — that reason usually turns up on the day you switch.

What this doesn't do

You decide what goes in, nothing else is in there, and none of it gets organized for you.

• Nothing is saved automatically. You decide what's worth keeping. Your conversations aren't being read in the background.
• Nothing is there but what you saved. That's the strength and the limit at once — what you didn't put in doesn't come back.
• What you get back depends on what you saved. It finds what's closest in meaning, so a thin note comes back thin — and a note that says what you decided and why comes back useful.
• It doesn't organize for you; it makes organizing unnecessary. If what you wanted was a folder structure, see the section above.

FAQ

If you want to try it, connecting takes about a minute:

• ChatGPT — works on the free plan; you add Contextick as a plugin. Connect ChatGPT →
• Claude — works on the free plan; you add Contextick as a connector. Connect Claude →
• Something else — Cursor, Claude Code, Codex CLI and others connect over MCP. All connection guides →