Memory keeps what. Unl keeps why.
Without your why, your AI gives the average answer. With it, it gives yours.
The difference
a why makes.
Tell your AI “exports run through the queue” and it will obey. Then it meets an export you never mentioned, a small one or an urgent one, and it has to guess.
Tell it why, “sending them directly failed on large accounts”, and it can work that case out. A small export carries no risk, so it sends it directly. A large one goes in the queue.
A rule covers the cases you listed. A why covers the ones you didn’t.
Your decisions,
with their why.
Unl keeps each decision you make, with its why and with what it replaced. When your AI starts a task, it gets the few decisions that bear on that task, in the order you made them. It does not get everything you ever said.
Your AI already knows how to reason. Unl gives it your reason.
A kept why
can be walked.
A why that is not kept when you decide is gone. No model can work it out later, because it was never written anywhere. The best it can do is guess.
A why that is kept can be walked. Each decision points back to what it came from and to what it replaced, so your AI can follow the line from where you started to where you are now.
That line gives direction. Your AI sees where the work is heading, not only where it stands, so it can take the next step on its own and come back to you less often.
Better models make this matter more. The lesson of the last decade is that general methods beat rules built by hand, and many took it to mean people should step out of the way. A kept why is not a rule built by hand. It is material a general model works from, so the stronger the model, the further it goes on your behalf.
Keep the why, and your AI can go further without you.
What changes
for you.
Your AI stops asking what you already decided. It comes back to you only when your decisions run out, or when two of them conflict.
One sentence from you goes a long way. Every AI you use carries it into work you never listed.
It improves as the models do. A stronger model takes the same why further, so your record is worth more with each new one.
Models change. Sessions reset. Your decisions shouldn’t.
Unl gives you the ingredients; your AI makes the meal; you decide whether it is right.
Facts, rules,
and the why behind them.
A stored fact tells your AI what happened. A rule tells it what to do in the cases someone listed. Memory helps an agent carry its past forward. Unl carries your purpose into whichever agent comes next, through your target, what you decided and why, what replaced it and what still holds.
What you said
What you told it
What you decided, and why
What you use today,
and what Unl adds.
| The usual way | Where it stops | With Unl |
|---|---|---|
| Custom instructions in ChatGPT or Claude | Stays inside one app, and applies to every chat whether it's relevant or not | The same decisions reach every AI you use, and only when they bear on the turn |
| CLAUDE.md, .cursorrules, project knowledge | Lives in one repo and one editor, kept up by hand, and goes stale | Your decisions follow you across repos, tools and models, and update the moment you change your mind |
| Memory features | Remember what you said, not why you decided it | Keeps each decision with its reason, and what it replaced |
| Building your own MCP memory server | You host it, configure it and keep it running | Connect once. Unl is the why agent already running |
You stop writing things down for your AI. Unl notices decisions as you make them, and hands each AI the one that matters, when it matters.
What keeping why
actually requires.
Keeping a purpose pointed takes more than recalling the past. Your whys, what still holds and what changed must reach the agent when they matter.
That is why Unl is an agent, not a memory.
Plain answers.
01Is Unl a memory tool?
No. Unl is your why agent. Memory keeps what was said. Unl keeps why: what you decided, the reason behind it, whether it still holds, and what replaced it. Your AI works from your why, not from a transcript.
02Does Unl change what I decided?
Never on its own. When something you say changes a decision, your AI can offer to update it, and nothing moves until you say yes.
03Does it work with Claude Code, Cursor and ChatGPT?
Yes. One address over MCP, the same on every surface. Once it is added and you have signed in, it is on in every conversation, chat or coding, with nothing to say or paste.
04What does it cost?
Free to start. Paid plans add a weekly usage allowance calibrated to the AI plan you already pay for, and the API is on every tier. What you keep stays readable on every plan. Every price is on the pricing page.
05Where does my why live?
In your own workspace, tied to your sign-in. Any AI you connect reads the relevant part when it bears. Nothing reaches into your model or your tools. Your why stays yours, kept as long as you want it, gone when you say so.