Why

Memory keeps what. Unl keeps why.

Why keeping the reasons behind your decisions takes an agent, not a memory.

A no without a why
is a yes.

Tell a model “don’t do that” and it can’t tell which neighbouring cases you meant, so it treats them as open. Give it the reason and it can work out the cases you never wrote down.

So Unl doesn’t steer your AI with stop signs. It steers with your why: a frame of reasons, as broad or as fine as you want, that keeps the model pointed where you meant it to go.

A missing layer

Memory keeps what.
Unl keeps why.

Memory keeps what you said. A prompt file holds what you told it. Neither keeps why. Unl keeps what you decided and why, what replaced it and what still holds.

01 / Chat history

What you said

×What you said
×In one model
×Lost over time
×No structure
02 / Notes or a prompt file

What you told it

×Static instructions
×Manual updates
×No reasoning behind it
×Easily forgotten
03 / Unl, your why agent

What you decided, and why

✓What you decided, and why
✓Updates with you
✓Structured and scoped
✓Available to any AI
Why is different

What keeping why
actually requires.

Memory is one capability. Keeping why faithfully sets a whole chain of requirements that memory does not meet.

01
Why requires provenance.Know where a decision came from.
02
Why over time requires replacement history.Know what changed, and what replaced what.
03
Why across AIs requires model-independent persistence.The why belongs to you, not to any one model.
04
Why right now requires relevance.Only what bears on this moment comes forward.
05
Why against reality requires live context.Know when the world around a decision has changed.
06
Why without taking over requires a human boundary.Unl can notice and propose. You decide.
07
Why that works with the model requires an agent.The model reasons; the why gives it direction. Unl keeps the two working together, turn by turn, at the moment it matters.

That is why Unl is an agent, not a memory.

Why compounds

Memory accumulates.
Why compounds.

A fact is a point. An instruction is a limit. A why has direction. Tell a model exports run through the queue and it follows the rule. Tell it why, because inline exports failed on large accounts, and it can reason about the case you never wrote down.

Your decisions don’t live alone. The reasons behind product, architecture, customers and pricing bear on one another. Unl brings the relevant path into the model, so a fresh AI starts from the direction you already set, not from zero.

The model doesn’t just inherit answers. It inherits the direction they came from.

pricingarchitecturecustomersproductthe question in front of youdirection
Questions

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. On coding surfaces the relevant part arrives on the turns that need it. In chat, say connect to unl.

04What does it cost?

Pricing opens shortly. Paid plans are usage allowances calibrated to the AI plan you already pay for, and the API is on every tier.

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.