A situation we handle
Claude forgets what we agreed
You reached a call together — and a session later it's open again, as if the conversation never happened. The frustrating part isn't the forgetting. It's that the agreement had a reason, and the reason is what went missing.
An agreement is a decision with a why — the one unit a transcript can’t keep straight. Unl holds what you agreed, with its reasoning, and serves it back to Claude unprompted when it bears — so the call stays settled instead of quietly re-opening. You stay in command; free at launch.
An agreement is a decision, not a mention
It isn’t a memory problem to solve — it’s a missing inheritance.
To a record of the chat, the thing you agreed and the three options you rejected on the way to it look identical — they’re all just text that was said. So a fresh session, reading that, treats the question as open. It isn’t being contrary; it’s missing the one bit that marks a decision as settled.
That bit is the why. Hold the agreement with its reasoning and it stops being a mention that fades and becomes a call that stands — until you supersede it.
So it stays agreed
The decision arrives with its reason, before the model re-argues it.
When the settled agreement is served back with its why, Claude builds on it rather than relitigating it. Reasoning models respect a why — give them one and the agreement holds.
How it works
Connect once. From then on, what you settled arrives on its own.
1 · Connect. Add the MCP connector in a couple of steps, about five minutes. It plugs into Claude, Claude Code, ChatGPT & Cursor as an MCP connector.
2 · Settle a decision. When you make a call, it’s held with its reasoning — on your word, never scraped. Change your mind and it’s superseded, the old one retired.
3 · It arrives unprompted. Next session, the decision that bears on the work is served into the model’s context the moment it’s relevant — you don’t fetch it, and you don’t re-explain it. The model inherits what you decided and builds from it.
Questions people ask
Why does Claude forget what we agreed?
A new session sees the conversation, not the conclusion — and a transcript can't tell a settled agreement from the options discussed around it. Without the decision marked as settled, with its reasoning, the model reasonably treats the question as still open.
How do I make an agreement with Claude stick?
Hold it as a decision with its why, and have it served back when it bears. Unl does this: the agreement is kept on your word, superseded only when you change it, and surfaced unprompted the moment it's relevant — so Claude works from it instead of re-opening it.
Does this apply beyond Claude?
Yes — the same settled agreements carry over MCP across Claude, Claude Code, ChatGPT and Cursor, so a call you made in one place holds in the others.
What this is
Think inside your AI world — you stay in command
Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.
It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.
Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:
Alpha is invite-only · free at launch.