A question people ask
How do I make Claude remember my project decisions?
It's the right instinct with a slightly wrong word. You don't really want Claude to remember — you want it to act on what you settled. Those aren't the same thing, and the difference is why memory alone disappoints.
The dependable version of “remember my decisions” is inheritance. Unl holds each decision you settle, with its reasoning, and serves the relevant one to Claude unprompted the moment it bears — so it acts on your call, not on a recollection that a topic arose. You stay in command; free at launch.
Remembering vs inheriting
It isn’t a memory problem to solve — it’s a missing inheritance.
A memory recalls that pricing came up, that you discussed the schema, that you prefer terse answers. Genuinely useful — and it can’t tell you which of those discussions ended in a decision, or what carried it. Recall of a conversation and a settled call are different units.
What you actually want is the second one: the decision, its reasoning, and its currency — superseded the moment you change your mind. Served when it bears, that’s something the model can build from, not just be reminded of.
So the model acts on your call
Inheritance is reading what stands, not searching what was said.
When Claude is handed the settled decision with its why, it doesn’t re-open the question or guess at your intent — it reasons forward from your position. That’s the reliability “remember this” was reaching for.
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 Change your mind and it’s superseded, the old one retired.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
How do I make Claude remember my project decisions?
The reliable form isn't memory, it's inheritance: hold each decision with its reasoning and serve the relevant one when it bears on the work. Unl does exactly that — so Claude acts on the decision you settled rather than recalling that it came up, and supersedes it cleanly when you change your mind.
Why isn't a memory feature enough on its own?
Memory recalls what was said; it can't distinguish a settled decision from the options you discussed and rejected on the way to it. Inheriting the decision itself — with its why — gives the model something to reason from, which recall of a transcript doesn't.
How do I set this up?
Add the Unl MCP connector — about five minutes. Settle decisions as you work; the relevant one is then served into Claude's context unprompted when it bears, and the same set carries across Claude Code, ChatGPT and Cursor.
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.