A situation we handle
When your AI treats your standing constraint as a soft hint that fades over the session
Your AI treats your standing constraint as a soft hint that fades over the session. A fresh session can't see the decision you already settled. Unlimitless hands it back, with its reasoning, the moment it bears on the work — so your AI acts on the call you made.
When your AI treats your standing constraint as a soft hint that fades over the session — and it's not that the model is weak; in a fresh session it just can't see the decision you already settled. Unlimitless (Unl) holds each decision you make with its reasoning and hands the relevant one back the moment it bears on the work, so your AI works from the call you already made. It's just-in-time context; the human stays in command. Works across Claude, Claude Code, ChatGPT and Cursor over MCP. Free at launch.
Adds it as a REST route with inline SQL in the handler — the default shape.
The settled decision isn't in view, so the model works from its own defaults.
Adds it the way this project is built — thin controller, service layer, repository for the query — because that structure is the call you settled.
The layered structure you settled for this project is right there when it's relevant — so the model works straight from it.
Same request, two outcomes. Unl doesn't make the model smarter — it hands back the call you already made, so the work stays on it.
Why this matters
The decision didn't have to be remembered. It had to be there — at the moment it bore on the next step.
You make a real call — an approach, a constraint, a convention you settled and why — and it lives in a conversation that's since scrolled away. A capable model, working only from what's in front of it, has no way to see it. Hand that decision back at the right moment and the work stays on track: the model reasons forward from your call instead of re-deriving it.
That's the difference Unl makes. It's just-in-time context: the settled decision, with its reasoning attached, arrives when it's relevant — and you stay in command of the call.
Questions people ask
Why does my AI drift back to its own defaults instead of the choices I settled?
A fresh session only has the conversation in front of it, so a call you settled earlier isn't in view — it's not that the model is weak, it just can't see it. Unl holds your settled decisions, each with its reasoning, and hands the relevant one back the moment it bears on the work — so the model works from the call you made. It works across Claude, Claude Code, ChatGPT and Cursor.
How is this different from my AI recalling past chats?
Recall surfaces what was said when you go looking for it. Unl hands a settled decision back unprompted — it arrives because it's relevant to what the model is about to do, with the reasoning attached. The unit is the decision and its why, in front of the model when it matters, not a transcript to search.
Which AI tools does this work with?
Unl is one connection over MCP, so it hands your settled decisions to Claude, Claude Code, ChatGPT and Cursor alike. The call you settle on one surface is inherited on 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.