Think inside your AI world.
A major release, against the ceiling you set
A release feed is loud by design: hundreds of tags a day, patches and minors and majors across every package you will never run. What you actually need is the one that breaks a ceiling you set — a major bump on a dependency you deliberately capped — and that is a line the feed cannot hold, because the line is yours.
Read npm and the GitHub releases feed through Unl and the whole public stream arrives measured against the criterion you ratified — so instead of scanning every tag, you get the single release that crosses a major ceiling you set on a dependency you actually run, with the reason it crosses. The one, not the thousand.
What npm and the GitHub releases feed publishes
npm and the GitHub releases feed are a genuine public good, and together they are a lot to keep up with:
- Thousands of new releases a day across npm and every repository you watch
- Every bump, from a routine patch to a full major-version break
- Package after package that never entered your build
- No sense of which of your capped dependencies a tag bears on — that context is not in the feed
The line the feed can't hold
Say you capped a dependency at a major version on purpose — 4.x, because a major bump means a migration you have not scheduled — and ratified the line that makes a release worth your attention: only a new MAJOR release, on a dependency I have deliberately capped, interrupts me — patches and minors ride the normal upgrade. That ceiling is a decision you made; it is not a column the feed models.
The reason the line is yours is the whole point. A feed can list every tag; it cannot know which dependencies you capped, or that you capped them to defer work, or that a minor bump is noise to you and the major you were holding off is not.
The frame judges the data it is given; it does not verify the source’s accuracy.
The one that crosses
So when that dependency publishes its next major release — 5.0, above the 4.x ceiling you set — it crosses, and nothing else does. Through Unl the answer arrives as a verdict: the dependency you capped at 4.x has shipped 5.0, over the major ceiling you drew, so this one is the migration you were deferring; the forty patches and minors this week were not. Same public feed; a decision instead of a digest.
You didn't ask — it was already there
You did not ask for it. The criterion was already ratified, so the next time you open Claude on that repository the crossing is already in the window — read against your ceiling, with the reason it cleared it — rather than waiting for you to remember to scan the releases. You author the line once; the read applies it every time the world moves; a scheduled push that ships the crossing on a timer is a separate delivery this page does not claim.
The answer comes back measured against what you already decided, and why.
The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Read further
Questions people ask
How is this different from a release feed or a version-bump alert?
An alert fires on the source's rule — every tag it watches, or a bump pattern someone else defined. This fires on YOUR rule: the major ceiling you set, applied only to a dependency you deliberately capped, with the reasoning attached. The feed shows you the thousand; the measured read shows you the one that crosses a line you drew, and why.
Do I get pinged the moment the release ships?
The capability is that the crossing arrives measured against your criterion the next time you are working — it is already in the window, read against your ceiling, rather than a feed of tags you monitor. A scheduled push is a separate delivery; what the read guarantees is that when the crossing surfaces, it surfaces as a verdict against your position, not as one more release note.
Does Unl change anything in my repository or the release feed?
Unl reads through npm and the GitHub releases feed, and can write back on your explicit gesture — it never acts as a side effect of a read. The releases feed is a public GET; your ceiling lives in Unl; the read joins them and returns a verdict, altering neither.
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.