Select what you're working on, choose what you want AI to do, and keep moving — without rebuilding the context every time.
Early beta. No spam.Early beta. No spam. One email when your invite is ready.
One command on the mouse and GalaxyBrain takes the whole screen — translucent. You still see the page you were on, and you can still point at it.One command on the mouse and GalaxyBrain takes the whole screen — translucent. You still see the page, the document and the code you were on, and you can still point at them. Nothing to open, nothing to leave.
One command on the mouse, from whatever app you are in.
Your screen stays visible underneath. You never lose your place.
Point at what is on screen instead of describing it in words.
One translucent screen you call up from wherever you are — and everything below runs inside it.Not three features in three places. One translucent screen you call up from wherever you already are — and everything below runs inside it.
Highlight anything, wherever you already work.
Explain, Summarize, Rewrite, Ask — or one of your own.
The answer lands in place. No tab switch, no re-explaining.
“Why am I the one carrying context between my tools?”
“Why is my work cut up along app borders instead of along how I think?”
“I already worked out how I want this done. Why do I have to explain it again?”
Your best prompts live in a note you copy-paste from. Here you never save one: the moment a prompt runs, it becomes a command — same instruction, with an empty slot where the thing you pointed at used to be.Right now your best prompts live in a note you copy-paste from, and you rewrite the context around them every single time. In GalaxyBrain you never save one. The moment a prompt runs, it becomes a command: the same instruction, with an empty slot where the thing you pointed at used to be.
rewrite?in the voice of?
rewrite?in the voice of?Kept word for word, exactly as you typed it the first time it worked.
What you selected is dropped and left empty, so the command fits the next thing instead of the last one.
From the overlay, from the menu that appears on a selection, or from a shortcut you assign.
Two things you pointed at on screen, dropped straight into the sentence.
The verb stays, the nouns go. Nothing to configure.
The verb stays, the nouns go. Nothing to configure.
Name it, give it a shortcut, or leave it as it is.
Tap the command, then keep tapping things down the page. Each one gets it. Esc when you are done.Click the command, then keep clicking things down the page. Each one gets it. Esc when you are done.
The command shows what you have filled so far. The last tap runs it — you never press send.The command shows what you have filled so far. The last click runs it — you never press send.
Point first, tap the command second. It runs once and does not stay armed — no mode to escape from.Point first, click the command second. It runs once and does not stay armed — no mode to escape from.
You already worked out how you want AI to do this. The point is not to make you explain it again.
Highlight A, type what you want done, highlight B, send. GalaxyBrain saves the request as an action with empty slots — next time you tap it and just point at the next two things.Highlight A, type what you want done, highlight B, send. The request keeps its shape: GalaxyBrain saves it as an action with empty slots, so next time you click it and just point at the next two things.
Each thing you point at drops into the sentence as itself — not as a paragraph of description.
Click it, then point at the next two things. The slots fill as you go.
None of this is invented from scratch. Pointing at objects instead of describing them, and keeping a prompt that worked as a reusable command, come out of published HCI research.
DirectGPT — Masson et al., CHI 2024We're looking for the first people who feel this problem every day.
Early beta. No spam.Early beta. No spam. One email when your invite is ready.