Claude Overlay

A floating Claude Code chat that sees your screen

Developer Tools

Artificial Intelligence

GitHub

Visit WebsiteSee on Product HuntGithub ⧉

since multi-monitor grabs one tagged image per screen, does token cost scale linearly with monitor count, or do you downsample/compress before it hits the model? curious how that plays with a fast Ctrl+Alt+Space hotkey loop

Nice, neat demo! Is this constantly recording the screen and if yes, is that something token efficiient. Also it is also paired with voice input along with screen share thing?

Since you're using the full Claude Code agent instead of just an API, what's the most surprising workflow users have discovered? Has anyone been using it for something completely different than debugging?

Always-on-top framing feels really natural when I'm jumping between editor and browser. The fact that it reads my actual screen and runs as a real agent on my plan makes it way more useful than another chat sidebar.

Really like that this sits on top of the existing Claude Code login instead of adding another agent layer.

One thing I’d want for daily coding use is a small run receipt after each screen-driven action: screenshot source, files touched, commands run, and which step came from what was visible on screen. When the input is a screen, debugging a wrong action later gets harder than with a normal prompt.

That kind of trace would make the overlay feel safer for long work sessions, not just faster.

Congrats on the launch! Since it reads whatever's on screen before answering, how do you handle sensitive info that might be visible (API keys, customer data, etc.) - is there any redaction or is it on the user to be careful what's showing?

the auto-shot + real agent combo raises a different question than the privacy-masking one - since it's not just reading the screen but can actually run commands and edit files, what stops a prompt injection sitting on screen (hidden text in a webpage, a doc, an email) from getting treated as an instruction the moment auto-shot captures it? not asking about intentional misuse, more about the screenshot itself becoming an untrusted input to an agent that has real write access

Love how it pulls from your actual screen context, that's the killer feature for me. One thing that would push it further: a quick toggle to switch between which monitor Claude reads, since I often have a reference doc on my second display I don't want it touching.

I really like that this is more than just a screen-aware chat. The fact that Claude can act on the file that’s already open makes it feel like part of the workflow rather than another window to manage.

Are you considering making context and permissions configurable for each overlay? For example, one overlay could be tied to a specific project in read-only mode, while another could be allowed to edit files. That could make using multiple overlays feel much safer and more predictable.

Nice work, Jason!

Hi Jason! Let's say I'm using this floating Claude Overlay on a web browser which has a very long content - meaning that we have to scroll down to read the full page. In this case, how can we make Claude Overlay read the whole context in our page?

One thing I'd love to see is cross-monitor support for the screenshot capture, specifically the ability to pick which screen Claude reads instead of grabbing everything at once. Would make it way more useful when working across a laptop and external display setup.

Hey this could actually save so much time/tokens. However regarding privacy - can you mask out specific regions of the screen (like .env files or sensitive API keys) so the overlay completely ignores them while capturing the rest of your layout? Any considerations around that?

finally something that lets claude see my actual screen instead of me copy-pasting everything. the always-on-top window is genuinely handy when you're jumping between docs and code.