Feature Requests

I would like a way to copy and paste in HTML. When I write an email in Fastmail (the MacOS app), I use rich text — same in Slack by the way — and so I want a way for Kerlig to copy the HTML version form of what's selected, modify it, and paste back as HTML so all the links/formatting stay.

Kerling Windows does not behave like a typical application window. It cannot be resized or positioned on one side of the screen or set to full screen to read responses properly.

Hi Kerlig Team, I've been using Kerlig for a while now, and I find it very nice with a simple and clean interface and user experience. I'd like to propose a feature that I believe some users would want. It would be cool if there was a "screen share undetectability" option to purchase as an additional add-on or upgrade to Kerlig. AI tools are employed by many users in meetings, presentations, interviews, tutoring sessions, or when working remotely. One feature that could set Kerlig apart from the competition is a feature to make the assistant stay in the background while the user is sharing the screen as a normal user would, and the only other app that does is I can think of is Cluely, but Cluely is just too expensive (79-149 USD a month for undetectability). It would also provide an extra paid option for those who require it but don't want to pay for it to be included in the standard product. This may be hard to do technically and may not be possible on different platforms depending on the operating system, but I think it would be interesting to include if possible. Thanks to the suggestion, and thanks for keeping on improving Kerlig! Best regards, Justin Song

I often engage in lengthy discussions on various topics and would appreciate the ability to export full chat conversations as a single Markdown file. This feature would enhance usability, improve documentation of conversations, and simplify the process of tracking information without the need to sift through individual segments for one chat.

Make Kerlig recognize specific code block tags and treat their contents as files. Example: A custom prompt that turns selected text into an ICS calendar event would output: ```ics EVENT DATA GENERATED BY PROMPT ``` If the code block is tagged ics , Kerlig extracts its contents, generates an .ics file, and shows the file inline instead of the code block. Clicking opens it in the default macOS app; right‑click provides options to save, open with another app, or reveal the raw contents. Similar to text correction feature, TAB key could be used to switch between file view and raw code block view.

Flash 2.5 is a wonderful model, as is o3 and the others, but for quick text manipulation, I don't need the thinking or reasoning. They add extra time to process and use extra tokens. Can we have an option to disable thinking on either a per model or (preferably) a per-action basis? For instance, Fix Grammar and Spelling shouldn't need thinking. For Gemini, setting the thinking budget to 0 will disable thinking altogether: https://ai.google.dev/gemini-api/docs/thinking#set-budget I'm not sure about the other models, but I think this would be hugely helpful.

Add OpenAI ChatGPT OAuth sign-in feature. Since they allow users to use models through OAuth in OpenClaw, they'll definitely allow this app as well.

Please include subscription login and validation to openAI subscription and model selection. A lot of people use Subscription now not API login That would help a lot. Thanks

As the title says, when using Kerlig in Discord, the selected text does not get improved.

As an OpenRouter user, I often find it hard to tell which models are active. This small improvement, moving the active models to the top of the integrations tab, would make a significant UX improvement.