Feature Requests

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.

I know this is a big lift but it would be awesome if somehow Kerlig was my main MCP client with an option to choose the inference server like ollama or OpenAI

As a User, I would like to have an Auto Updater settings, So that I do not have to manually download the binary for the website and install it, So that I can be up to date and take advantage of Kerlig. So that I do not miss improvements, bug fixes, and new features.

I click on Translate, I want it to automatically go to the next step. I click on a language, I want the action to start on click, not enter, not double clic... on single clic thanks

The fix spelling and grammar feature is great for small bits of text, but sometimes if I end up doing a lot more, like a couple pages for a quick check before sending, some little punctuation changes are hard to make out. It would be good if there was maybe a bar along the side of the text to show which lines have changes. For example, in Word, when using track changes simplified view, the red line shows in parts where there have been changes. Maybe a similar concept would be good for Kerlig.

Since 2.0, the window is no longer hiding by itself when losing focus. It doesn’t seem to behave like the other system windows. It doesn’t appear in the quick app switcher (Cmd + Tab), and when I swipe to another macOS desktop space with my trackpad, I see it briefly above all the other windows no matter what before going background, which creates a visual glitch. If an opt-in is possible to get auto-hiding like before (v1.X) I would take it or at least being visible in macOS quick app switcher.

Dear, I would like to suggest, if possible, that the application allows multiple requests on the selected text. Currently, it only supports an initial prompt or textual request, without the possibility to continue interacting with the text to further transform it. This limitation forces to repeat the selection process for each new action, which results in a considerable waste of time. I thank you in advance for your attention to this suggestion that could significantly improve the user experience.

When running an operation via a shortcut in headless mode, it would be nice to have an indicator that: The request is received by Kerlig The designated AI is processing it The AI has completed to query This can be done on MacBooks by activating the Taptic Engine under the trackpad for an audible and tactile click.

Temperature can make a huge difference in the way that the LLM responds. I might want to have high temperature when I'm doing a creative task, but I definitely want lower temperature when I'm doing more deterministic things like spelling and grammar checks. Can you consider adding the ability to set Temperature on either a per model or (better yet) per Action basis? I would use a 0.1 for my spelling and grammar check, but I would absolutely use something closer to 1.0 or even higher than 1.0 for more creative tasks like improving writing or rewording.

For apply preset and changing models, ctrl+p and tab, would be great if those keys can be rebinded!