Feature Requests

Please add a URL scheme for Kerlig, so that apps like PopClip can access Kerlig actions using kerlig://. It is easier to integrate into workflows that manipulate text selection without needing to use a keyboard shortcut.

Tahoe now enables access to Apple's on-device LLM from within apps ( https://developer.apple.com/documentation/foundationmodels ). Integrating this model within Kerlig would be wonderful! Here is how someone has already experimented with that approach: https://github.com/gety-ai/apple-on-device-openai

It would be great for Kerlig to support Azure's OpenAI models, as some companies have set up these models for their employees to use.

add functionality that will return an image as a response if the generate image promt is used

Hello, can we remove the 20 character limit for the Custom Model Display Name? "Gemini 2.5 Flash-Lite" is the exact same number of characters as the built-in "Gemini 2.0 Flash-Lite" :)

Please implement a feature to display the real-time cost of the current chat exchange within the Kerlig app interface. This cost should update as the conversation progresses, reflecting token usage and associated pricing.

When users upload a PDF in Kerlig, configure the OpenRouter API call to use plugins.pdf.engine: 'native' for models supporting native PDF input. This leverages the model's direct PDF understanding, improving accuracy and efficiency. Reference: https://openrouter.ai/docs/features/images-and-pdfs

Some custom HTTPS API endpoints have no certificates, which probably explains why, when I attempt to integrate them with Kerlig, I get a Connection error (for example, a curl -k request works). Would it be possible to add an optional switch that allows the use of HTTPS API endpoints without certificates?

Please enable an option to add multiple tabs in the browser (just like in the Dia browser). It will help a lot with research.

Would love to be able to just "speak" to Kerlig to input my request. Straight up Speech to text, but also some kind of "ramble mode" To be able to ramble and have it summarize my thoughts, cataloging them and allowing me to use the output in different ways. stored as notes, or Todo's or pull parts of all of it into prompts for further processing.