Feature Requests

I'm wondering whether Kerlig could integrate with an MCP server to enable AI interactions with various applications, such as the Sketch MCP Server. https://www.sketch.com/docs/mcp-server/

I would love to be able to send results and context to a persistant memory or knowledge base to keep for extended periods and reference later, preferably supporting multiple locations so I can swap between groups of context.

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

Exa, native integrations (Gemini, Anthropic, OpenAI, OpenRouter all have native web search). Trigger web search via e.g. '@web'. Support in-line citation of sources. Some way of defining max results

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.

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.

Wondering if you can add support for GitHub Copilot, similar to what BoltAI has. This allows a consolidation of model subscription as well. Thanks!

Add support for context in Comet browser, similar to what you already have with Chrome.

adding files eg(pptx pdf word) course content. to setting named context and if I mentioned @the name of context it will answer my question based on what in the context