cortexosmain

Would love that — issues are open and the codebase is small enough to read in one sitting. The areas I'd most welcome help on right now are additional transcript backends and smarter grid packing.

NotebookLM was transcript-only when I last checked. Gemini proper does ingest video natively (samples ~1fps server-side). This tool is for everything that can't — Claude, ChatGPT web, local models — it turns the video into frames + transcript on your machine so any of them can read it.

Took this — pip install llm-real-video works now, same tool. Kept the original repo name so existing links don't break.