PDF YouTube Transcriptions
Yet another YouTube caption extractor when DownSub already does this.

Runs Karpathy's Micrograd code directly in the browser without setup.
Developers learning from video tutorials
Cursor · Replit · Obsidian
I built YouNote to make it more like a database. except it's multimodal and interactive. You can click, extract code, run, modify and re-run in one surface. It preserves everything you do so you can build a knowledge base of useful information over time.
Try it out - no signup needed: https://younote.co/kane/share/VMj-3S1tku0?token=1CIznh5eGzDN...
Click 'run' on any cell and experiment with it directly — it executes in-browser via Pyodide and supports NumPy, Pandas, SciPy, Matplotlib, SymPy, and Statsmodels. Heavier workloads (like PyTorch) open in Colab.
Current limitations: Single-cell execution YouTube-native for now Shared workspace is view-only but fully-featured (code will run)
Framework (EdArXiv): https://osf.io/preprints/edarxiv/fntyu_v1
Would love to hear if you find this useful for learning/experimenting — or what you think it could do better.
Yet another YouTube caption extractor when DownSub already does this.
YouTube demo of AI agents on a Kanban board, but no link to try.
Summarizes long YouTube videos by topic—Glasp and similar extensions exist, but UX is thoughtfully tuned.
Turns YouTube cooking videos into shopping lists, solving the 'what's in the description' hunt.
Whisper fallback for captionless videos when YouTube API fails.
YouTube transcript extractor when YouTube's built-in and DownSub already exist.