Hung Tran

Hung Tran

Building Notebook OS for Gemini Notebook

About

Enjoy building solutions to remove frictions in the workflow of knowledge workers.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

14d ago

Notebook OS - The OS layer Gemini Notebook was missing

Gemini Notebook is brilliant at thinking. Everything around it is friction: copy-pasting URLs, hunting for papers in other tabs, re-typing the same instructions every session, exporting a deck with a watermark. Notebook OS removes that friction: one-click YouTube and academic sources, voice notes straight into a notebook, Skills that make it remember how you work, Studio recipes for decks, reports and quizzes, and watermark-free presenting.

Are you "Team Filesystem" or "Team Vector Search" for AI Memory?

When it comes to AI Memory, everyone's arguing "RAG vs. grep" like it's a religious war. It's not. It's just a cost curve. I've gotten this question so many times that I thought I'd just share my thoughts. So here goes:
Vector search wins when your corpus is massive, messy, and unstructured. Thousands of docs, no clean boundaries, meaning matters more than exact words.
Filesystem plus grep wins when your corpus is structured and actually yours. A folder of markdown files you can open, read, and audit line by line. No infra required.
Anthropic already ran this experiment in production. Claude Code dropped its RAG pipeline for plain agentic search (grep, glob, read) and it outperformed the vector pipeline on real work. Not close.
But the benchmark wars are missing the actual point. It was never about picking one. It's about knowing what each layer is for.
Markdown is your source of truth. Portable, human readable, greppable, not locked to one provider. Memory you can actually own and move.
Vector search is an accelerant on top of that truth. A fast index for when the haystack gets too big for exact match to keep up.
Use either one alone and it breaks down:
- Markdown alone stalls at scale and struggles with paraphrasing or fuzzy recall
- Vectors alone turn your memory into a black box you can't read, audit, or export
The next step for memory infrastructure isn't picking a side. It's the filesystem as the ledger and RAG as the index on top of it, so memory stays legible and portable, and still fast when it needs to be.
This is the exact direction we're building with AI Context Flow: markdown as the portable, ownable source of truth, with retrieval layered on top instead of replacing it.
If your memory only exists as embeddings inside someone else's vector DB, that's not memory. That's a lease.
Which team are you on?

2mo ago

What are the 5 tools you simply couldn't do your work without?

This could be related to your industry, or even a side project you're working on.

Here are my 5 (I couldn't function without them):

  1. Grammarly proofreading my texts, not just posts, but also client communication

  2. ChatGPT / Claude mostly brainstorming, help with copy, and summarising

  3. Figma I can put the basic graphics together quickly.

  4. Translator sounds incredibly old-school, but English is not my mother tongue

  5. Gmail and not only for communication, but also for storing ideas and sending myself email reminders for posts

View more