Launch HN: Poly (YC S22) – Cursor for Files

Hooking up the Internet to my filesystem is scary. What security measures are in place to ensure a compromise of your infrastructure doesn't compromise mine?

This is really cool! I suck at organizing my filesystem and I've lost track of how many times I had to find _that ONE_ PDF which I KNOW I have but cannot find! This would have solved that many times over.

However, at least for my use-case, this is a very infrequent problem. So, a monthly subscription and the security risk wouldn't be worth it. Though I'm certain there are people who work with files all day and for them, this might be god-send!

Nitpick: Cursor for Files makes approximately zero sense to me given what I see here.

Feedback:

Supporting an enterprise air gapped solution of this clearly has huge value. It really doesn't matter where the data is stored if the indexing / embedding is happening on your infrastructure.

Enterprises with compliance requirements are quite likely the types of clients looking for ways to save time searching through petabytes of data.

I'd rather see a demo instead of a highly edited video with split second shots of the product.

When I read “Cursor for Files” my mind went to “app for reading and diffing content (i.e markdown) which I was very excited about.

While it seems like a cool enough product conceptually, in practice there is absolutely zero chance I'm putting my files in your cloud to be garbelled up by AI and paying you for the privilege. Also, allowing an agent to download arbitrary files from the internet is extremely alarming. nope nope nope nope NOPE

Only way I would ever use something like this is with a local/self-host model that I run myself on my own hardware, with meticulous control over what the thing can access on the internet.

Can you say more about how Polyembed-v1 handles video files? Does it handle the audio or just the video? What do you do about videos longer than a couple of minutes?

Cool idea.

Maybe I'm too old, but after I read the post I thought -- oh this is an "AI-first Quicksilver" -- who remembers that plugin for Mac? I don't think they stayed relevant enough

My immediate hesitance with a tool like this (which sounds awesome) is that I don't actually trust tools like Claude Code unless I have them running in a git directory where I can see exactly what changed, and easily revert when needed.

Do y'all have a solution for this here? Some kind of safety layer of some kind to easily review and optionally revert actions the agent has taken across my entire file system?

The search part of this is cool, but if the write side is solved, shut up and take my money.

The landing makes focus on multimedia, but I am writing a non fiction book, and most of my sources are links, PDFs, docs with notes, etc. Would it work in that case as well? My ideal solution should be able to oganize my files and be able to ask questions about the contents.

Won’t this only work when connected to the internet? So I can’t use it on a flight.

Or if I work in finance, or healthcare, or law, or government, or a hardware design company, I don’t want my files leaving my network. Those are very important use cases, much more important than searching my personal laptop. I want this for WORK, not my little photo collection or notes or whatever.

This is a great use case for modern LLM/embedding models but gotta be local to be actually useful in the places where it’s most needed.

Very interested in the idea of an AI being able to interact with my filesystem.

we experimented with something like this: https://local-note-taker.vercel.app/chat

repo in case you'd rather run it locally: https://github.com/tambo-ai/local-note-taker

Curious to compare how our two ideas are built differently, feel free to reach out (email in my profile)

Greplin was just too early.

Great idea, but the landing page visuals is too cluttered, makes me want to have cursor for your website

Thanks for sharing this.

I am curious to know if your agent can connect to a user’s custom MCP server in order to make tool/calls with files attached. For example I have a custom MCP server that catalogs the images which are submitted in the RPS 2.0 payload. I have a python wrapper script that convert’s Cursor’s stdio MCP interface to an http request, inserting htaccess credentials and scanning the tool call args for any files that it needs to attach to the payload. This lets me set up the wrapper script as an MCP server in the cursor settings. This lets the built in Auto-mode agents do some similar kinds of tasks like you are describing.

With that said, it sounds like your system has better agents and tools for working with things besides just text files, so I am wondering if perhaps your agentic tools might be a good fit for a situation where for example I have a messy filesystem full of images that may already be duplicates in the database. If I provide the MCP tools into my database, can your system and agents use tools that I define? Does your system have ability to attach access credentials if/when making calls to third party mcp/tools?

Have to admit I went in kinda dismissive (who wants to change finder?) but that landing page really sells the value well, love the flip cards. Wonder how much of it was AI generated?

[dead]

[dead]

Congrats on the launch!

Feedback: this site crashes my Safari (Sequoia) reliably, so I can't see the demo.

Could you elaborate how this is superior to using Microsoft OneDrive + Copilot? Particularly in an enterprise setting where a corporate Microsoft 365 account is subject to whatever controls we want to put on the corporate OneDrive accounts.

Seeing a loading spinner like that makes me feel like I'm back in the Flash days

I assume that someone has been mighty proud about the website. But I am sorry, it is terrible. Loading my "experience" took over a minute. An my "experience" is not even cached, it was loaded from scratch on the second visit.

Also, while it looks visually stunning, it is really not helping much introducing the product. I find it rather confusing, really.

The first thing I noticed - when you searched for "upcycling", all results that you have shown hat the exact match keyword "upcyling" in their filename. If this is just a text grep, then the product is redundant: "everything" exists.

In case you really would get results for "upcycling" based on an internal LLM-based summary of disk content, that would be great - but your live demo does not show that.

Also, later down my "experience" you try to show how user input is handled. But as the "experience" is fixed size and can not be zoomed in, it is impossible to read any of the blurry text.

Again, I understand that this "experience" looks impressive. But it is a complete distraction and does not help at all to introduce your product.

I spent 5 minutes looking at this, one of that looking at a loading spinner like it's 2005 again, and I have no clue what your USP is.

And to be honest: Your HN post here also is not helping. Think "Dropbox + NotebookLM + Perplexity" - what? That makes no sense. It is a complete distraction. Explain what your product/service is, what it's USP is, and what value it provides to me.

Instead after a wall of text you are explaining me that one can select files by clicking on them.

It feels like an LLM wrapper in search of a problem. Cloud search plus already exists: https://www.glean.com/product/workplace-search-ai

I do not find the idea of bringing my data to your search engine attractive. The data should stay put and you should merely index it.

And since LLMs let you generate things, you also have a feature to do that. But who is going to want to create things -- armed with only a text prompt -- while they are searching? Rarely have I wanted to combine images like in your demo. And on the rare occasion I did -- like today! -- I used a GUI to do it in. I suppose creatives would find this feature more.