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

Hello world, this is Abhay from Poly (https://poly.app). We’re building an app to replace Finder/File Explorer with something more intelligent and searchable. Think of it like Dropbox + NotebookLM + Perplexity for terabytes of your files. Here’s a quick demo: https://www.youtube.com/watch?v=RsqCySU4Ln0.

Poly can search your content in natural language, across a broad range of file types and down to the page, paragraph, pixel, or point in time. We also provide an integrated agent that can take actions on your files such as creating, editing, summarizing, and researching. Any action that you can take, the agent can also take, from renaming, moving, tagging, annotating, and organizing files for you. The agent can also read URLs, youtube links, and can search the web and even download files for you.

Here are some public drives that you can poke around in (note: it doesn’t work in Safari yet—sorry! we’re working on it.)

Every issue of the Whole Earth Catalogue: https://poly.app/shared/whole-earth-catalogues

Archive of old Playstation Manuals: https://poly.app/shared/playstation-manuals-archive

Mini archive of Orson Welles interviews and commercial spots: https://poly.app/shared/orson-welles-archive

Archive of Salvador Dali’s paintings for Alice in Wonderland: https://poly.app/shared/salvador-dali-alice-in-wonderland

To try it out, navigate to one of these public folders and use the agent or search to find things. The demo video above can give you an idea of how the UI roughly works. Select files by clicking on them. Quick view by pressing space. Open the details for any file by pressing cmd + i. You can search from the top middle bar (or press cmd + K), and all searches will use semantic similarity and search within the files. Or use the agent from the bottom right tools menu (or press cmd + ?) and you can ask about the files, have the agent search for you, summarize things, etc.

We decided to build this after launching an early image-gen company back in March 2022, and realizing how painful it was for users to store, manage, and search their libraries, especially in a world of generative media. Despite our service having over 150,000 users at that point, we realized that our true calling was fixing the file browser to make it intelligent, so we shut our service down in 2023 and pivoted to this.

We think Poly will be a great fit for anyone that wants to do useful things with their files, such as summarizing research papers, finding the right media or asset, creating a shareable portfolio, searching for a particular form or document, and producing reports and overviews. Of course, it’s a great way to organize your genAI assets as well. Or just use it to organize notes, links, inspo, etc.

Under the hood, Poly is built on our advanced search model, Polyembed-v1 that natively supports multimodal search across text, documents, spreadsheets, presentations, images, audio, video, PDFs, and more. We allow you to search by phrase, file similarity, color, face, and several other kinds of features. The agent is particularly skilled at using the search, so you can type in something like “find me the last lease agreement I signed” and it can go look for it by searching, reading the first few files, searching again if nothing matches, etc. But the quality of our embed model means it almost always finds the file in the first search.

It works identically across web and desktop, except on desktop it syncs your cloud files to a folder (just like google drive). On the web we use clever caching to enable offline support and file conflict recovery. We’ve taken great pains to make our system faster than your existing file browser, even if you’re using it from a web browser.

File storage plans are currently at: 100GB free tier, paid tier is 2TB at $10/m, and 1c per GB per month on top of the 2TB. We also have rate limits for agent use that vary at different tiers.

We’re excited to expand with many features over the following months, including “virtual files” (store your google docs in Poly), sync from other hosting providers, mobile apps, an MCP ecosystem for the agent, access to web search and deep research modes, offline search, local file support (on desktop), third-party sources (WebDAV, NAS), and a whole lot more.

Our waitlist is now open and we’ll be letting folks in starting today! Sign up at https://poly.app.

We’d also love to hear your thoughts (and concerns) about what we’re building, as we’re early in this journey so your feedback can very much shape the future of our company!

56 points | by aabhay 19 hours ago

32 comments

  • Fischgericht 9 hours ago
    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.

    • aabhay 8 hours ago
      You really would get results for "upcycling" based on an internal LLM-based summary of disk content!
      • Fischgericht 6 hours ago
        Then this is what you should point out. In this case the file names in your promo visualization should NOT contain the search keyword.

        So if a search for "fashion upcycling" also returns "case_study_on_how_to_turn_PET_into_clothings.docx", then that's a great USP, and that is what you should point out in your pitch and visualization.

        This is because in real life most people already fail at finding good search terms. Many people are not even able to come up with a collection of words to put into the google search box. And the word(s) they may choose could be too specific, or not specific enough. So any kind of "unsharp" search is helping those kind of users.

        • aabhay 6 hours ago
          I'm not sure what you're referring to. On the landing page animation, out of 8 search results, only 3 have the word "upcycling", and 5 have either "upcycled" or "upcycling". In the segment after that, two files have neither "upcycling" nor "upcycled". What you're referring to seems already to be the case.
          • PrairieFire 25 minutes ago
            I love the website. You’ll find some strong opinions here, I wouldn’t make changes based solely on the HN crowd’s curmudgeonly takes.
  • bangaladore 18 hours ago
    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.

    • aabhay 18 hours ago
      I think the phrase is apt, actually, but it's not perfect:

      1. We have an embedded agent that can read, edit, organize, and take actions on your files. This means it can read almost any media type, which is why it's "cursor for files" even though "isn't _cursor_, cursor for files?". In other words, Cursor is "Poly for text" :)

      2. We provide you with an "IDE", I.e. a file browser. However, unlike Cursor we actually built our engine rather than relying on an existing open source one like VS Code

      Lastly, agree about the enterprise solution. All in due time for sure!

      • layer8 12 hours ago
        “Cursor” is a developer product. A non-dev is less likely to know Cursor-the-product or understand what it is, and will more likely think of a mouse cursor or a text cursor. So even disregarding whether the analogy makes sense, this is a strange slogan for a file browser that presumably is targeted at regular computer users. “ChatGPT for files” would make more sense.
      • bangaladore 15 hours ago
        Part of the issue with the "slogan" is Cursor/XYZ jank IDE is already "for files". "Cursor for data" seems slightly better in my opinion. You are clearly using "Cursor" as something to draw familiarity to, But I suspect the bulk of your future target market probably doesn't know what "Cursor" is.
        • aabhay 14 hours ago
          Agreed. We chose it for the Hacker News crowd.
  • esafak 9 hours ago
    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.

    • aabhay 8 hours ago
      We are creating things! You can create reports, summaries, documents, etc. via the agent. And yes we can mass edit your files through prompts. The agent can take both single and batch actions. That's the power of the harness we built for the agent. It actually understands and can take action on your file system.
  • bluelightning2k 27 minutes ago
    This website is so so good! How did you make it technically?
  • prasoonds 18 hours ago
    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!

    • aabhay 17 hours ago
      Agree. One thing that we see our users doing more of is "NotebookLM style tasks" where they just drop in a bunch of files or ask the agent to download stuff and then start using the agent to do things. Summarize, create notes, answer questions, etc. We believe that an increasing amount of work with "files" will be stuff like this, and having a file system that can search all your files to do these things seemed useful enough for us to build!
    • conductr 13 hours ago
      I used the original Google Desktop app a long time ago and even though I didn’t need to use it often it did become my de facto way of opening/locating files (I was really bummed when they killed it).
  • BrandiATMuhkuh 4 hours ago
    Congratulations on the launch.

    One customer type that will absolutely love that are architecture studios. Basically all data they generate (drawing, plans, presentation) live either on SharePoint or NFS (or some other file system like ACC).

    If you can provide for them a solution they can host on their private cloud (air-gapped) you have an enterprise-deal.

    Why air-gapped - many documents they generate are secret (military or competition. Think next largest tower in the world) - copy right: for example the German norm body DIN does not allow you to use documents from them and add them into an LLM (I'm not talking training, I simply talk RAG) except!!! if you keep it in a private cloud like Azure.

    Why do I know that: because I worked on that problem @howie.systems

  • akersten 18 hours ago
    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?
    • aabhay 17 hours ago
      I'm not certain what exact scenario you are referring to. Do you mean if someone is able to install malware on our backend system will that malware get sent to you?

      Is there something in particular that we are vulnerable to that doesn't also affect Google Drive, Dropbox, iCloud Drive, OneDrive, etc.?

      • encroach 16 hours ago
        You are correct that, from a security standpoint, your software is no different than any other software I install on my computer, since desktop computers have no sandboxing. But from a privacy standpoint, it could be uniquely concerning.

        With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer.

        Dropbox, iCloud, and OneDrive are just backup services, so in theory they could just back up your files as an encrypted blob and have no way to read them. Unfortunately, they don't encrypt them (which is partly why I don't use those services). But at least I have their "promise" that they won't read or analyze my files, which would make me feel better even if its a weak promise.

        On the other hand, your service, by nature, is reading an analyzing all of my files using a remote server.

        • aabhay 16 hours ago
          You choose which files to use in Poly, we don't scan your hard drive either.

          I don't know about the other services, but Dropbox _does_ read your files. https://help.dropbox.com/security/privacy-policy-faq

          > We may build models that identify keywords and topics from a given document. These models may be trained on your documents and metadata, and power features within Dropbox such as improved search relevance, auto-sorting and organization features, and document summaries.

          • mbesto 9 hours ago
            That's the thing. I'm already tied into GDrive, Dropbox, OneDrive, etc. all which have LLMs hooked up to them in some form or other. I'll gladly just wait until those catch up and I'll avoid the switching costs. You're all using the same LLMs under the hood anyway.
    • bigyabai 18 hours ago
      +1 for this - I don't trust proprietary software with access to my whole filesystem like this. Definitely not if a future update could change the pricing terms, introduce hidden telemetry or deprive me of the app on a whim.

      This app gives me the same heebie-jeebies as the "Warp" terminal that was heavily pushed (and then rebuked) on HN. I don't want to replace my file browser or terminal with a subscription service, full-stop. The most magical featureset on the market won't move my needle, but then again maybe I'm not the ideal customer for this kind of product.

  • 7sedam7 4 hours ago
    Cool, i have something similar that works locally on your machine: https://lasearch.app

    (uses custom algorithm instead of embeddings. Not as powerful in terms of contextual understanding, but enough for search and a LOT faster, plus minimal resource usage)

  • leekrasnow 13 hours ago
    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?

    • aabhay 13 hours ago
      Huh! Very cool. We do want to integrate MCP servers for sure. There are some amazing use cases — downloading and organizing email attachments, importing or exporting from other services, using citations/references. And because we have a desktop app we could support local MCP as well. But nothing immediate as far as timeline on our end.
  • milst 16 hours ago
    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)

  • redhale 17 hours ago
    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.

    • aabhay 17 hours ago
      We're adding that feature to be able to manually approve agentic actions! You can already revert things, as our file system is fully version controlled.
      • lumirth 14 hours ago
        Genuine question: why is that a feature that you have to add, instead of something foundational? Most folks, I'd wager, are sloppy about backups, so a level of manual control and oversight seems vital!
        • aabhay 14 hours ago
          Hm.. I think because the requirement for approval adds additional arms to the state machine. And the approval step is a message you send to the server that you don't want passed straight to the agent so it doesn't follow the rest of our pattern.

          Stupid, not good, unsatisfying reasons I agree!

  • heliosapollo 4 hours ago
    Hey, great launch and nice UI! Nitpick: The site allocates a large amount of VRAM on desktop, which takes forever to load. Please check.
  • trollbridge 10 hours ago
    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.
  • articulatepang 16 hours ago
    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.

    • aabhay 16 hours ago
      The file browsing is fully offline supported (as in the files get synced locally). We also allow text search offline, but smart search is not yet offline (we need to embed the search prompt), however, we would like to support fully offline use soon!
  • triyambakam 10 hours ago
    Seeing a loading spinner like that makes me feel like I'm back in the Flash days
  • elemdos 10 hours ago
    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?
  • saadatq 18 hours ago
    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.
    • aabhay 17 hours ago
      Haha, we might need to actually build this feature!
  • 101008 16 hours ago
    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.
    • aabhay 16 hours ago
      Yes it does! We support web links, PDFs, documents (with annotations!).
  • runako 10 hours ago
    Congrats on the launch!

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

  • cyrusradfar 17 hours ago
    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

    • aabhay 16 hours ago
      I remember Quicksilver! That's not what we do though. You're thinking of stuff like Alfred, Spotlight, Raycast, etc.
  • rahimnathwani 17 hours ago
    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?
    • aabhay 17 hours ago
      It handles both video frames and audio-in-video. So if you wanted, you could search for something that was said in a video and it'll find you the exact segment of it!

      We don't use transcription or any post processing. We simply embed the file. Our embedding has an additional inner dimension to support long duration content. So it's [N x D] where D is the embed dimension and N is an internal dimension that varies on the content.

  • mifydev 14 hours ago
    Great idea, but the landing page visuals is too cluttered, makes me want to have cursor for your website
    • aabhay 14 hours ago
      That's literally the point! <3
  • burnerzzzzz 2 hours ago
    Terrible, terrible website. Loading experience? Come on
  • gregjw 5 hours ago
    cursor for files, hmmmm
  • pgt 15 hours ago
    Greplin was just too early.
    • aabhay 14 hours ago
      There’s nothing more powerful than an idea whose time has come.
  • theoldgreybeard 18 hours ago
    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.

    • aabhay 18 hours ago
      Great user name for sure!
  • Fraaaank 18 hours ago
    I'd rather see a demo instead of a highly edited video with split second shots of the product.
    • dang 18 hours ago
      Isn't https://www.youtube.com/watch?v=RsqCySU4Ln0 (linked above) that?

      Here's what we always tell founders about demo videos: "What works well for HN is raw and direct, with zero production values. Skip any introductions and jump straight into showing your product doing what it does best. Voiceover is good, but no logos or music!"

      • Fraaaank 16 hours ago
        My bad, totally missed the link in the text post. I clicked on 'watch video' on the Poly website
        • dang 14 hours ago
          Ah good! I was wondering if I'd missed something.
    • aabhay 17 hours ago
      The video I provided was a raw, uncut, video. The editing is done by Screen Studio, which only does the "zoom" effect. But there's no studio magic there. I didn't speed anything up or cut out buggy bits or even do a retake!
  • michaelyin 10 hours ago
    [dead]
  • rockyterracotta 10 hours ago
    [dead]