Live data from Hacker News

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

news.ycombinator.com

41–50 of 75 posts

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

#41
post #39
post #22

Earlier quoted context omitted.

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.

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!

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!

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

#42

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 th…

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).

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

#43
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?

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

#44

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…

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.

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

#45
post #11

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 petab…

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 bui…

“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.
Post reply on HN