I built a similar system for php and I can tell you what is the smart thing here: accessing data using tools.
Of course tool calling and MCP are not new. But the smart thing is that by defining the tools in the context of an authenticated request, one can easily enforce the security policy of the monolith.
In my case (we will maybe write a blog post one day), it's even neater as the agent is coded in Python so the php app talks with Python through local HTTP (we are thinking about building a central micro service) and the tool calls are encoded as JSON RPC, and yet it works.
I had to do something similar. Ruby is awful and very immature compared to python, so I "outsourced" the machine learning / LLM interaction to python. The rails service talks to it through grpc / protobuf and it works wonderfully.
While I agree that the training/learning ecosystem is pretty heavily centered in Python, going from that to "Ruby is awful" seems like a very drastic jump, especially if we are talking about the LLM interaction only.
I probably wouldn't write a training system in Ruby (not because it's not doable, just because it's not a good use of time to rewrite stuff that is already available in python ecosystem)... but hooking up a Ruby system up to LLM's for interaction is eminently doable with very little effort.
I am assuming your situation had some specific constraints that made it harder, but it would be nice to understand what they were - right now your comment describes a more complicated solution and I am curious why you needed it.
While I agree that Python is where most of the implementation action is, one of the great things about building applications with LLMs is that almost all API providers offer a rich REST interface, and I have found it simple to use LLM services in Haskel, various Lisp languages, etc. It is nice having very old code in various languages and be able to add new functionality with LLMs.
I think the hardest for this kind of projects is to keep it active. Environments with a "global state" like this (everyone shares the same website) are ultimately limited to surges (seasonal events like Magnus vs The World or a single game of Twitch plays Pokemon) or to a recurring flow of new people.
Maybe having multiple "realms", so that there are not too many people in a single realm in case of virality, and the ability for people to spawn their own realms would be nice (think skribbl or Among Us) but then it would kind of be a Lovable and cost a lot to host the LLM. But since the html code is open source, local LLMs (like Gemini Nano embedded in Chrome) could theoretically do the editing. In that case, the web page should definitely be marked as even unsafer! I wonder how one could avoid the red flag of Chrome for pages that are deliberately made to host collaborative crap.
I don't get why one wouldn't just use webworkers to run the simulation instead, thus making the game fully executable in a web browser.
If deno has some perks during development, there must be a way to replace websocket with some other transport that works with webworkers for "production" builds.
Any recurrence that holds on the matrix also holds on each individual element (and vice versa, in that a recurrence holds on the matrix just in case it holds on every individual element).
Very interesting in the context where major porn websites blocked access in France (now reverted) and in some US states as a response to age verification regulations that were too difficult to implement without compromising user experience and privacy.
Interesting. My process is similar, although based on the GTD method (for example with an Inbox list) and using Trello for implementation (I get syncing, task level notes, multimedia, item drag and drop, etc)
Nice! Recently I had the need for pdf censoring, aka not adding black rectangles but actually removing the content underneath and I still haven't found a suitable tool. Any recommendation? Or even python library to do it?
I developed another tool pdfredactoronline.com that does this. Full redaction/removal of content, not just blacking out text. I didn't include it in this tool for now due to the APGL license of the library that enables the redaction, but since something fully in the browser is kinda open source already, I'll see if I can comply with the license while including it in BreezePDF
You can open PDF in LibreOffice Writer, just make sure to select "PDF - Portable Document Format (writer)" in the file selection dialog. This is very important, if you don't do that, the file will be opened in LibreOffice Draw instead of Writer.
Of course tool calling and MCP are not new. But the smart thing is that by defining the tools in the context of an authenticated request, one can easily enforce the security policy of the monolith.
In my case (we will maybe write a blog post one day), it's even neater as the agent is coded in Python so the php app talks with Python through local HTTP (we are thinking about building a central micro service) and the tool calls are encoded as JSON RPC, and yet it works.