I've been building SmallDocs [1], a fairly fully functional office suite (text, formatting, presentations, spreadsheets) which is based in markdown (and mainly written by agents).
Given my experience building this, I think the idea of "a truly independent document":
> one that displays identically on any system, in any country, for any user, regardless of the software used
Will be very difficult to achieve in practice.
Building software is an expression of opinions. And one of the main drivers of building an app is to innovate or improve the user experience vs. what exists today. These things combine to result in new features, and new features breaks the open standard.
If I wanted to build a new Excel, I might want to add something to spreadsheets which a basic open source reader cannot, or even Excel itself, might not be able to handle.
With SmallDocs, I built on the standard rendering of markdown, but then added a bunch of properties which traditional markdown renders would ignore.
~~~slide
grid 100 56.25 bg=#0b1220
r 6 9 82 4 text=caption color=#fbbf24 align=left | LAUNCH REVIEW - Q2 2026
r 6 18 84 16 text=title color=#f8fafc align=left | Atlas 2.0 shipped to every customer
r 6 37 78 6 text=subtitle color=#94a3b8 align=left | What changed, what it cost, and what we learned
l 6 47 24 47 stroke=#fbbf24 strokeWidth=0.2
~~~
All this means SmallDocs markdown files only render correctly through our rendering engine - but this enables me to add something new to an existing document format.
Claude can right great code, but it’ll throw comments into the code about why we chose this approach instead of the random one I discussed with it - when the comment is of no use to a future developer.
It points at some sort of theory of mind problem in LLMs imo.
The charts are very nice, and I think the visualisation layer for LLMs is a very interesting problem.
I’ve been building https://smalldocs.org for this exact reason. It’s an office suite for AI agents - but my main use case is giving a cli based LLM the canvas to express itself - charts, mermaid diagrams, etc. I’ve extended it a bit further to be a format for all types of work so the agent can embed slides and spreadsheets in a document.
I created https://smalldocs.org to help with this. After installing you can tell your agent to "sdoc me a mermaid diagram of X flow" or "sdoc me a visual architecture of this repo" or something, and it handles it nicely (imo!).
I posted the same thing below, but I’m open for feedback on the license. I’ve put a lot of work in and I think there is a commercial pathway forward for the product. I don’t want to let someone else - who might be more experienced re commercialisation - take everything I’ve done and build a business with it (I’d really like to do that myself), so wasn’t sure what license to use as MIT didn’t feel right to me at the moment. But open for feedback/maybe I’m being too short sighted…
I’m open for feedback on the license. As you say/notice, I’ve put a lot of work in and I think there is a commercial pathway forward for the product. I don’t want to let someone else - who might be more experienced - take everything I’ve done and build a business with it (I’d really like to do that myself), so wasn’t sure what license to use as MIT didn’t feel right to me at the moment. But open for feedback/maybe I’m being too short sighted…
Thanks, please could you email me at [email protected]. I’m trying to learn how to make this a better experience for teams, so would love to work with you guys to optimise the experience.
Multiple agents could write to the doc locally, but for the moment it’s not predominantly could based (only short links). I think I will build a cloud first version/offering/config soon