Rendered at 12:16:51 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
zeroq 19 hours ago [-]
If you're still looking for a name let me suggest "hyper text".
It embodies the whole idea of having data, code and presentation at the same place.
If you're open for contributions I already have an idea for cascading styles system in mind.
altruios 18 hours ago [-]
Every turn of the wheel someone wants to make a new one.
Maybe one day someone will invent a rounder wheel.
doublerabbit 17 hours ago [-]
Personally I think we should move to heptagons, they're round enough.
The wheel is what I would call, passé.
smnrchrds 11 hours ago [-]
I disagree. Hexagons are the bestagons.
keeganpoppen 13 hours ago [-]
nah heptagons are passé; nowadays it’s all about nonagons. xD
altruios 16 hours ago [-]
Every day the wheel of society turns a little further off course.
Soon we'll be optimizing for minimizing the sides of a wheel (triangles are not the final form here...) /s
inopinatus 9 hours ago [-]
In this timeline I suggest favouring a style semantics and specification language.
[given what CSS has incrementally and inevitably become, it's my ever-firmer belief that DSSSL would've been the right choice in the first place]
noman-land 17 hours ago [-]
If HTML happened again except this time it was markdown, maybe more non-nerds would be able to use it? XML just looks gnarly.
NL807 13 hours ago [-]
Problem with the markdown approach the text will become rapidly ugly with hacks, non-standard annotations to enable same features as HTML.
FabianCarbonara 18 hours ago [-]
Ha, history does rhyme ;)
Happy if you reach out via mail!
heckintime 17 hours ago [-]
I think he's talking about CSS
0ing0b0ing0 14 hours ago [-]
[dead]
joelres 17 hours ago [-]
I quite like this! I've been incrementally building similar tooling for a project I've been working on, and I really appreciate the ideas here.
I think the key decision for someone implementing a flexible UI system like this is the required level of expressiveness. To me, the chief problem with having agents build custom html pages (as another comment suggested) is far too unconstrained. I've been working with a system of pre-registered blocks and callbacks that are very constrained. I quite like this as a middleground, though it may still be too dynamic for my use case. Will explore a bit more!
FabianCarbonara 16 hours ago [-]
Thanks! Really interesting to hear you're working on something similar.
You're right that the level of expressiveness is the key design decision. There's a real spectrum:
- pre-registered blocks (safe, predictable)
- code execution with a component library (middle ground)
- full arbitrary code (maximum flexibility).
My approach can slide along that spectrum: you could constrain the agent to only use a specific set of pre-imported components rather than writing arbitrary JSX. The mount() primitive and data flow patterns still work the same way, you just limit what the LLM is allowed to render.
Would love to hear what you learn if you explore it!
joelres 16 hours ago [-]
Will do! I'm using a JSON DSL currently, I wonder if there's a best choice for format that is both at the correct level of expressiveness and also easy enough for the LLM to generate in a valid way. I do think markdown has advantage of being very trivial for LLMs, but my current JSON blocks strategy might be better for more complex data.... will play around.
realrocker 16 hours ago [-]
The streamed execution idea is novel to me. Not sure what’s it significance ?
I have been working on something with a similar goal:
Add a video or a live demo, there's still too much friction on this readme.
Always Show then Ask.
FabianCarbonara 14 hours ago [-]
and I meant to say: tinkerdown looks pretty cool!
FabianCarbonara 16 hours ago [-]
[dead]
pbkhrv 16 hours ago [-]
Very cool. I'm imagining using this with Claude Code, allowing it to wire this up to MCP or to CLI commands somehow and using that whole system as an interactive dashboard for administering a kubernetes cluster or something like that - and the hypothetical first feature request is to be able to "freeze" one of these UI snippets and save it as some sort of a "view" that I can access later. Use case: it happens to build a particularly convenient way to do a bunch of calls to kubectl, parse results and present them in some interactive way - and I'd like to reuse that same widget later without explaining/iterating on it again.
FabianCarbonara 16 hours ago [-]
Exactly this!
Right now this uses React for Web but could also see it in the terminal via Ink.
And I love the "freeze" idea — maybe then you could even share the mini app.
pbkhrv 7 hours ago [-]
Did you see that Claude Code just came out with "channels" that allows for messages to be injected into the session/sent out by claude via hooks and MCP server [1]? I had CC code an integration between fenced and CC using channels and it actually worked - a little clunky since there is no streaming, but very interesting nevertheless.
The nice thing about standards is that you have so many to choose from
z3ugma 16 hours ago [-]
I will say I came upon this same design pattern to make all my chats into semantic Markdown that is backward compatible with markdown. I did:
````assistant
<Short Summary title>
gemini/3.1-pro - 20260319T050611Z
Response from the assistant
````
with a similar block for tool calling
This can be parsed semantically as part of the conversation
but also is rendered as regular Markdown code block when needed
Helps me keep AI chats on the filesystem, as a valid document, but also add some more semantic meaning atop of Markdown
eightysixfour 19 hours ago [-]
There seems to be a lot of movement in this direction, how do you feel about Markdown UI?
Markdown UI and my approach share the "markdown as the medium" insight, but they're fundamentally different bets:
Markdown UI is declarative — you embed predefined widget types in markdown. The LLM picks from a catalog. It's clean and safe, but limited to what the catalog supports.
My approach is code-based — the LLM writes executable TypeScript in markdown code fences, which runs on the server and can render any React UI. It also has server-side state, so the UI can do forms, callbacks, and streaming data — not just display widgets.
A2UI is Google's take — declarative JSON, tool-calling based, predefined component catalog. Clean and safe but constrained.
My approach is the opposite bet: full code execution instead of tool calls. The agent can build any React UI from scratch with the full power of code — including client-server data flow, callbacks, streaming data.
theturtletalks 18 hours ago [-]
OpenUI and JSON-render are some other players in this space.
I’m building an agentic commerce chat that uses MCP-UI and want to start using these new implementations instead of MCP-UI but can’t wrap my head around how button on click and actions work? MCP-UI allows onClick events to work since you’re “hard coding” the UI from the get-go vs relying on AI generating undertemistic JSON and turning that into UI that might be different on every use.
FabianCarbonara 18 hours ago [-]
In my approach, callbacks are first-class. The agent defines server-side functions and passes them to the UI:
When the user clicks the button, it invokes the server-side function. The callback fetches fresh data, updates state via reactive proxies, and the UI reflects it — all without triggering a new LLM turn.
So the UI is generated dynamically by the LLM, but the interactions are real server-side code, not just display. Forms work the same way — "await form.result" pauses execution until the user submits.
The article has a full walkthrough of the four data flow patterns (forms, live updates, streaming data, callbacks) with demos.
smahs 17 hours ago [-]
In an agentic loop, the model can keep calling multiple tools for each specialized artifact (like how claude webapp renders HTML/SVG artifacts within a single turn). Models are already trained for this (tested this approach with qwen 3.5 27B and it was able to follow claude's lead from the previous turns).
Lws803 16 hours ago [-]
I see potential to take over Notion's / Obsidian's business here. Imagine highly customizable notebooks people can generate on the fly with the right kind of UI they need. Compared to fixed blocks in Notion
rthrfrd 15 hours ago [-]
That’s what I’m building, along with the invisible unified data model underneath, that is needed to tie everything together. Always glad for feedback, reach out in my profile if it sounds interesting!
mncharity 12 hours ago [-]
Brainstorming, perhaps `<<named-block-code-transclusion>>`? It goes against the grain of "eval() line-by-line", even if it's handled ASAP. But it might relax the order constraint on codegen. Especially if the UI gets complex, or rendered on a "pane off to the side".
mncharity 20 minutes ago [-]
Oops - that's not transclusion. Merely literate programming tangles.
FabianCarbonara 6 hours ago [-]
[dead]
iusethemouse 18 hours ago [-]
There’s definitely a lot of merit to this idea, and the gifs in the article look impressive. My strong opinion is that there’s a lot more to (good) UIs than what an LLM will ever be able to bring (happy to be proven wrong in a few years…), but for utilitarian and on-the-fly UIs there’s definitely a lot of promise
FabianCarbonara 18 hours ago [-]
[dead]
18 hours ago [-]
4ndrewl 16 hours ago [-]
The bots that read the instruction and yet add the emoji to the _beginning_ of the PR title though. Even bigger red flag I guess?
nthypes 15 hours ago [-]
Why not MDX?
FabianCarbonara 14 hours ago [-]
The goal isn't really a better markdown format — it's bringing code execution and generative UI together. The code fences run on the server: calling APIs, processing data, doing agentic work. And they can also mount reactive UIs with full data flow between client, server, and LLM.
MDX is a compile-time format for static content. This is a runtime protocol where the LLM writes code that executes as it streams, and the UIs it creates stay connected to the server.
dominotw 16 hours ago [-]
would be nice if it wasnt just ui but other form like voice narration, sounds ect
23 hours ago [-]
kevindo9x19 16 hours ago [-]
[dead]
AiStockAgent62 14 hours ago [-]
[dead]
ayeteas54 11 hours ago [-]
[dead]
YANGBOKEE56 11 hours ago [-]
[dead]
ZakDavydov30 16 hours ago [-]
[dead]
wangmander 17 hours ago [-]
[flagged]
Retr0id 17 hours ago [-]
What's the going rate these days for decade-old HN accounts to repurpose as AI spambots?
It embodies the whole idea of having data, code and presentation at the same place.
If you're open for contributions I already have an idea for cascading styles system in mind.
Maybe one day someone will invent a rounder wheel.
The wheel is what I would call, passé.
Soon we'll be optimizing for minimizing the sides of a wheel (triangles are not the final form here...) /s
[given what CSS has incrementally and inevitably become, it's my ever-firmer belief that DSSSL would've been the right choice in the first place]
I think the key decision for someone implementing a flexible UI system like this is the required level of expressiveness. To me, the chief problem with having agents build custom html pages (as another comment suggested) is far too unconstrained. I've been working with a system of pre-registered blocks and callbacks that are very constrained. I quite like this as a middleground, though it may still be too dynamic for my use case. Will explore a bit more!
You're right that the level of expressiveness is the key design decision. There's a real spectrum:
- pre-registered blocks (safe, predictable)
- code execution with a component library (middle ground)
- full arbitrary code (maximum flexibility).
My approach can slide along that spectrum: you could constrain the agent to only use a specific set of pre-imported components rather than writing arbitrary JSX. The mount() primitive and data flow patterns still work the same way, you just limit what the LLM is allowed to render.
Would love to hear what you learn if you explore it!
I have been working on something with a similar goal:
https://github.com/livetemplate/tinkerdown
Always Show then Ask.
Right now this uses React for Web but could also see it in the terminal via Ink.
And I love the "freeze" idea — maybe then you could even share the mini app.
[1] https://code.claude.com/docs/en/channels-reference
[1] https://github.com/FabianKuebler/fenced/blob/main/packages/l...
````assistant
<Short Summary title>
gemini/3.1-pro - 20260319T050611Z
Response from the assistant
````
with a similar block for tool calling This can be parsed semantically as part of the conversation but also is rendered as regular Markdown code block when needed
Helps me keep AI chats on the filesystem, as a valid document, but also add some more semantic meaning atop of Markdown
https://markdown-ui.com/
Markdown UI is declarative — you embed predefined widget types in markdown. The LLM picks from a catalog. It's clean and safe, but limited to what the catalog supports.
My approach is code-based — the LLM writes executable TypeScript in markdown code fences, which runs on the server and can render any React UI. It also has server-side state, so the UI can do forms, callbacks, and streaming data — not just display widgets.
My approach is the opposite bet: full code execution instead of tool calls. The agent can build any React UI from scratch with the full power of code — including client-server data flow, callbacks, streaming data.
I’m building an agentic commerce chat that uses MCP-UI and want to start using these new implementations instead of MCP-UI but can’t wrap my head around how button on click and actions work? MCP-UI allows onClick events to work since you’re “hard coding” the UI from the get-go vs relying on AI generating undertemistic JSON and turning that into UI that might be different on every use.
So the UI is generated dynamically by the LLM, but the interactions are real server-side code, not just display. Forms work the same way — "await form.result" pauses execution until the user submits.
The article has a full walkthrough of the four data flow patterns (forms, live updates, streaming data, callbacks) with demos.
MDX is a compile-time format for static content. This is a runtime protocol where the LLM writes code that executes as it streams, and the UIs it creates stay connected to the server.