Incrementally parsing LLM Markdown streams on server/client

Most AI chat applications (such as ChatGPT or Claude) stream their responses to the client as markdown text. As each new chunk of text arrives, the front end typically re-parses the entire markdown document to render the updated message. This works, but it can quickly slow down the UI for long responses.

I’ve been obsessing over ways to make this more efficient, so I wrote a markdown parser that can parse streaming markdown (semi) incrementally. Instead of re-processing the whole document each time, it only parses what’s new, processing each line only once. Block‑level nodes are buffered until they’re complete (for example, once a paragraph is done and won’t be extended by more text).

The API is intentionally simple, but there’s an experimental mode that surfaces all finalized nodes (both top‑level and nested), so you can take more control over how and when you render.

Here’s a demo if you’d like to see it in action:

https://markdownparser.vercel.app/

I’ve spent a lot of time thinking about this problem, so if you’re working on similar issues, I'd love to chat.

I’ve been looking for this exactly. For container nodes, such as blockquote or lists, do you wait until all children nodes are fully finalized or is it possible to also parse a container block node incrementally?