MUP – Interactive UI inside LLM chat, so anyone can use agentic AI

Name: MUP – Interactive UI inside LLM chat, so anyone can use agentic AI
Availability: InStock
Author: Ricky_Tsou

by Ricky_Tsou·Mar 17, 2026·1 point·2 comments

Visit Project View on HN

AI Analysis

●●●BangerZero to OneBig BrainShip It

Single HTML files become bidirectional UI—users click, LLMs call, both see results instantly.

Strengths

•One function, two entry points—user clicks and LLM tool calls share the same code path.
•No build step or SDK required—just a manifest and plain HTML file.
•Demo videos show genuine LLM-UI collaboration, not just static embedding.

Weaknesses

•No production host integrations yet—works with PoC host, not ChatGPT or Claude directly.
•Protocol adoption depends on LLM platforms supporting the manifest format.

Post Description

Agentic AI is powerful, but most people never experience it — it's trapped behind text commands and dev tools.

MUP (Model UI Protocol) lets you embed interactive UI directly in LLM chat. Each MUP is just a single .html file. The same functions can be triggered by the user (clicking a button) or by the LLM (function call). Both sides see each other's actions in real time.

The repo includes a PoC host and 9 example MUPs. Demo mode lets you interact with the UI side without an API key. Add an OpenAI key to see full LLM-UI collaboration.

Demo videos in the README show things like: drawing pixel art then charting its colors, a camera that captures a scene and the LLM recreates it, making beats on a drum machine with the LLM.

I'd love feedback on the protocol design.