Generative UI: A rich, custom, visual interactive user experience for any prompt
Yaniv Leviathan, Google Fellow, Dani Valevski, Senior Staff Software Engineer, Vishnu Natchu, Principal Engineer, and Yossi Matias, Vice President & Head of Google Research

Awesome Generative UI - AI-Powered User Interface Generation Resources
Discover the best Generative UI resources: research papers, real-world cases, video tutorials, and open-source projects about AI-driven dynamic interface generation. Explore how LLMs like Gemini, Claude, and GPT are revolutionizing UI/UX design.
scn chat generative ui
Why Generative UI Is the New Frontier for Business Software
In an era where AI constructs UIs on the fly, discover how SAP is tapping generative UI to reimagine how works gets done.

Introducing Open Intelligent UI | The Open-Source Alternative to ChatGPT's Intelligent UI
Beautiful UI — Crafted primitives for AI-native interfaces
A small library of extremely crafted, copy-paste components for chat agents, thinking states, human-in-the-loop approvals, and everything agents need to talk to humans beautifully.
Reverse-engineering Claude's generative UI - then building it for the terminal
Extracting Anthropic's design system from a conversation export and rebuilding generative UI for the terminal.

The Generative Stack - The Phoenix Architecture
Trying to find the best tool or platform for generative software in 2026 is a mistake that could haunt you for decades
Macaron-A2UI: A Model for Generative UI in Personal Agents
As personal agents evolve to handle complex, user-centric tasks, static plain-text chat is rapidly becoming a bottleneck. Generative UI emerges as the necessary new interface layer, dynamically synthesizing the right controls, options, and state from the interaction context in real time. We present Macaron-A2UI, a model for Generative UI in personal agents. Our goal is to move beyond text-only interaction by enabling agents to generate natural language together with lightweight, executable UI actions for information collection, preference refinement, confirmation, and multi-goal organization. We build a large-scale Generative UI corpus from heterogeneous dialogue sources, introduce A2UI-Bench for controlled evaluation, and train 30B, 235B and 754B models with parameter-efficient LoRA-based supervised fine-tuning followed by reward-driven reinforcement learning. The best Macaron-A2UI model reaches 75.6 overall on A2UI-Bench without explicit schema hints, surpassing the strongest full-schema frontier baseline. We release the models, benchmark, and evaluation protocol to support future work on Generative UI for personal agents.

Generative UI – Paseo plugin
Paseo plugin: agents answer with charts, diagrams, maps, plans and forms rendered inline in the chat.

The Weird Death Of User Interfaces
Generative UI: The AI agent is the front end
In a new model for user interfaces, agents paint the screen with interactive UI components on demand. Let’s take a look.

What is Malleable Software Now | Bryan Min (02-27-2026)
Chat is a bad UI pattern for development tools
You don’t want to have a conversation with your computer, you want to build.
Using AI to create your own visualizations, interfaces, and going beyond “apps” bmannconsulting.com/notes/malleable-software/ Other terms: * Regenerative Software semble.so/url?id=https://aicoding.leafl…

Codex OS is now Mutable OS! | Mutable OS

Defining the common primitive — Tonk
A Malleable Diffuse | tokono.ma

OpenUI - The Open Standard for Generative UI

Software for One

Extensible Software in the age of LLMs | Jeremy Morrell