a2ui

A language like E seems about the right level for a simple user-friendly programmatic layer wrapping applications, i.e. enable the users to ask a natural language question or build a simple GUI layer which has question actions, with results displayed in the custom GUI or exported as files (CSV or spreadsheets etc). I expect we'll see a blurring of the web app GUI, allowing users and LLMs to augment the GUI. There are a few tools offering the GUI part of that; I had read about Google A2UI, and search finds more : Anthropic Claude Rivet, CopilotKit (uses AG-UI Standard), Chainlit (Python UI framework), Vercel AI SDK (React Server Components stream from the LLM to the client). URLs : https://github.com/google/A2UI, https://fast.io/resources/best-ui-frameworks-ai-agents/, https://rivet.ironcladapp.com/ and https://techcommunity.microsoft.com

A comprehensive developer tutorial covering A2UI – a declarative protocol for AI agents to generate native UIs via JSON messages. Technical highlights: - Adjacency list model (flat component list with ID refs) instead of nested trees – designed for LLM streaming and incremental generation - Data binding via JSON Pointer paths (RFC 6901) for reactive updates without component regeneration - Three-layer architecture: UI structure (surfaceUpdate), application state (dataModelUpdate), client rendering - Transport-agnostic: works with A2A Protocol, SSE, WebSockets, or AG UI The tutorial includes: - Step-by-step agent setup with Python ADK (code examples included) - Client implementation guides for Lit, Angular, and Flutter renderers - Message processing & state management implementation checklist - Custom component catalog creation -

I tell you what, I'll add Svelte/Kit to the list we want to target: https://github.com/google/A2UI/pull/352 Thanks for the recommendation.