About
mdocUI is an alpha Generative UI library that asks LLMs to write normal Markdown with inline Markdoc-style component tags. The project is still early, but it is useful because it represents a distinct approach from JSON trees and tool calls: prose and interactive components can share the same stream while the renderer handles validation, placeholders, error boundaries, and custom component mapping.
Summary
Why Track mdocUI:
1. Markdown-native generation: Keeps prose and UI components in one LLM-friendly output format
2. Markdoc tag syntax: Offers a compact alternative to JSON-heavy generated interface specs
3. Streaming UX focus: Includes placeholders, streaming animations, and component merging for partial output
4. Validation and boundaries: Explicitly addresses malformed generated props and runtime rendering failures
5. Curated cautiously: Worth tracking as an emerging pattern, even if it is not yet as mature as OpenUI or json-render
1. Markdown-native generation: Keeps prose and UI components in one LLM-friendly output format
2. Markdoc tag syntax: Offers a compact alternative to JSON-heavy generated interface specs
3. Streaming UX focus: Includes placeholders, streaming animations, and component merging for partial output
4. Validation and boundaries: Explicitly addresses malformed generated props and runtime rendering failures
5. Curated cautiously: Worth tracking as an emerging pattern, even if it is not yet as mature as OpenUI or json-render
Tags
mdocuimarkdocmarkdownstreamingopen-source