matchcn matches UI components with a Jev classifier
The author indexed 1,783 components across 9 shadcn registries and uses a Jev classifier to match them, so coding agents search before generating and get a confidence score with each match.
Built @matchcndev because I think coding agents should search before they generate. You describe the UI in plain language, and matchcn finds the closest component, explains why it matched, and gives you the install command. No guessing component names. No jumping between libraries. No rebuilding something that already exists. Right now I’m indexing 1,783 components across 9 shadcn registries, classified across purpose, motion, density, interaction, data, and decoration. The classification and matching layer is powered by Jev through classifier, so every decision comes with confidence instead of just generated text. The goal is simple: make component discovery agent-native, so coding agents can reliably find and install the right existing component for the UI they’re building. Still early, but this is the direction I’m pushing.