Setup

Installing the Devcn UI Design Registry is straightforward and can be done in a couple of ways. You can use the dedicated Devcn UI CLI for the fastest setup, or integrate via the standard shadcn/ui CLI if you've already adopted shadcn's workflow.

This guide will walk you through the prerequisites and the installation steps for both methods, complete with example commands. By the end, you'll have specialized AI chatbot components ready to use in your project.

Prerequisites

Before installing Devcn UI Design Registry, make sure your environment meets the following requirements:

• Node.js, version 18 or later
• A React project, version 18 or later
• shadcn/ui installed in your project. In practice, this means you have already initialized shadcn in your project (for example by running npx shadcn@latest init and configuring Tailwind CSS). Devcn UI Design Registry currently supports only the CSS Variables mode of shadcn/ui for theming.

Installing Chatbot Components

You can install Devcn UI Design Registry components using either the Devcn UI CLI or the shadcn/ui CLI. Both achieve the same result: adding the selected component's code and any needed dependencies to your project. For example, to install the AI Conversation component, you would run:

devcn-uishadcn

npx devcn-ui@latest add ai-conversation

The CLI will download the component's code and integrate it into your project's directory (usually under your components folder). By default, Design Registry components are added to the @/components/ui/devcn-ui/ directory (or whatever folder you've configured in your shadcn components settings).

For instance, the command above will place the AI Conversation component files in @/components/ui/devcn-ui/ai-conversation/. The CLI also ensures that any required dependencies (for example, specific headless libraries a component might need) are installed automatically.

Key Chatbot Components

The Design Registry includes several specialized components for building AI chatbot interfaces:

• AI Conversation - A complete conversation container with messages, typing indicators, and user input
• Message Handler - Components for rendering different message types (text, code, images)
• Reasoning Visualizer - Shows AI reasoning steps and thought processes
• Source Attribution - Displays citations and references for AI responses
• System Prompt Editor - Interface for configuring AI behavior

To install any of these components, use the same CLI command pattern:

npx devcn-ui add <component-name>