How to Set Up Chatbot UI Locally: Step-by-Step Guide

Getting Started with Chatbot UI

Chatbot UI is a Next.js application that uses Supabase for authentication and data storage. Setting it up locally is straightforward. This guide walks you through the entire process from cloning the repo to running your first conversation.

Prerequisites

Before you begin, ensure you have the following installed on your system:

Node.js (v18 or later) and npm
Docker — required for running Supabase locally
Git — for cloning the repository

Step 1: Clone the Repository

git clone https://github.com/mckaywrigley/chatbot-ui.git
cd chatbot-ui

Step 2: Install Dependencies

npm install

This installs all required packages including Next.js, Supabase client, Tailwind CSS, and other dependencies.

Step 3: Set Up Supabase Locally

Chatbot UI uses Supabase for its backend. You need Docker to run Supabase locally:

Make sure Docker is running on your machine
Start Supabase: npx supabase start
Copy the local Supabase credentials (anon key, service role key, and database URL) from the output

Step 4: Configure Environment Variables

Copy the example environment file and fill in the values:

cp .env.local.example .env.local

Edit .env.local and add your Supabase credentials and any API keys for the AI providers you want to use (OpenAI, Anthropic, etc.).

Step 5: Run the App

npm run dev

Your Chatbot UI instance will be available at http://localhost:3000. Open your browser, create an account, and start chatting with AI models right away.

Step 6: Apply Database Migrations

When you update Chatbot UI, run migrations to keep your database schema in sync:

npm run db-push

Connecting AI Providers

Chatbot UI supports 80+ AI models. Add your API keys in the settings panel:

OpenAI: Set your OpenAI API key in the settings
Anthropic: Add your Anthropic API key for Claude models
Google: Configure Google AI API key for Gemini models
Custom: Point to any OpenAI-compatible endpoint (Ollama, vLLM, etc.)

Conclusion

Setting up Chatbot UI locally takes about 15 minutes. Once running, you get a powerful, customizable AI chat interface with complete control over your data and model choices. It is an excellent starting point for building AI-powered applications or for personal use with multiple AI providers.