<h1 align="center">
<a href="https://prompts.chat">
- **Curated Prompt Library** — Access 100+ high-quality, community-tested prompts for ChatGPT, Claude, Gemini, Llama, Mistral, and other AI models
Sign in to like and favorite skills
Requirements:
This guide explains how to deploy prompts.chat on your own private server for enhanced privacy and customization.
Create a
.env file based on .env.example:
# Database DATABASE_URL="postgresql://user:password@localhost:5432/prompts" # Authentication (choose one provider) # GitHub OAuth AUTH_GITHUB_ID="your-github-client-id" AUTH_GITHUB_SECRET="your-github-client-secret" # Or Google OAuth AUTH_GOOGLE_ID="your-google-client-id" AUTH_GOOGLE_SECRET="your-google-client-secret" # NextAuth AUTH_SECRET="generate-a-random-secret" # Optional: AI-powered semantic search OPENAI_API_KEY="your-openai-api-key"
The fastest way to create a new prompts.chat instance:
npx prompts.chat new my-prompt-library cd my-prompt-library
This will:
Clone the repository
git clone https://github.com/f/awesome-chatgpt-prompts.git cd awesome-chatgpt-prompts
Install dependencies
npm install
Run the interactive setup wizard
npm run setup
This will guide you through configuring:
Configure environment variables
cp .env.example .env # Edit .env with your database and auth credentials
Run database migrations
npm run db:migrate
Seed initial data (optional)
npm run db:seed
Start the development server
npm run dev
Build for production
npm run build npm run start
The setup wizard (
npm run setup) generates prompts.config.ts automatically. You can also manually edit it:
// Set to true to use your own branding instead of prompts.chat branding const useCloneBranding = true; export default defineConfig({ // Branding branding: { name: "Your Prompt Library", logo: "/your-logo.svg", logoDark: "/your-logo-dark.svg", description: "Your custom description", }, // Theme theme: { radius: "sm", // "none" | "sm" | "md" | "lg" variant: "default", // "flat" | "default" | "brutal" colors: { primary: "#6366f1", }, }, // Authentication auth: { provider: "github", // "credentials" | "github" | "google" | "azure" allowRegistration: true, }, // Features features: { privatePrompts: true, changeRequests: true, categories: true, tags: true, aiSearch: false, // Requires OPENAI_API_KEY }, // Homepage homepage: { useCloneBranding, // Use your branding on homepage achievements: { enabled: !useCloneBranding, // Hide prompts.chat achievements }, sponsors: { enabled: !useCloneBranding, // Hide prompts.chat sponsors }, }, // Internationalization i18n: { locales: ["en", "es", "ja", "tr", "zh"], defaultLocale: "en", }, });
When
useCloneBranding is set to true, the homepage will:
This is ideal for organizations that want to deploy their own white-labeled prompt library without prompts.chat branding.
For issues and questions, please open a GitHub Issue.