prompts.chat
prompts.chat is a large, community-curated collection of ready-to-use prompt examples for AI chat models (originally ChatGPT), packaged as a browsable site, downloadable datasets, a self-hostable prompt library, and integrations like a CLI, Claude Code plugin, and MCP server.
Embed badge
[](https://opensources.dev/resource/promptschat)CC0-1.0Public domain / no rights reserved — use freely, no attribution required.View license →
Production readiness
4/5- Actively maintainedCommits in the last 6 months
- No known vulnerabilitiesNot yet scanned
- Clear, usable licenseCC0-1.0 (public domain)
- Proven adoptionWidely used
- Has documentationDocumentation indexed
Our analysis
A curated, public-domain collection of prompt examples for AI assistants, distributed via a web app, CSV/Markdown/Hugging Face datasets, and deployable as a self-hosted prompt library with CLI and MCP integrations.
When to use prompts.chat
Use it to discover proven starter prompts, learn prompt engineering from its interactive book, pull prompts programmatically into AI tooling via the MCP server, or stand up an internal branded prompt library for a team.
When not to
It is not a programmatic prompt-management framework with versioning, evaluation, or A/B testing in your own code — for that, reach for LangSmith, PromptLayer, or a templating library. It is also overkill if you just want a single static list of prompts.
Strengths
- Enormous, well-known prompt collection with very high adoption
- Multiple consumption formats (web, CSV, Markdown, Hugging Face dataset)
- Prompt content released under CC0 public domain, removing licensing friction
- First-class integrations: CLI, Claude Code plugin, and hosted/local MCP server
- Self-hosting path with auth, theming, and PostgreSQL support
Trade-offs
- Prompt quality is community-driven and uneven; many entries are generic personas
- Not a structured prompt-engineering or evaluation toolkit — no versioning/testing primitives
- Self-hosting pulls in a full Next.js-style app and PostgreSQL, which is heavyweight for simple use
- Many prompts are tuned for older ChatGPT behavior and may need adaptation
Maturity
Extremely popular (one of the most-starred AI repos) and actively maintained, with an expanding ecosystem of integrations, datasets, and an interactive book. Dual MIT/CC0 licensing is clear and permissive.
What is this?
A curated collection of prompt examples for AI chat models. Originally created for ChatGPT, these prompts work great with any modern AI assistant.
Browse PromptsData Formatsprompts.chatprompts.csvPROMPTS.mdHugging Face Dataset
Want to contribute? Add prompts at prompts.chat/prompts/new — they sync here automatically.
📖 The Interactive Book of Prompting
Learn prompt engineering with our free, interactive guide — 25+ chapters covering everything from basics to advanced techniques like chain-of-thought reasoning, few-shot learning, and AI agents.
Start Reading → (Source: https://github.com/f/prompts.chat/tree/main/src/content/book)
🎮 Prompting for Kids
An interactive, game-based adventure to teach children (ages 8-14) how to communicate with AI through fun puzzles and stories.
🚀 Self-Hosting
Deploy your own private prompt library with custom branding, themes, and authentication.
Quick Start:
npx prompts.chat new my-prompt-library
cd my-prompt-library
Manual Setup:
git clone https://github.com/f/prompts.chat.git
cd prompts.chat
npm install && npm run setup
The setup wizard configures branding, theme, authentication (GitHub/Google/Azure AD), and features.
Recommended database: prompts.chat uses PostgreSQL. For a hosted database, we recommend Neon.
📖 Full Self-Hosting Guide • 🐳 Docker Guide
🔌 Integrations
CLI
npx prompts.chat
Claude Code Plugin
/plugin marketplace add f/prompts.chat
/plugin install prompts.chat@prompts.chat
MCP Server
Use prompts.chat as an MCP server in your AI tools.
Remote (recommended):
{
"mcpServers": {
"prompts.chat": {
"url": "https://prompts.chat/api/mcp"
}
}
}
Local:
{
"mcpServers": {
"prompts.chat": {
"command": "npx",
"args": ["-y", "prompts.chat", "mcp"]
}
}
}
💖 Sponsors
👥 Contributors
📜 License
This project is dual-licensed:
Source code and site-authored content is licensed under the MIT License, including the interactive book content in
src/content/book.Prompt content and data (prompts.csv, PROMPTS.md, user-submitted prompts) is dedicated to the public domain under CC0 1.0 Universal.
See LICENSE for details.