LobeHub is a platform for organizing AI agents into always-on teams that can be hired, scheduled, and reviewed from one place.
f/prompts.chat
A community-curated open-source library of prompts for AI chat models, with a website, CSV/Hugging Face datasets, CLI and MCP server integration.
- Stars
- 173,623
- Forks
- 22,213
- Open issues
- 90
- Last commit
- 9 hours ago
What is it?
prompts.chat is a collection of prompts for AI chat assistants such as ChatGPT, Claude, and Gemini. Users can browse, share, and collect prompts on the prompts.chat website, and the same content is published as a CSV file, a Markdown list, and a Hugging Face dataset. The project was formerly known as Awesome ChatGPT Prompts.
Beyond the public library, the project offers a command-line tool (npx prompts.chat), a Claude Code plugin, and an MCP server that AI tools can connect to for retrieving prompts. It also includes an interactive guide to prompt engineering and a game-based lesson for children aged 8 to 14.
The application is built with Next.js and TypeScript and can be self-hosted with a setup wizard that configures branding, themes, and authentication through GitHub, Google, or Azure AD. It uses PostgreSQL as its database. Prompt content is released under CC0 and the source code under MIT.
Key features
- 01Browse and submit prompts on the prompts.chat website
- 02Export the library as CSV, Markdown, or a Hugging Face dataset
- 03Command-line access via npx prompts.chat
- 04MCP server for connecting AI tools to the prompt library
- 05Self-hosted deployment with GitHub, Google, or Azure AD login
Use cases
- Finding ready-made prompts for writing, coding, or analysis tasks
- Giving an AI assistant access to a shared prompt library via MCP
- Running a private prompt library for an organization
- Teaching students or children the basics of prompt writing
Quick start
- 1
Create a new self-hosted prompt library
npx prompts.chat new my-prompt-library - 2
Enter the new project folder
cd my-prompt-library
Things to know
- Self-hosting requires a PostgreSQL database, and the README recommends a hosted one such as Neon.
- Setting up your own instance includes a setup wizard for branding, theme, and authentication (GitHub, Google, or Azure AD).
Topics
FAQ
- What is prompts.chat?
- A community-curated open-source library of prompts for AI chat models, with a website, CSV/Hugging Face datasets, CLI and MCP server integration. prompts.chat is a collection of prompts for AI chat assistants such as ChatGPT, Claude, and Gemini. Users can browse, share, and collect prompts on the prompts.chat website, and the same content is published as a CSV file, a Markdown list, and a Hugging Face dataset. The project was formerly known as Awesome ChatGPT Prompts.
- Is prompts.chat free to use? What license does it have?
- prompts.chat is open source under the Other license. Check the license terms before using it in commercial products.
- Is prompts.chat still maintained?
- Actively maintained. The last commit to prompts.chat was on Oct 20, 2026.
- What can I use prompts.chat for?
- Finding ready-made prompts for writing, coding, or analysis tasks Giving an AI assistant access to a shared prompt library via MCP Running a private prompt library for an organization Teaching students or children the basics of prompt writing
- How do I install prompts.chat?
- Create a new self-hosted prompt library: npx prompts.chat new my-prompt-library Enter the new project folder: cd my-prompt-library
- Where can I get prompts.chat?
- The source code and installation instructions are on GitHub: https://github.com/f/prompts.chat
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A TypeScript framework for building AI agents and LLM-powered applications, with workflows, tools, memory, MCP servers, and evals.
An SDK for building AI agents and multi-agent systems in Python, .NET and Java, with model, plugin and vector database integrations.
An open-source AI coding agent that runs in your terminal, with companion desktop, web, editor, and chat interfaces.
A provider-agnostic TypeScript toolkit for building AI-powered applications and agents with React, Next.js, Svelte, Vue and Node.js.
Agent-native memory infrastructure that turns LLM agent conversations and execution into persistent, structured memory for Python and TypeScript apps.