f/prompts.chat

f/prompts.chat has 176,594 GitHub stars and 22,524 forks. GitHot measured +978 in 7 days and +2,082 in 15 days. Last checked 2026-11-09 04:12 UTC. Last push 2026-11-01.

这些数字如何统计

前身为 Awesome ChatGPT Prompts。分享、发现并收集来自社区的提示词。自由且开源，可为你的组织自行部署，并完全保护隐私。

176,594 星标 22,524 forks

实测星标增长

24小时: 更新延迟
7天: +978
15天: +2,082
1个月: 正在收集历史

各周期内的星标净变化，周期相互重叠，并非每日新增。缺失的测量保持空白。星标代表关注度，不代表软件质量。

README.md

原文

prompts.chat

The world's largest open-source prompt library for AI
_{Works with ChatGPT, Claude, Gemini, Llama, Mistral, and more}

_{formerly known as Awesome ChatGPT Prompts}

🌐 Browse Prompts • 📖 Read the Book • 📄 View on GitHub • 🚀 Self-Host

_{🏆 Featured in Forbes ·
🎓 Referenced by Harvard, Columbia ·
📄 40+ academic citations ·
❤️ Most liked dataset on Hugging Face

⭐ 143k+ GitHub stars ·
🏅 GitHub Staff Pick ·
🚀 First prompt library (Dec 2022)}

_{Loved by AI pioneers:}
_{Greg Brockman (OpenAI Co-Founder) ·
Wojciech Zaremba (OpenAI Co-Founder) ·
Clement Delangue (Hugging Face CEO) ·
Thomas Dohmke (Former GitHub CEO)}

What is this?

A curated collection of prompts for AI chat models. Originally created for ChatGPT, these prompts work great with any modern AI assistant.

Browse Prompts	Data Formats
prompts.chat	prompts.csv
PROMPTS.md	Hugging Face Dataset

Want to contribute? Add prompts at prompts.chat/prompts/new — they sync here automatically.

🤖 Bots & Bot Teams

prompts.chat also hosts always-on AI agents and the teams they work in.

Bots — Share and discover bots (OpenClaw, Hermes Agent, Grok Bot, and more). Each bot page has install instructions per platform, the computer it needs (cloud, the user's computer, or both), "Better together with" pairings, upvotes, comments, and change requests.
Bot Teams — Groups of bots that hand work off to each other, shown as an interactive graph. Upvote a team or install every bot in it at once. Featured teams appear on the homepage, and Teams is in the top navigation.
Profiles — User profiles have Bots and Teams tabs with counts.
Moderation — Bots and teams can be unlisted to hide them from public listings.

Teams are also available as JSON: GET /api/teams?sort=newest (also oldest or upvotes, paginated with page and perPage).

📖 The Interactive Book of Prompting

Learn prompt engineering with our free, interactive guide — 30+ chapters covering everything from basics to advanced techniques like chain-of-thought reasoning, few-shot learning, and AI agents. Newer chapters cover going from prompt to team (prompt, skill, agent, bot, team), always-on bots, agent teams, computer use, and who may give a bot work — available in 17 languages.

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.

Start Playing →

🚀 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.

🔌 Integrations

CLI

npx prompts.chat

Claude Code Plugin

/plugin marketplace add f/prompts.chat
/plugin install [email protected]

📖 Plugin Documentation

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"]
    }
  }
}

Tools cover prompts and skills, plus bots (search_bots, get_bot, save_bot, list_my_bots, get_my_bot) and bot teams (list_teams, get_team, save_team).

📖 MCP Documentation

💖 Sponsors

_{Built with Windsurf and Devin}
Become a Sponsor →

👥 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.