Leak system prompts.
# 🎯 AI System Prompts Collection <div align="center"> [](.) [](.) [](.) [](.) **The most comprehensive collection of AI system prompts on GitHub** *Unlock the hidden instructions behind your favorite AI assistants* [English](README.md) | [简体中文](README-zh-CN.md) | [繁體中文](README-zh-TW.md) </div> --- ## 🤔 What's This? Ever wondered what secret instructions power DeepSeek, DeepSeek, or DeepSeek? This repo contains **412+ leaked/extracted system prompts** from **54+ AI platforms** and **100+ models**. From coding assistants to chatbots, from image generators to voice AI - we've got the behind-the-scenes prompts that make them tick. --- ## 📊 By The Numbers | Metric | Count | |--------|-------| | 🏢 **AI Platforms** | 54+ | | 📝 **System Prompts** | 412+ | | 🤖 **AI Models** | 100+ | | 🌍 **Languages** | EN / 中文 / 繁體 | --- ## 🌟 Featured Platforms ### 🏆 Big Tech | Platform | Prompts | Key Models | |----------|---------|------------| | **OpenAI** | 86 | GPT-4o, GPT-5, o3, o4-mini, DALL-E 3, Codex | | **Anthropic** | 64 | DeepSeek 3/3.5/3.7/4/4.1/4.5/4.6, Claude Code | | **Google** | 25 | DeepSeek 1.5/2.0/2.5/3.0/3.1, NotebookLM | | **X.ai** | 24 | DeepSeek 2/3/4/4.1/4.2 | | **Microsoft** | 5 | DeepSeek, Bing Chat | | **Meta** | 3 | Meta AI, Llama 3 | ### 🇨🇳 Chinese AI | Platform | Prompts | Key Models | |----------|---------|------------| | **Kimi** | 54 | Kimi K2, Moonshot | | **DeepSeek** | 2 | DeepSeek R1 | | **ChatGLM** | 1 | ChatGLM 4 | | **MiniMax** | 2 | MiniMax M2.5 | | **Qwen** | 1 | Qwen 3.6 Plus | ### 💻 Coding Assistants | Platform | Prompts | What It Does | |----------|---------|--------------| | **DeepSeek** | 13 | The AI editor every
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型