Overview
System Prompts Leaks is a public GitHub repository that collects the verbatim system prompts behind widely used chatbots and AI coding agents. The project describes itself as "The full verbatim system prompts behind the most popular chatbots in the world. Carefully curated and complete." The repository is organized into folders by vendor, including Anthropic, Cursor, DeepSeek, GLM, Google, Kimi, Meta, Microsoft, Mistral, Notion, OpenAI, OpenCode, Perplexity, Pi, Qwen, and xAI.
Its coverage spans multiple model families and products. The repository description lists "Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code." It also documents OpenAI models such as ChatGPT and Codex, Google models such as Gemini, and xAI models such as Grok, alongside entries for Cursor and Kimi. The README includes tables of recent additions with dates and links to individual prompt files.
The repository is maintained as an open, community-contributed collection. The README states, "Feel free to open up a PR or get in contact if you got a different result." It is published under a CC0-1.0 license and has accumulated 807 commits, 68.6k stars, and 11.2k forks.
The collected prompts have been used as source material by outside organizations. According to the README, "The Washington Post built its interactive story on prompts from this repo," and "CEPS' AI World built a live data dashboard from this repo's files."
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Researchers use the repository to examine the hidden rules behind AI systems.
- News organizations use the collected prompts as source material for interactive stories.
- Analysts use the repository's files to build live data dashboards.
- Developers use the repository to compare documented system prompts across model providers.
- Contributors use pull requests to submit differing results they have captured.
Features
AI assistant
Natural language interface
Workflow automation
Reviews
No reviews yet. Be the first to share your experience!