Secret instructions of artificial intelligence models
The system_prompts_leaks repository shared on GitHub brings together system prompts of artificial intelligence models of major technology companies such as Anthropic, OpenAI, Google and xAI. This collection provides a central resource for developers who want to examine the background configuration instructions and constraints of popular language models.
Updates
- October 5, 2026: Stars 65,657 → 68,956.
- September 13, 2026: Stars 61,968 → 65,657.
- August 2, 2026: Stars 44,809 → 61,968.
What you get
- Opportunity to examine background configurations of popular artificial intelligence models
- See the restrictions of models like Claude, ChatGPT and Gemini
- Access to system prompts given by technology companies to their models
Getting started
This tool does not require a software installation. By going to the System Prompts Leaks repository on GitHub, you can click on the folder of the artificial intelligence model or company you want to examine and read the relevant system prompt files directly from your browser.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-22: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.