jujumilk3/leaked-system-prompts

Collection of leaked system prompts

57
/ 100
Established

This project helps AI researchers, ethicists, and curious individuals understand the hidden instructions guiding large language models (LLMs). It provides a collection of 'system prompts' – the secret initial directives given to popular AI chatbots – allowing you to see what an AI is told behind the scenes before it ever interacts with a user. This is useful for analyzing AI behavior, uncovering potential biases, or learning how to better prompt your own models.

14,260 stars. Actively maintained with 13 commits in the last 30 days.

Use this if you are studying AI model behavior, investigating AI safety, or want to gain insight into how commercial LLMs are internally configured.

Not ideal if you are looking for a tool to develop or fine-tune your own AI models, or if you need general information about AI prompting.

AI-ethics AI-research prompt-engineering-insights LLM-analysis AI-transparency
No License No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 22 / 25

How are scores calculated?

Stars

14,260

Forks

1,985

Language

License

Last pushed

Jan 31, 2026

Commits (30d)

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/jujumilk3/leaked-system-prompts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.