Home/AI Agents/system_prompts_leaks
system_prompts_leaks logo

system_prompts_leaks

asgeirtj/system_prompts_leaks

Leaked system prompts from various AI agents

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

82views this month

67k stars11k forksLast push Sep 17, 2026 JavaScript CC0-1.0

Decision brief

system_prompts_leaks is a repository that collects and shares leaked system prompts from various AI agents, including Anthropic Claude, OpenAI ChatGPT, Google Gemini, and xAI Grok. It is updated regularly and provides a窥

Good fit when

  • Use system_prompts_leaks when you need to understand the underlying instructions and rules that different AI agents follow. This can be particularly useful for researchers, developers, and prompt工程师
  • Consider using this repository if you are working on projects that require a deep dive into how AI agents are programmed to behave and respond, offering insights that can inform the development of new

Avoid when

  • Do not use system_prompts_leaks if you are looking for official documentation or support from the AI agent providers, as the content here is based on leaked information and may not be up-to-date or
  • Avoid relying on this repository if you need legally compliant or secure system prompts, as the repository's content is unverified and may contain inaccuracies or outdated information.
Pricing:
freemium - The repository is available under the CC0-1.0 license, which means it is free to use and distribute without any restrictions. However, users should be cautious about the reliability and legality of
Requirements:
Min 1 GB RAM; Users should have a basic understanding of AI agents and system prompts to effectively utilize the information provided in the repository.; It is recommended to cross-reference the information with official sources where possible to ensure accuracy and reliability.

Observed Sep 18, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Very active (0d since push)
As of Sep 18, 2026
Provenance
Not a fork · Personal account
As of Sep 18, 2026
Security (OSV)
No lockfile
As of Sep 18, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

npm install system_prompts_leaks
npm

How it fits your stack(14)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Related

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Repository containing extracted system prompts from multiple AI agents including Anthropic Claude, OpenAI ChatGPT, Google Gemini, and xAI Grok. Updated regularly.

Capability facts

Languages
javascript

Source: github.language · Sep 18, 2026

Categories

Graph entities

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Works with ChatGPTChatGPT

Source: README excerpt (regex_v1, Sep 18, 2026)

aked system prompts, captured verbatim — the hidden instructions and rules that ChatGPT, Claude, Gemini, Grok and every other AI chatbot receives before your first mes
Source link

Tags

README

<p align="center" <sub Thanks to</sub </p <p align="center" <a href="https://go.asgeirtj.workers.dev/latitude" <img src="assets/latitude dark.png" alt="Latitude Logo" width="700"/ </a </p <div align="center" markdown="1" Open Source Agent Analytics Understand your agents in produ...

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.