asgeirtj/system_prompts_leaks
This repository provides a collection of extracted system prompts from various large language models (LLMs) including Anthropic's Claude, OpenAI's ChatGPT, Google's Gemini, and xAI's Grok, updated ...
Awesome AI Agents › Prompt Libraries
project-codeguard/rules
Project CodeGuard is a security framework and ruleset for AI assisted coding workflows, covering both code generation and code review. The core of the repository is a set of security rules written once in a model-agnostic source form, describing practices that generated code should follow, such as safe handling of secrets, input validation and avoidance of known dangerous patterns. Around those rules the project ships translators that render the same source rules into the instruction formats that individual coding agents read, so that one maintained ruleset can be distributed to several tools without hand editing each configuration. It also ships validators that check whether a given rule set is well formed and whether generated output complies with the rules, which allows the rules to be exercised in continuous integration rather than trusted by inspection. The repository is Python based, with a src directory for the tooling, a sources directory for the rule definitions, a skills directory holding agent skill packages, and a Claude plugin manifest for direct installation into that agent. The intended users are teams that already let coding agents write or review production code and want a consistent security baseline applied across whichever agent a developer happens to use, instead of relying on ad hoc prompt instructions per repository. Maintenance has moved: the README states that the project has been donated to the Coalition for Secure AI and now lives under the cosai-oasis organisation, so this repository points to the new location while retaining the rule sources and tooling. Anyone adopting it should follow that pointer for current releases and contribution guidance.
https://github.com/project-codeguard/rules
Also in Prompt Libraries
HKUDS/RAG-Anything
RAG-Anything is a next-generation all-in-one multimodal Retrieval-Augmented Generation system that processes and queries diverse document content including text, images, tables, and equations within a unified framework.
dzhng/deep-research
Open Deep Research is an AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models to generate comprehensive markdown reports.
dottxt-ai/outlines
Outlines is an open-source tool that enables structured text generation with large language models, ensuring predictable and schema-compliant outputs for various applications.
microsoft/RD-Agent
RD-Agent is an open-source R&D automation tool by Microsoft designed to automate and enhance industrial research and development processes focused on data and models using AI.
arcee-ai/mergekit
mergekit is a toolkit for efficiently merging pre-trained large language models using various algorithms, supporting CPU and GPU execution, and enabling creation of versatile merged models with maintained inference costs.
icip-cas/PPTAgent
PPTAgent is an innovative system that automatically generates and evaluates high-quality presentations from documents using a two-phase approach and a comprehensive multi-dimensional evaluation framework.
serenakeyitan/awesome-notebookLM-prompts
A curated collection of NotebookLM and Kael.im slide prompts designed to generate presentation-ready decks from various content types.