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
ai-boost/awesome-prompts
awesome-prompts is a curated, actively maintained reference for working with large language models, organized as a GitHub awesome-list with an engineering rather than marketing focus. Its largest component is a library of 2,790 everyday prompts for writing, coding, marketing, study and design, each provided in both English and Chinese, with the majority written natively in both languages and the rest machine-translated and flagged as such. Beyond the prompt library, the repository collects copy-paste system prompts organized by domain (coding, research, safety, creative and others), leaked production system prompts from commercial AI products useful for studying how real systems are instructed, write-ups on prompt engineering techniques and defenses, and a section on context engineering that looks past single prompts to the design of an agent's whole informational environment (memory, retrieved documents, tool outputs). A dedicated "Agent Ecosystem" section indexes resources on MCP, the Agent2Agent (A2A) protocol, agent payments and identity schemes, Claude Code-style skills, agent harnesses and sandboxing, and agent memory systems. The list also links vendor prompt-engineering guides, a curated set of academic papers spanning prompt optimization, reasoning, retrieval-augmented generation, agents, safety and multimodal models, and a set of open-source tools and libraries for working with LLMs. Companion resources include an online gallery, a Hugging Face dataset mirror of the prompt library, and a sibling repository focused specifically on image and video generation prompts. It is maintained with a generation script that keeps the prompt library tables in sync with the underlying per-category files. The audience is prompt engineers, LLM application developers and researchers who want a single, continuously updated entry point into prompts, leaked system prompts, papers and agent-ecosystem tooling rather than scattered individual repositories.
https://github.com/ai-boost/awesome-prompts
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.
brycewang-stanford/Auto-Empirical-Research-Skills
Curated catalog of agent skills for empirical social science research, installable into Claude Code or Codex as plugins or skill folders and covering a nine-stage pipeline from data cleaning to journal submission.