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
GPT-Instagram is an autonomous multi-agent AI application built with Next.js that leverages GPT technology to research and recommend Instagram posts tailored to the user's personality and historical posting style. The app integrates with the Instagram Basic Display API to extract data from a user's past Instagram posts, which it then analyzes to understand the user's unique style and preferences. This analysis is conducted through a series of specialized AI agents, each with distinct roles to ensure comprehensive and personalized post recommendations. The system includes several agents: the Data Explainer Agent analyzes the user's historical posts; the Explanation Condenser Agent synthesizes this information into a coherent report on the user's posting style; the IG Post Generator Agent creates Instagram post suggestions based on the user's personality and feedback from the Viral Critique Agent, who evaluates the potential virality of the posts. Additionally, the Image Generator Agent creates accompanying images, and the Post Improver Agent interacts with the user to refine and enhance the posts. The application requires users to obtain an Instagram Access Token via the Instagram Basic Display API, an OpenAI API key, and a Tavily Search API key to function. It uses Drizzle ORM for database management and requires setup steps including dependency installation, database migration, and environment variable configuration. The project is designed as a proof-of-concept or toy project, originally created for the Tavily AI Intern Application, and may not receive further updates. Overall, GPT-Instagram combines AI-driven data analysis, content generation, and marketing expertise to help users create Instagram posts that reflect their personality while maximizing engagement potential. It showcases the integration of multiple AI agents working collaboratively to deliver personalized social media content recommendations.
https://github.com/MODSetter/gpt-instagram
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 ...
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.
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.
Outlines is an open-source tool that enables structured text generation with large language models, ensuring predictable and schema-compliant outputs for various applications.
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.
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.
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.
A curated collection of NotebookLM and Kael.im slide prompts designed to generate presentation-ready decks from various content types.