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
johnbean393/Sidekick
Sidekick is a native macOS application designed to enable users to interact with a local large language model (LLM) that can provide responses based on information extracted from files, folders, and websites on the user's Mac. This application operates entirely offline, ensuring user data privacy and security by not requiring any additional software installations. It is powered by llama.cpp and supports a local-first approach with a built-in inference engine for local models, while also allowing integration with OpenAI-compatible APIs for extended model options. The app is particularly useful for research and information retrieval tasks. Users can create and configure "experts"—collections of resources such as documents, folders, and websites related to specific topics or areas of interest. Sidekick uses Retrieval Augmented Generation (RAG) to efficiently search through these resources and provide relevant, context-aware answers. For example, a student can set up experts for different academic subjects and query Sidekick to get precise information with references and source links. Sidekick also supports web search to fetch the latest information, enhancing its utility for up-to-date research. It offers advanced features such as function calling to perform mathematical and logical operations or execute actions like drafting emails using contact information from the user's address book. The app supports memory capabilities, allowing it to remember details across conversations to provide more personalized and contextually relevant responses. Additional features include a Canvas for creating and editing websites or code, automatic image generation from text prompts using CoreML on macOS 15.2 or later, and advanced markdown rendering with native LaTeX support for mathematical equations, data visualization with various chart types, and syntax-highlighted code rendering. Sidekick aims to be a comprehensive, secure, and powerful assistant for macOS users seeking to leverage local LLMs for research, writing, coding, and more.
https://github.com/johnbean393/Sidekick
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.