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
dzhng/deep-research
The project "Open Deep Research" is an AI-powered research assistant designed to perform iterative and deep research on any given topic. It combines the capabilities of search engines, web scraping, and large language models (LLMs) to refine research directions over time and dive deeper into subjects. The primary goal of this repository is to provide a simple yet effective implementation of a deep research agent, keeping the codebase under 500 lines of code for ease of understanding and extensibility. The assistant works by taking a user query along with parameters for breadth and depth of research. It then generates multiple search engine results page (SERP) queries using LLMs, processes the results to extract key learnings, and generates follow-up research directions. This process is recursive, allowing the agent to explore topics in increasing depth based on previous findings until the specified depth is reached. The final output is a comprehensive markdown report that organizes findings, sources, and references in a clear and readable format. Key features include iterative research with intelligent query generation, configurable depth and breadth controls, smart follow-up question generation, concurrent processing for efficiency, and detailed markdown report generation. The system requires Node.js and API keys for Firecrawl (for web search and content extraction) and OpenAI (for language model access). It supports local LLM endpoints and models, Docker deployment, and concurrency adjustments for performance optimization. This project is ideal for users who need an automated, intelligent research assistant capable of deep and broad exploration of topics, producing well-organized and detailed research reports. It is open-source under the MIT License, encouraging modification and extension.
https://github.com/dzhng/deep-research
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.
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.
ai-boost/awesome-prompts
Large bilingual (EN/ZH) collection of LLM prompts, system-prompt leaks, prompt-engineering frameworks and agent-ecosystem references, with 2,790 everyday prompts.
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.