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
qx-labs/agents-deep-research
The project "agents-deep-research" by qx-labs is an advanced implementation of an iterative deep research assistant leveraging the OpenAI Agents SDK. It is designed to perform comprehensive and in-depth research on any given topic by using a multi-agent architecture that iteratively refines its understanding and produces detailed insights culminating in a final report. The system supports compatibility with a wide range of language models and APIs including OpenAI, Anthropic, Gemini, DeepSeek, Perplexity, OpenRouter, Hugging Face, and local models like Ollama, making it highly versatile. The project offers two main modes of research: the IterativeResearcher and the DeepResearcher. The IterativeResearcher runs a continuous loop of research on a topic or sub-topic, drafting reports that are ideal for shorter documents up to about 5 pages or 1,000 words. Users can specify constraints such as research depth, time limits, report length, and formatting instructions. The DeepResearcher mode is designed for more extensive and structured research, suitable for longer reports (20+ pages). It first creates a report outline and then runs multiple IterativeResearcher instances concurrently for each section of the report. This approach allows for thorough exploration of each section, identifying knowledge gaps, selecting appropriate tools, executing research actions, and synthesizing findings into comprehensive sections before compiling them into a coherent final report. The architecture includes specialized agents such as Knowledge Gap Agent, Tool Selector Agent, Tool Agents (for web search, crawling, and custom tools), Observations Agent, and Writer Agent. The project supports tracing of LLM and tool calls using OpenAI's tracing feature for enhanced monitoring. It is designed to be extendable with custom tools and third-party LLMs compatible with the OpenAI API specification. Installation is straightforward via pip or cloning the repository, and usage is flexible through Python modules or command-line interface. The project also allows runtime configuration of LLMs for dynamic model selection. Sample outputs demonstrate its capability to generate detailed research reports on diverse topics such as Plato, quantum computing, and Tesla. Keywords: iterative deep research, OpenAI Agents SDK, multi-agent architecture, deep research assistant, language models, LLM compatibility, report generation, knowledge gap identification, tool selection, web search, crawling, custom tools, tracing, Python module, command-line interface, research automation, extensible, concurrent research, report outline, research synthesis, OpenAI API compatible models.
https://github.com/qx-labs/agents-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.
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.