• Introduction
• Acknowledgements
• Installation
• Environment Variables
• Folder Structure
  • Notebooks
  • reports
  • Scripts
• Contributing
• License

This repository contains a variety of AI-assisted research tools and sub-agent pipelines designed to aid in different tasks. The tools are organized into different folders based on their types.

This project is an evolving fork of the AI-Researcher repository originally created by @mattshumer. The original version utilized Claude 3 and SERPAPI to conduct research. This fork modifies the original project to encompass an array of agent+sub-agent pipelines, including real-time research and comprehensive report creation/revision. Changes will be taking place quite a bit, but pushed updates may be sparse depending on free personal time

To use the tools in this repository, follow these steps:

1. Clone the repository:

   git clone https://github.com/yourusername/AI-Research-Assistants.git
   

2. Install the required dependencies:

   pip install -r requirements.txt
   

The following environment variables are used in the scripts and notebooks:

• ANTHROPIC_API_KEY: API key for accessing the Anthropic API.
• GOOGLE_SEARCH: API key for accessing the Google Search API.
• GOOGLE_SEARCH_ENGINE_ID: Search engine ID for the Google Custom Search API.

Make sure to set these environment variables or replace the os.getenv() calls with your actual API keys before running the scripts or notebooks.

This folder will be created upon generated reports from the research tools provided.

This folder contains various Python scripts for various research and sub-agent tasks.

• Maestro

  • This project demonstrates an AI-assisted task breakdown and execution workflow using the Anthropic API. It utilizes two AI models, Opus and Haiku, to break down an objective into sub-tasks, execute each sub-task, and refine the results into a cohesive final output.

• Ollama Researcher

  • This project was published to my blog. For a full breakdown, please view the provided link.

Contributions to this repository are welcome. Add to the pile.

This project is licensed under the MIT License.