HUGGINGFACE.md

DeepResearchAgents on Hugging Face

This repository contains the DeepResearchAgents project, a comprehensive research assistant that combines Deep Research, AI Co-Scientist, and specialized MCP agents to create a powerful research workflow.

Overview

DeepResearchAgents is a monorepo that integrates several components:

1. Deep Research: A Next.js application for generating in-depth research reports using AI models.
2. AI Co-Scientist: A multi-agent system for generating, reviewing, ranking, and evolving research hypotheses.
3. MCP Agents: Specialized Model Context Protocol agents that enhance the research cycle with domain-specific expertise.
4. Cognee: A knowledge graph system that provides powerful capabilities for processing and analyzing text.

Features

• Generate in-depth research reports on any topic
• Create and explore research hypotheses
• Generate research questions from hypotheses
• Visualize knowledge graphs
• Chat with an AI assistant that has access to your knowledge graph
• Choose from specialized research agents (academic, problem-solving, health)
• Configure API settings for different models

Deployment on Hugging Face

This project is deployed as a single Docker container on Hugging Face Spaces. The container includes all components and their dependencies.

Environment Variables

To run this project, you need to set the following environment variables in your Hugging Face Space:

GOOGLE_GENERATIVE_AI_API_KEY=your-google-api-key
MODEL_CHOICE=gemini-2.5-pro-preview-03-25
MODEL_PROVIDER=google

You can also set these optional variables for alternative models:

OPENAI_API_KEY=your-openai-api-key
OPENROUTER_API_KEY=your-openrouter-api-key
ANTHROPIC_API_KEY=your-anthropic-api-key

Hardware Requirements

This project requires at least:

• 4 CPU cores
• 16 GB RAM
• 10 GB disk space

Accessing the Application

Once deployed, you can access the application at the URL provided by Hugging Face Spaces.

Local Development

To run this project locally:

1. Clone the repository
2. Build the Docker image:

   docker build -t deep-research-agents .
   

3. Run the container:

   docker run -p 3000:3000 -e OPENAI_API_KEY=your-api-key deep-research-agents
   

4. Access the application at http://localhost:3000

License

This project is licensed under the MIT License - see the LICENSE file for details.