Deep-research
by ssdeanx
Deep-research is an AI-powered research assistant that conducts iterative, deep research using search engines, web scraping, and Gemini LLMs. It provides a lightweight and understandable codebase for efficient web data extraction and advanced language understanding.
Last updated: N/A
What is Deep-research?
Deep-research is a tool designed to provide the simplest yet most effective implementation of a deep research agent. It leverages Firecrawl for web data extraction and Gemini for advanced language understanding and report generation, aiming for a codebase under 500 lines of code.
How to use Deep-research?
To use Deep-research, you need a Node.js environment (v22.x recommended) and API keys for Firecrawl and Gemini. Clone the repository, install dependencies, set up environment variables in a .env.local file, and build the project. It can be used as an MCP tool or standalone via the CLI. Invoke it with a research query, depth, and breadth parameters.
Key features of Deep-research
MCP Integration: Seamlessly integrates as a Model Context Protocol (MCP) tool into AI agent ecosystems.
Iterative Deep Dive: Explores topics deeply through iterative query refinement and result processing.
Gemini-Powered Queries: Leverages Gemini LLMs to generate smart, targeted search queries.
Depth & Breadth Control: Configurable depth and breadth parameters for precise research scope.
Smart Follow-up Questions: Intelligently generates follow-up questions for query refinement.
Comprehensive Markdown Reports: Generates detailed, ready-to-use Markdown reports.
Concurrent Processing for Speed: Maximizes research efficiency with parallel processing.
Use cases of Deep-research
Automated literature review
Market research and competitive analysis
Scientific research and data analysis
Content creation and summarization
FAQ from Deep-research
What is MCP Integration?
What is MCP Integration?
MCP (Model Context Protocol) allows Deep-research to seamlessly integrate with other AI agents and tools.
What are the requirements to run Deep-research?
What are the requirements to run Deep-research?
You need Node.js (v22.x), API keys for Firecrawl and Gemini, and a cloned repository with installed dependencies.
How do I set up the environment variables?
How do I set up the environment variables?
Create a .env.local file in the project root and add your API keys for Gemini and Firecrawl.
Can I use Deep-research without MCP?
Can I use Deep-research without MCP?
Yes, you can run it directly from the command line using npm run start "your research query".
What are Persona Agents?
What are Persona Agents?
Persona Agents are used to guide the behavior of the Gemini language models, imbuing it with a specific role, skills, personality, communication style, and values.