GPT Researcher
GPT Researcher is an open-source deep research agent that generates detailed, factual, and unbiased research reports with citations by aggregating web and local documents. It solves the problems of slow manual research, hallucination from outdated LLMs, and limited or biased web sources. It is for developers and organizations needing automated, comprehensive research reports.
🎬 GPT Researcher UX/UI - New · Assaf Elovic
✨ Key features
- Generates detailed research reports using web and local documents.
- Aggregates over 20 sources for objective conclusions.
- Supports JavaScript-enabled web scraping.
- Exports reports to PDF, Word, and other formats.
- Includes AI-generated inline images using Google Gemini.
- Offers deep research with tree-like exploration and concurrent processing.
🎯 Use cases
- Automating market research and competitive analysis.
- Generating comprehensive literature reviews from academic sources.
- Creating detailed reports on current events or technical topics.
- Researching local documents for internal knowledge synthesis.
- Integrating with AI assistants like Claude for deep research capabilities.
📦 Installation
🧰 Requirements: Python 3.11 or later, API keys for OpenAI and Tavily (or other retrievers), optional LangChain and Google API keys for tracing and image generation.
git clone https://github.com/assafelovic/gpt-researcher.git
cd gpt-researcher
Set up API keys by exporting them or storing them in a .env file:
export OPENAI_API_KEY={Your OpenAI API Key here}
export TAVILY_API_KEY={Your Tavily API Key here}
Install dependencies and start the server:
pip install -r requirements.txt
python -m uvicorn main:app --reload
Visit http://localhost:8000 to start.
🚀 Usage
from gpt_researcher import GPTResearcher
query = "why is Nvidia stock going up?"
researcher = GPTResearcher(query=query)
# Conduct research on the given query
research_result = await researcher.conduct_research()
# Write the report
report = await researcher.write_report()
⚠️ Good to know
GPT Researcher is an experimental application provided as-is without warranty, and the README notes that it may have limitations not fully disclosed.
❓ FAQ
What are the system requirements?
You need Python 3.11 or later, and API keys for OpenAI and Tavily (or other retrievers).
Can I use local documents for research?
Yes, set the DOC_PATH environment variable to your documents folder and select 'My Documents' in the frontend or pass report_source='local' in the PIP package.
How do I enable image generation?
Set IMAGE_GENERATION_ENABLED=true, GOOGLE_API_KEY, and IMAGE_GENERATION_MODEL in your .env file.
Does GPT Researcher support MCP integration?
Yes, you can set RETRIEVER=tavily,mcp and provide MCP configs to connect to data sources like GitHub.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.