gpt-researcher
by assafelovic
GPT Researcher is a Python tool that automatically researches a question by searching the web and your own documents, then writes a cited report. It can be run as a local web app, used as a Python package, or added to Claude as a skill.
- Stars
- 30.4k +18 a day
- Licence
- Apache-2.0
- Runs on
- Your computer
- Setup
- Moderate
- Language
- Python
- Age
- 1266 days
What you can do with it
- Generate a long, cited research report on a market, competitor or topic
- Research across both web sources and your own local documents
- Export finished reports to PDF or Word, or call it from your own Python code
Make money with it
A freelancer could offer paid research reports or market briefings to clients, using the tool for the first draft and checking the facts before delivery.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Produce competitor and market research briefs in minutes instead of paying for manual desk research
- Draft sourced background reports for client proposals, blog content or due diligence
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Clone the repository, set your API keys, run pip install -r requirements.txt and start the server with uvicorn, or install the gpt-researcher package with pip; a Docker image is also available.
Follow the official instructions in the project README.
Things to check
- Needs paid API keys (for example OpenAI and Tavily) to work as described
- Reports can contain errors, so sources and facts need checking
- Web scraping may breach some sites' terms of service
- Costs can rise with deep, multi-step research runs
Checked 29 Oct 2026. Summary drafted by AI from the project's README.
