DEDUPEDcost. Each report makes many LLM and search API calls billed to your OpenAI and Tavily accounts.
Who it is forAnyone who wants a research report on a topic in minutes.
The problemReading dozens of sources by hand for one question takes hours.
The outcomeA local web app at localhost:8000 that writes research reports.
What you need first
- Python 3.12 or later
- An OpenAI API key and a Tavily API key, or a custom OpenAI-compatible endpoint
- Docker if you prefer the docker compose setup
Steps
- Clone with
git clone https://github.com/assafelovic/gpt-researcher.gitandcd gpt-researcher - Set your OPENAI_API_KEY and TAVILY_API_KEY as environment variables or in a .env file
- Install and start with
pip install -r requirements.txtandpython -m uvicorn main:app --reload - Open http://localhost:8000 and enter your research question
Prompt for your agent
Set up assafelovic/gpt-researcher locally: clone it, install with `pip install -r requirements.txt`, start it with `python -m uvicorn main:app --reload`, and run a report on <my topic>.
Caveat. Reports summarize web sources automatically, so verify key claims against the cited sources before relying on them.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for assafelovic/gpt-researcher and "Run a deep research web app on your machine"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer