GPT Researcher

What is GPT Researcher?

GPT Researcher splits a research question into sub-questions with a planner agent, sends execution agents to gather sources from the web (or your own documents), filters the context and writes a long report with citations that can be exported to PDF, Word or Markdown. It ships a FastAPI server, a Next.js web app, a Python package and an MCP server, and supports many LLM providers and search retrievers. By default it uses OpenAI for the LLM and Tavily for web search.

Where it fits in a 10–200 person business

• Market, competitor or supplier research reports with sources for management
• Research over internal documents (PDF, Word, Excel, PowerPoint) placed in a local folder
• Background briefings for sales or consulting teams before a customer meeting

These use cases are our editorial suggestions, not claims made by the project.

Can a business use GPT Researcher? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does GPT Researcher phone home?

Checked against the project's own docs and repository on Oct 23, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does GPT Researcher need?

The Linux deployment guide lists "Server Requirements" of 2 GB RAM, 1 vCPU and 50 GB SSD (a default DigitalOcean droplet that "works well"), so treat it as a sizing suggestion. LLM and search run through external APIs by default, so no GPU is needed for the app itself.

Source: docs.gptr.dev/docs/gpt-researcher/getting-started/linux-deployment

How much does it cost to host GPT Researcher per month?

How to deploy GPT Researcher

Method: Docker Compose

git clone https://github.com/assafelovic/gpt-researcher.git && cd gpt-researcher
cp .env.example .env   # add OPENAI_API_KEY and TAVILY_API_KEY
docker compose up --build
# API server on :8000, Next.js web app on :3000

From the official instructions: docs.gptr.dev/docs/gpt-researcher/getting-started/getting-started-with-docker. Always check the source for the current version before you run it.

Known gotchas when self-hosting GPT Researcher

• The defaults need two paid cloud APIs, OpenAI for the LLM and Tavily for web search (RETRIEVER defaults to tavily). For a more private setup, change the LLM, embedding and RETRIEVER settings (e.g. Ollama, SearxNG) in the config. source
• To use an LLM other than OpenAI in Docker, first add the matching langchain package (e.g. langchain-google-genai, langchain-deepseek) to requirements.txt, then rebuild the image. source
• The official docker-compose.yml builds the web app from frontend/nextjs/Dockerfile.dev with the source folder mounted, runs the API container as root and publishes ports 8000 and 3000 directly. The Linux deployment guide puts Nginx with HTTPS in front. source

Alternatives in AI search & research assistants

• Khoj Personal and team AI "second brain" for your documents and the web. Compare GPT Researcher vs Khoj
• Vane (formerly Perplexica) Private, Perplexity-style AI answer engine with cited web sources. Compare GPT Researcher vs Vane (formerly Perplexica)

Sources

• GitHub repository: github.com/assafelovic/gpt-researcher
• Official documentation: docs.gptr.dev/
• License text: github.com/assafelovic/gpt-researcher/blob/main/LICENSE
• Hardware requirements: docs.gptr.dev/docs/gpt-researcher/getting-started/linux-deployment
• Deploy instructions, Gotcha 2: docs.gptr.dev/docs/gpt-researcher/getting-started/getting-started-with-docker
• Gotcha 1: docs.gptr.dev/docs/gpt-researcher/gptr/config
• Gotcha 3: github.com/assafelovic/gpt-researcher/blob/main/docker-compose.yml
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Oct 23, 2026