GPT Researcher

What GPT Researcher is

GPT Researcher is an open-source agent that investigates web sources and user documents, then produces detailed reports with citations. It turns a research request into sub-questions, searches sources in parallel, filters relevant passages, and assembles a cited report. The homepage lists more than 20 retrievers, including Tavily, Google, Bing, Exa, arXiv, and PubMed. It supports a range of language models, including OpenAI, Anthropic, Google, Mistral, DeepSeek, and local models through Ollama. Document research can cover PDFs, Word files, spreadsheets, and Markdown, either on their own or alongside web sources. Reports can be exported as Markdown, PDF, Word, JSON, or CSV. Its official gptr-mcp server makes research tools available to Claude, Cursor, ChatGPT custom GPTs, n8n, and other MCP clients. Developers can use a self-hosted FastAPI server with REST endpoints for deep research, quick search, and report writing. The software can run on a personal machine, server, or container, including through a Docker image. The maker says data leaves the user’s machine only through configured LLM and retriever providers; local models with SearXNG can keep it on the user’s infrastructure. GPT Researcher has no usage limits of its own, though provider limits and costs apply.

Who it suits

GPT Researcher suits people who need cited reports built from web research, their own files, or both. Its self-hosted deployment options, API, and MCP server also suit developers who want to use research tools in applications or MCP clients.

Limits

The Open Source plan has no GPT Researcher usage limits. Usage limits and costs depend on configured providers; a deep research run with the default OpenAI and Tavily settings is estimated at a few cents to a few dollars in provider spend.

Getting started

1. Visit the GPT Researcher website.
2. Use Python 3.11 or later for the documented setup.
3. Configure keys for an LLM and a retriever, or use local models through Ollama.
4. Run it on a personal machine, server, or container; a Docker image is available.
5. Choose web research, document research, or both, then select an output format.

Verdict

Choose GPT Researcher if you want an open-source research agent that can cite findings from the web and your own files, with self-hosting and export options. It does not impose its own usage limits, but you need configured providers and may incur their costs. People seeking a managed plan should consider that the listed offering is self-hosted open source.