GPT Researcher

What is GPT Researcher?

GPT Researcher is an open-source autonomous research agent. Given a topic or question, it plans a set of sub-questions, runs parallel web searches, reads and filters the sources, and writes a long-form report with inline citations — the ‘research agent’ pattern that later tools productised. Open-sourced by Assaf Elovic in 2023, it has since passed 28,600 GitHub stars (as of July 2026) and remains model- and search-agnostic: you bring your own API keys and plug in the LLM and search engine you prefer, so there is no subscription — you pay only the underlying API costs. Elovic went on to co-found Tavily — a paid search API for AI agents, and one of GPT Researcher's own supported search back-ends — with Rotem Weiss in late 2023, growing it directly out of this project; Nebius agreed to acquire Tavily in February 2026 for a reported ~$275M (Bloomberg; Nebius has not disclosed official terms), but GPT Researcher itself remains a separate, independent, free and open-source project, unaffected by that deal.

What does GPT Researcher do?

You give GPT Researcher a research question and it runs a planner-and-executor workflow: a planning agent generates focused sub-questions, executor agents fire off parallel web (or local-document) searches, scrape and summarise the results, and a publisher agent stitches the accumulated context into a structured, cited report — typically a couple of thousand words drawing on twenty or more sources. It offers a deeper ‘Deep Research’ mode that recursively explores a topic across many branches for more thorough coverage, at the cost of more time and API spend (its docs cite roughly five minutes and well under a dollar per run on a small model). Because it is model-agnostic, you can drive it with OpenAI, Anthropic, Google, Groq, local Ollama models and others, and pair it with search back-ends like Tavily, Google, Bing or DuckDuckGo. You can run it as a Python package, a FastAPI service with a bundled Next.js web UI, or in Docker, and export reports to PDF or Word; an MCP server is available as a companion project (gptr-mcp) rather than bundled in the main repo. There is no hosted subscription — it is free and open-source, and your only costs are the LLM and search APIs you supply.

Key features

• Planner–executor multi-agent pipeline: A planning agent writes sub-questions, executor agents search and summarise sources, and a publisher agent composes the cited report.
• Cited long-form reports: Produces structured reports of 2,000+ words with inline citations, typically aggregating 20+ sources.
• Deep Research mode: A recursive mode that explores a topic across many branches for deeper, broader coverage.
• Model- and search-agnostic: Bring your own keys — OpenAI, Anthropic, Google, Groq or local Ollama, with Tavily, Google, Bing or DuckDuckGo search.
• Multiple runtimes: Use it as a Python package, a FastAPI + Next.js app or via Docker; export to PDF or Word. A companion project (gptr-mcp) adds an MCP server.

What are GPT Researcher's use cases?

• Automated research reports: A developer asks GPT Researcher a question and gets a cited, multi-source report without manually gathering and reading sources.
• Research over private documents: Point it at local PDFs, spreadsheets or docs and it researches and cites across your own files, not just the web.
• Embed research into an app: A team runs it as a FastAPI service or MCP server so their own product can generate cited research on demand.

What does GPT Researcher integrate with?

• LLM providers — OpenAI, Anthropic, Google, Groq, local Ollama
• Search — Tavily, Google, Bing, DuckDuckGo
• MCP server (companion gptr-mcp project) + LangGraph multi-agent workflows
• Runtimes — Python package, FastAPI + Next.js, Docker; PDF/Word export

Why use GPT Researcher?

• Fully open-source (Apache 2.0) and self-hosted — no vendor lock-in and no subscription.
• Model- and search-agnostic: swap in whichever LLM and search engine you trust or can afford.
• Produces genuinely cited, long-form reports rather than a single unsourced answer.
• One of the earliest and most-adopted research agents, with an active community.

Pros & cons

GPT Researcher pricing

• Open sourceFree
• Your API usagePay-as-you-go

See current pricing on gptr.dev ↗Compare GPT Researcher alternatives →

GPT Researcher review

GPT Researcher is the reference open-source implementation of the autonomous research agent, and it holds up: give it a question and its planner-and-executor agents fan out across the web, read the sources and return a properly cited, long-form report. Its biggest strengths are openness and control — Apache-2.0 licensed, self-hosted, and agnostic about which LLM and search engine you use, so you can tune cost, quality and privacy to your needs, and even research your own local documents. The tradeoffs are the flip side of that freedom: it is a developer tool you have to install, key up and run, there is no hosted polish, and both quality and spend ride on the model and retriever you pick. Like every research agent, its citations cut hallucination without eliminating it, so reports still need a human check. Pick GPT Researcher if you want a free, hackable, self-hosted research engine you can build on; skip it if you want a no-setup, hosted product and are happy to pay for the convenience.

The open-source original of the research-agent pattern — maximum control and zero subscription, in exchange for doing your own setup and paying your own API bills.

Frequently asked questions