assafelovic/gpt-researcher

Project overview

An autonomous research agent that aggregates over 20 web or local sources in parallel to produce detailed, cited reports. It requires external LLM and search API providers and is positioned as an experimental application provided without warranty.

Project type

AI Agent · RAG · AI Search

Use cases

Search & Research · Automation

Deployment

Python environment

License

Apache-2.0

Best for

• Researchers and general users who need to compile factual, cited reports from over 20 aggregated web sources to mitigate hallucination risks.
• Developers requiring an autonomous, self-hosted research agent library or web GUI that integrates with external LLM and search APIs.

Key capabilities

• Conducts autonomous deep research on the web and local documents using planner and execution agents to generate detailed reports with citations.
• Performs research tasks using local documents including PDF, plain text, CSV, Excel, Markdown, PowerPoint, and Word files.
• Executes a tree-like exploration pattern with configurable depth and breadth for agentic and comprehensive research.
• Supports Model Context Protocol integration to connect with specialized data sources like GitHub repositories, databases, and custom APIs alongside standard web search.
• Showcases multi-agent assistants built with LangGraph and AG2 frameworks where multiple agents with specialized skills collaborate to conduct research.
• Automatically generates and embeds AI-created illustrations in research reports using Google Gemini models.
• Provides a lightweight static frontend served by FastAPI and a feature-rich NextJS application for interacting with the research process.

Limitations and risks

• Current language models have token limitations that are insufficient for generating very long research reports without chunking or aggregation strategies.
• Running deep research incurs an approximate cost of $0.4 per research task due to external API usage.
• Language models trained on outdated information can hallucinate or become irrelevant for current research tasks if not paired with current web search results.
• The project is an experimental application provided 'as-is' without any warranty, making it unsuitable for critical production environments without external safeguards.

Getting started

• Setup requires configuring API keys for LLM and search providers and involves selecting from multiple deployment options with varying complexity.
• Clone the project, navigate to the directory, set up API keys in a .env file, install dependencies with pip install -r requirements.txt, and start the server using python -m uvicorn main:app --reload.

Evidence and sources

• GitHub project description: An autonomous agent that conducts deep research on any data using any LLM providers
• README: 🖥️ Frontend available in lightweight (HTML/CSS/JS) and production-ready (NextJS + Tailwind) versions.
• README: pip install gpt-researcher
• README: - Objective conclusions for manual research can take weeks, requiring vast resources and time. - LLMs trained on outdated information can hallucinate, becoming irrelevant for curr…
• README: GPT Researcher the first open deep research agent designed for both web and local research on any given task. The agent produces detailed, factual, and unbiased research reports w…

Reviewed at: 2026-07-17T09:55:32Z