---
id: gpt-researcher
version: "0.16.0"
license: MIT
license_treatment: permissive
maintenance: active
---

# gpt-researcher — GPT Researcher is an autonomous agent designed for comprehensive online research on a variety of tasks.

License: permissive · Maintenance: active · Downloads: 95.2K/mo

## What it is and what it does

GPT Researcher is an autonomous agent framework that automates the research process by decomposing a research query into sub-questions, gathering information from multiple web sources in parallel, and synthesizing findings into a comprehensive report with citations. It addresses common LLM limitations—hallucination, outdated training data, token constraints, and shallow web coverage—by combining planning agents, execution agents, and a publisher component that aggregates results.

The package is designed for both programmatic use (via pip install and async Python API) and interactive deployment (with web frontends in HTML/CSS/JS and NextJS variants). It supports customization through environment variables and configuration objects, including optional features like AI-generated inline images, MCP integration for specialized data sources, and a deep research mode for recursive topic exploration. With 140 runtime dependencies, it brings a full ecosystem of async HTTP clients, web scrapers, LLM integrations, and document processing tools.

Use it for:

- Generate objective research reports on current events or technical topics without manual source gathering and synthesis.
- Automate competitive analysis or market research by aggregating information from multiple sources into a structured report.
- Build domain-specific research agents by customizing the planner and execution logic for specialized tasks.
- Integrate research capabilities into chatbots or assistants (e.g., Claude via the published Skill) to answer complex queries with citations.
- Export research findings to PDF or Word for stakeholder communication or documentation.
- Conduct deep exploratory research on complex topics using the recursive tree-like exploration mode.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

GPT Researcher is an autonomous agent that conducts comprehensive online research on a given query and generates detailed, factual reports with citations by orchestrating planner and execution agents to gather and synthesize information from multiple sources.

Yes, if you need to automate research report generation and have API keys for OpenAI and Tavily (or compatible services). The project is actively maintained, has no known vulnerabilities, and the MIT license imposes no restrictions. The main commitment is managing 140 dependencies and ensuring Python 3.12+ availability. Start with the pip package and async API examples in the documentation.

## Install

pip install gpt-researcher
uv add gpt-researcher
poetry add gpt-researcher

## Installing gpt-researcher

Before you install: Installation is straightforward with low friction—a pure Python wheel with no compiled dependencies. The project is actively maintained with recent commits and steady releases. Requires Python 3.12 or later and 140 runtime dependencies, which is substantial but typical for a complex agent framework.

License in practice: MIT license is permissive and places no restrictions on use, modification, or distribution in commercial or private projects.

Quickstart:

pip install gpt-researcher

from gpt_researcher import GPTResearcher
import asyncio

async def research():
    researcher = GPTResearcher(query="your research topic")
    result = await researcher.conduct_research()
    report = await researcher.write_report()
    return report

Requires Python 3.12 or later. API keys for OpenAI and Tavily (or compatible alternatives) must be set as environment variables before use.

Verify before relying:

- Whether the 2,000+ word report length claim and 20+ source aggregation are typical or best-case outcomes.
- Performance characteristics and cost implications of the deep research feature mentioned in the description.
- Whether MCP integration and inline image generation features are stable or experimental.
- Real-world latency and reliability of the parallelized agent execution model.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 95.2K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

autonomous research agent, ai research report generation, web research automation, fact-based report synthesis, multi-source information aggregation, research task automation, deep research with citations, research-automation, agent-framework, report-generation

[View on SkillFed](https://skillfed.io/packages/gpt-researcher) · [View on PyPI](https://pypi.org/project/gpt-researcher/)