GPT Researcher

Active
GitHub Python Apache-2.0

Description

GPT Researcher is an autonomous research agent that can gather, organize, and analyze information to produce detailed research reports.

Key Features

  • Parallel research architecture — Planner generates questions, multiple Execution Agents crawl in parallel aggregating 20+ sources
  • MCP data source integration — Hybrid web + MCP research via RETRIEVER=tavily,mcp for GitHub repos, databases, custom APIs
  • Smart image scraping & filtering — Auto-extracts report-relevant images with AI filtering, Google Gemini inline illustration generation
  • Multi-format report export — Generates 2000+ word reports, exportable to PDF, Word, and other formats
  • Local document research — Deep research on local documents combined with web search for comprehensive reports
  • Claude Skill integration — Installable as a Claude Skill via npx skills add to extend Claude's deep research capabilities

Use Cases

💡 Market research & competitive analysis — Auto-collect multi-source info to generate objective market research reports
💡 Academic literature review — Quickly aggregate latest research progress and citations across multiple fields
💡 Technical feasibility assessment — Analyze technical solutions by combining web and local document research
💡 Industry trend tracking — Periodically generate trend reports for specific industries with up-to-date information
💡 Investment research assistance — Auto-analyze company info and market data to generate investment research summaries

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (29.0k stars)
  • Permissive open-source license (Apache-2.0)
  • Established track record (3 years in production)

Quick Start

pip install gpt-researcher
export OPENAI_API_KEY={your-key}
export TAVILY_API_KEY={your-key}

from gpt_researcher import GPTResearcher
import asyncio

query = "Why is Nvidia stock going up?"
researcher = GPTResearcher(query=query)
result = asyncio.run(researcher.conduct_research())
report = asyncio.run(researcher.write_report())
print(report)

Related Projects

LangChain

144.4k · Python
Active A+

LangChain is the open-source agent engineering platform that unifies model IO, tool calling, RAG, memory and observability under one composable framework.

agent-frameworkragorchestration +2
  • · Unified model abstraction — ChatModel interface covers OpenAI, Anthropic, Bedrock, Vertex and 100+ providers
  • · Tool calling & agents — tool calling, ReAct, OpenAI Tools, Plan-and-Execute agent paradigms
  • · RAG as a first-class citizen — Document Loader, Text Splitter, Retriever and Index abstractions

LlamaIndex

51.7k · Python
Active A+

LlamaIndex is a data framework for building LLM applications. It provides data connectors, indexing, query engines, and agent workflow orchestration — a core tool in the RAG ecosystem.

ragdata-frameworkindexing +2
  • · Data connectors — 300+ integration packages connecting diverse data sources (files, databases, APIs, web, etc.)
  • · Vector indexing and query engine — Supports multiple vector databases with semantic search and hybrid retrieval
  • · Agent workflow orchestration — Build complex multi-step AI agent flows with Workflows

WeKnora

19.9k · Go
Active A

Tencent's open-source LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG.

goragllm +3
  • · RAG-based Quick Q&A for everyday document lookups with semantic retrieval
  • · ReAct Agent autonomously orchestrating retrieval, MCP tools, and web search for complex multi-step tasks
  • · Wiki Mode where agents distill raw documents into self-maintaining, interlinked markdown knowledge bases with interactive knowledge graphs

Related Articles