Logo
Deploy Now

SaaS Alternative

Perplexity OpenAI Deep Research Elicit Consensus

Categories

Productivity Developer Tools AI Automation LLM Agents Research Reports

Stars

28129

Forks

3796

Watchers

169

Developer links

Last Updated: 07-07-2026 11:36 AM (UTC)

GPT Researcher

A question goes in; a cited, long-form report comes out - GPT Researcher is an open-source autonomous research agent. A planner agent decomposes the query into sub-questions, execution agents crawl 20+ web sources in parallel with JavaScript-enabled scraping, and a publisher aggregates findings into a 2,000+ word report with inline citations, exportable to PDF, Word, and Markdown. The Deep Research mode extends this recursively: each result yields follow-up questions that are explored to configurable breadth and depth in a tree pattern, while accumulated learnings, citations, and visited URLs are shared across branches. It also researches local documents (PDF, CSV, Word) alongside the web. LLM and search providers are pluggable, including OpenAI, Anthropic, Google, DeepSeek, and Ollama for models, and Tavily, Google, Bing, DuckDuckGo, and SearXNG for retrieval. It ships as a Python package, a FastAPI server with web frontend, a Docker image, and an MCP server for use inside Claude or Cursor. MIT-licensed.

GPT Researcher
GPT Researcher

Benefits

  • Hours of Research in Minutes
  • Parallelized planner and execution agents aggregate dozens of sources and produce a structured, cited report faster than manual searching, reading, and note-taking.
  • Citations Against Misinformation
  • Every claim links back to a source URL, and aggregating 20+ sources per query reduces the single-source bias and hallucination risk of asking a chatbot directly.
  • Your Keys, Your Model Choice
  • Run it against OpenAI, Anthropic, Google, DeepSeek, or a local Ollama model at raw API cost, instead of paying per-seat pricing for hosted deep-research products.
  • Embeds in Your Workflow
  • Use the web UI, call the Python package from your own code, or connect the MCP server so agents like Claude and Cursor can invoke deep research as a tool.

Features

  • Planner-Executor Architecture
  • A planner agent generates research questions, parallel execution agents gather evidence, and a publisher composes the final report.
  • Recursive Deep Research
  • Tree-like exploration with configurable breadth and depth, feeding follow-up questions back into the loop while tracking learnings and citations per branch.
  • Long-Form Cited Reports
  • Reports exceeding 2,000 words with inline citations, scraped and filtered images, and export to PDF, DOCX, and Markdown.
  • Web Plus Local Documents
  • Research spans JavaScript-rendered web pages and your own files, including PDF, Word, CSV, and text documents.
  • Pluggable LLMs and Retrievers
  • OpenAI, Anthropic, Google, Mistral, DeepSeek, and Ollama models; Tavily, Google, Bing, DuckDuckGo, and SearXNG search backends.
  • MCP Server and API
  • Exposes deep_research, quick_search, and write_report tools over MCP with stdio and SSE transports, plus a FastAPI backend with WebSocket streaming.