Source: https://seerepo.com/compare/assafelovic/gpt-researcher/vs/Unstructured-IO/unstructured
Markdown source: https://seerepo.com/compare/assafelovic/gpt-researcher/vs/Unstructured-IO/unstructured.md
Description: gpt-researcher and unstructured share 9 technologies: langdetect, unstructured-client, filetype, html5lib, lxml, python-magic, python-oxmsg, beautifulsoup4, and psutil. gpt-researcher is written in Python and unstructured in HTML.

# gpt-researcher vs unstructured

gpt-researcher and unstructured share 9 technologies: langdetect, unstructured-client, filetype, html5lib, lxml, python-magic, python-oxmsg, beautifulsoup4, and psutil. gpt-researcher is written in Python and unstructured in HTML.

- [assafelovic/gpt-researcher](https://seerepo.com/r/assafelovic/gpt-researcher): An autonomous agent that conducts deep research on any data using any LLM providers
- [Unstructured-IO/unstructured](https://seerepo.com/r/Unstructured-IO/unstructured): Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models.  Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

## What they share and what sets them apart

- In common: langdetect, unstructured-client, filetype, html5lib, lxml, python-magic, python-oxmsg, beautifulsoup4, psutil
- Only in gpt-researcher: FastAPI, anyio, starlette, AIOHTTP, uvicorn, React, Next.js, @next/third-parties, fonttools, soupsieve, tinycss2, SQLAlchemy, cryptography, LangGraph, langgraph-sdk, langsmith, litellm, MCP, nltk, Ollama, OpenAI, tavily-python, tokenizers, LangChain, langchain-community, langchain-openai, langchain-mcp-adapters, langchain-text-splitters, deepagents, langchain-ollama, langchain-classic, tiktoken, cssselect2, feedparser, jinja2, markdown2, markupsafe, olefile, pydyf, pymupdf, pypdf, python-pptx, tinyhtml5, unstructured, webencodings, markdown, mistune, pillow, python-docx, weasyprint, annotated-types, jsonschema, jsonschema-specifications, marshmallow, pydantic-core, referencing, Pydantic, loguru, Tailwind CSS, react-hot-toast, Framer, react-dropzone, @langchain/langgraph-sdk, isomorphic-dompurify, remark, remark-gfm, remark-html, ag2, langchain-core
- Only in unstructured: spaCy, nh3

## Side by side

| | gpt-researcher | unstructured |
|---|---|---|
| Size | 51,624 lines written, 233 code files | 285,496 lines written, 315 code files |
| Who writes it | 3.2% of its commits signed by AI. With Claude Code, Cursor, GitHub Copilot, Jules, and Codex | 2.4% of its commits signed by AI. With Claude Code and GitHub Copilot |
| Activity | Last push October 10, 2026, 2,477 commits, 30,542 stars | Last push November 6, 2026, 2,032 commits, 15,696 stars |
| Tests | 149 test files. 36.5% of its code files have a test that imports them | 131 test files. 34.3% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, gpt-researcher or unstructured?

unstructured, with 285,496 lines written; gpt-researcher has 51,624.

The proof: [Unstructured-IO/unstructured's code at commit 293d235](https://github.com/Unstructured-IO/unstructured/tree/293d235cfcd5f5e89c3cc5ff85562005e182ae33)

### Which has more GitHub stars, gpt-researcher or unstructured?

gpt-researcher, with 30,542 stars; unstructured has 15,696.

The proof: [assafelovic/gpt-researcher on GitHub](https://github.com/assafelovic/gpt-researcher)

### Which has more tests, gpt-researcher or unstructured?

gpt-researcher, with 149 test files; unstructured has 131.

The proof: [assafelovic/gpt-researcher's code at commit 3582a68](https://github.com/assafelovic/gpt-researcher/tree/3582a6841fe7dc801e2a34e34ee408641aea9bce)

### Which was updated more recently, gpt-researcher or unstructured?

unstructured: its last push was on November 6, 2026, and gpt-researcher's on October 10, 2026.

The proof: [Unstructured-IO/unstructured's commits on GitHub](https://github.com/Unstructured-IO/unstructured/commits)

### Which has more commits signed by AI, gpt-researcher or unstructured?

gpt-researcher: an AI signed 3.2% of its commits, with Claude Code, Cursor, GitHub Copilot, Jules, and Codex; in unstructured, 2.4%.

The proof: [the commits each tool signed in assafelovic/gpt-researcher](https://seerepo.com/r/assafelovic/gpt-researcher/ai)

## Sources

- assafelovic/gpt-researcher: Read on November 7, 2026, at commit 3582a68 (https://github.com/assafelovic/gpt-researcher/tree/3582a6841fe7dc801e2a34e34ee408641aea9bce)
- Unstructured-IO/unstructured: Read on November 7, 2026, at commit 293d235 (https://github.com/Unstructured-IO/unstructured/tree/293d235cfcd5f5e89c3cc5ff85562005e182ae33)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.