Source: https://seerepo.com/r/Unstructured-IO/unstructured
Markdown source: https://seerepo.com/r/Unstructured-IO/unstructured.md
Description: Unstructured-IO/unstructured is an HTML repo with 285,496 lines written. SeeRepo read unstructured and doesn't recognize any of its technologies yet.

# What's inside Unstructured-IO/unstructured

Unstructured-IO/unstructured is an HTML repo with 285,496 lines written. SeeRepo read unstructured and doesn't recognize any of its technologies yet. AI signed 2.4% of the 2,032 commits of unstructured.

Its description on GitHub: “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.”

HTML · Apache-2.0 · 15,696 stars · GitHub: https://github.com/Unstructured-IO/unstructured

Read on November 7, 2026, at commit 293d235.

## More on this repo

- [What is unstructured built with?](https://seerepo.com/r/Unstructured-IO/unstructured/built): SeeRepo read unstructured and doesn't recognize any of its technologies yet.
- [How much of unstructured did AI write?](https://seerepo.com/r/Unstructured-IO/unstructured/ai): AI signed 2.4% of the 2,032 commits of unstructured.

## In figures

- 285,496 lines written: The ones people and agents wrote: product, tests, schemas and tooling. Generated code doesn’t count.
- 315 source files: The same as the lines: product, tests, schemas and tooling. What’s generated doesn’t count.
- 131 test files: The files that test the code.
- 11 technologies: Each service with the file and line that prove it.

SeeRepo read the facts in its code and kept none of it. AI only helps sort its packages and folders by their names, and never sees its code.

## Frequently asked questions

### What is Unstructured-IO/unstructured?

Unstructured-IO/unstructured is an HTML repo with 285,496 lines written. Its description on GitHub: “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.”

The proof: [its page on GitHub](https://github.com/Unstructured-IO/unstructured)

### What is unstructured built with?

SeeRepo read unstructured and doesn't recognize any of its technologies yet.

The proof: [each service with its file and line](https://seerepo.com/r/Unstructured-IO/unstructured/built)

### How much of unstructured did AI write?

AI signed 2.4% of the 2,032 commits of unstructured.

The proof: [the commits each tool signed](https://seerepo.com/r/Unstructured-IO/unstructured/ai)

### What license does unstructured have?

unstructured is released under the Apache-2.0 license.

The proof: [its page on GitHub](https://github.com/Unstructured-IO/unstructured)

### How many stars does unstructured have on GitHub?

unstructured had 15,696 stars on GitHub on November 7, 2026.

The proof: [its page on GitHub](https://github.com/Unstructured-IO/unstructured)

## Add this badge to your README

It links to this page and updates itself each time SeeRepo reads the repo.

```markdown
[![Unstructured-IO/unstructured on SeeRepo](https://seerepo.com/badge/Unstructured-IO/unstructured.svg)](https://seerepo.com/r/Unstructured-IO/unstructured?de=insignia)
```

## 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.