Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
| Date | Stars |
|---|---|
| 2026-07-24 | 1768 |
| 2026-07-25 | 1768 |
| 2026-07-28 | 1768 |
| 2026-07-30 | 1768 |
| 2026-08-06 | 1768 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center" style="margin-top: 20px">
<a href="https://yobix.ai">
<img height="28px" alt="yobix ai logo" src="https://framerusercontent.com/images/zaqayjWBWNoQmV9MIwSEKf0HBo.png?scale-down-to=512">
</a>
<h1 style="margin-top: 0; padding-top: 0">Extractous</h1>
</div>
<div align="center">
<a href="https://github.com/yobix-ai/extractous/blob/main/LICENSE"></a>
[](https://crates.io/crates/extractous)
[](https://pypi.org/project/extractous/)
<img src="https://img.shields.io/github/commit-activity/m/yobix-ai/extractous" alt="Commits per month">
[](https://pepy.tech/project/extractous)
</div>
<div align="center">
_Extractous offers a fast and efficient solution for extracting content and metadata from various documents types such as PDF, Word, HTML, and [many other formats](#supported-file-formats).
Our goal is to deliver a fast and efficient comprehensive solution in Rust with bindings for many programming
languages._
</div>
---
**Demo**: showing that [Extractous 🚀](https://github.com/yobix-ai/extractous) is **25x faster** than the popular
[unstructured-io](https://github.com/Unstructured-IO/unstructured) library ($65m in funding and 8.5k GitHub stars).
For complete benchmarking details please consult our [benchmarking repository](https://github.com/yobix-ai/extractous-benchmarks)
<sup>* demo running at 5x recoding speed</sup>
## Why Extractous?
**Extractous** was born out of frustration with the need to rely on external services or APIs for content extraction from unstructured data. Do we really need to call external APIs or run special servers just for content extraction? Couldn't extraction be performed locally and efficiently?
In our search for solutions, **unstructured-io** stood out as the popular and widely-used library for parsing unstructured content with in-process parsing. However, we identified several significant limitations:
- Architecturally, unstructured-io wraps around numerous heavyweight Python libraries, resulting in slow performance and high memory consumption (see our [benchmarks](https://github.com/yobix-ai/extractous-benchmarks) for more details).
- Inefficient in utilizing multiple CPU cores for data processing tasks, which are predominantly CPU-bound. This inefficiency is due to limitations in its dependencies and constraints like the Global Interpreter Lock (GIL), which prevents multiple threads from executing Python bytecode simultaneously.
- As unstructured-io evolves, it is becoming increasingly complicated, transitioning into more of a complex framework and focusing more offering an external API service for text and metadata extraction.
In contrast, **Extractous** maintains a dedicated focus on text and metadata extraction. It achieves significantly faster processing speeds and lower memory utilization through native code execution.
* **Built with Rust:** The core is developed in Rust, leveraging its high performance, memory safety, multi-threading capabilities, and zero-cost abstractions.
* **Extended format support with Apache Tika:** For file formats not natively supported by the Rust core, we compile the well-known [Apache Tika](https://tika.apache.org/) into native shared libraries using [GraalVM](https://www.graalvm.org/) ahead-of-time compilation technology. These shared libraries are then linked to and called from our Rust core. No local servers, no virtual machines, or any garbage collection, just pure native execution.
* **Bindings for many languages:** we plan to introduce bindings for many languages. At the moment we offer only Python binding, which is essentially is a wrapper around the Excerpt of 12,907 characters
Read on GitHub
227
9
7
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:97019b7837c1567d, topic:etl, topic:ocr, topic:pdf-parser
matched fp:97019b7837c1567d, topic:nlp, topic:natural-language-processing