xberg vs unstructured
Document extraction projects compared
xberg and unstructured both extract and organize content from varied document formats for downstream applications such as search and LLM workflows. xberg centers on a Rust engine with several interfaces and language bindings, while unstructured is a Python library built around automatic and format-specific partitioning.
xberg: Extract Text and Structure from Documents
Xberg is a Rust-based document intelligence engine that extracts text, tables, metadata, and structured data from many file types. Use it as a library, CLI, REST API, or MCP server, with bindings for multiple languages.
unstructured: Turn Documents Into Structured Data
Unstructured is a Python library for parsing and preprocessing documents into structured elements for downstream applications, including LLM workflows. It supports many file types, with format-specific dependencies for some inputs.
| xberg | unstructured | |
|---|---|---|
| Language | Rust | HTML |
| License | MIT | Apache-2.0 |
| Stars | 9.4k | 15.5k |
| Forks | 588 | 1.4k |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- xberg is written in Rust and offers a library, CLI, REST API, MCP server, and bindings for 15 languages; unstructured is a Python library.
- xberg covers documents, archives, audio, video, web content, and source code, while unstructured focuses on document inputs such as PDFs, HTML, Word files, images, and email.
- xberg offers output formats including Markdown, HTML, JSON tree, and DocTags; unstructured organizes parsed content into structured elements.
- xberg is licensed under MIT, while unstructured is licensed under Apache-2.0.
- Both have optional dependencies, but xberg lists optional Cargo features and model or runtime requirements, while unstructured uses dependency extras and may require system packages such as Tesseract, Poppler, or LibreOffice.
- The supplied project data lists 9.4k stars for xberg and 15.5k for unstructured.
Choose xberg if you…
- need extraction through Rust, CLI, REST API, MCP, or language bindings.
- want to process source code, archives, or supported audio and video alongside documents.
- need output options such as Markdown, HTML, JSON tree, or DocTags.
Choose unstructured if you…
- want a Python library with automatic file-type detection and parser selection through `partition`.
- need to preprocess common document inputs such as PDFs, HTML, Word files, images, or email.
- prefer selecting document-format support through optional dependency extras and local tooling such as Docker.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.