docling vs xberg
Document extraction and conversion projects compared
docling and xberg turn varied files into structured content for document-processing and AI workflows. docling is a Python toolkit with emphasis on document conversion and PDF analysis, while xberg is a Rust-based extraction engine offering multiple interfaces and language bindings.
docling: Convert Documents into Structured Content
Docling parses documents such as PDFs, Word files, spreadsheets, and images into structured content for applications and generative AI workflows. It offers local processing, a Python library, and a command-line interface.
xberg: Extract Documents Across Languages with a Rust Core
Xberg is a polyglot document-intelligence engine built on a Rust core, with bindings for 15 languages and CLI, REST API, and MCP interfaces. It extracts text, tables, metadata, and structured data from many document formats, and uses Whisper for optional audio transcription.
| docling | xberg | |
|---|---|---|
| Language | Python | Rust |
| License | MIT | MIT |
| Stars | 68.7k | 9.4k |
| Forks | 5k | 593 |
| Last analyzed | Oct 12, 2026 | Oct 15, 2026 |
Key differences
- docling is written in Python; xberg is built around a Rust core and provides bindings for 15 languages.
- docling exports formats including Markdown, HTML, WebVTT, and lossless JSON; xberg offers plain text, Markdown, Djot, HTML, JSON tree, and DocTags.
- docling focuses PDF analysis on layout, reading order, tables, code, formulas, and images; xberg also describes syntax-aware code extraction and chunking.
- docling can run locally, including in air-gapped environments; xberg offers a library, CLI, REST API, and MCP server, with some capabilities depending on enabled features or external runtimes.
- Both projects use the MIT license. docling has 68.3k stars and 5k forks; xberg has 9.4k stars and 588 forks.
- docling specifies Python 3.10 or higher; xberg notes that existing Kreuzberg integrations may need migration review.
Choose docling if you…
- need a Python toolkit with a CLI and Python API for document conversion.
- want PDF analysis covering layout, reading order, and tables, alongside exports such as Markdown and JSON.
- need local processing, including for sensitive documents or air-gapped environments.
Choose xberg if you…
- want a Rust-based extraction engine with bindings for multiple languages.
- need interfaces such as a REST API or MCP server, in addition to a library or CLI.
- want features such as syntax-aware code chunking or archive processing, and can check their feature requirements.
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.