docling vs xberg
Document extraction projects compared
docling and xberg turn varied files into structured content for applications and AI workflows. docling is a Python library focused on document conversion, while xberg uses a Rust core and offers bindings and several deployment interfaces.
docling: Parse Documents for AI Workflows
Docling converts documents from formats such as PDF, Office files, images, and audio into structured representations and exports. It suits developers building document-processing and generative AI pipelines that need format coverage, OCR, or local execution.
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 | 68.3k | 9.4k |
| Forks | 5k | 593 |
| Last analyzed | Oct 3, 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 lists PDF, Office files, images, audio, video, email, and EPUB among its input formats; xberg also describes archive processing, URL ingestion, and source-code extraction.
- docling exports Markdown, HTML, WebVTT, DocTags, DocLang, and lossless JSON; xberg offers plain text, Markdown, Djot, HTML, JSON tree, and DocTags.
- Both provide a CLI and MCP server; docling also has a Python API and API server, while xberg offers a REST API and language bindings.
- Both are MIT-licensed and not archived. docling reports 68.3k stars and 5k forks; xberg reports 9.4k stars and 588 forks.
- Some xberg capabilities depend on optional Cargo features, runtimes, or models; docling notes that parsing capabilities vary by format and pipeline, and that individual models may have separate licenses.
Choose docling if you…
- need a Python library and CLI for converting documents into a unified representation.
- want PDF structure extraction, OCR, and exports such as Markdown or lossless JSON.
- need local processing for sensitive or air-gapped environments.
Choose xberg if you…
- want a Rust-based engine with bindings for multiple programming languages.
- need a REST API, CLI, library, or MCP server for document extraction.
- plan to extract source-code structure or process archives recursively.
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.