xberg-io/xberg

Xberg is a document intelligence library that extracts text, metadata, images, tables, and structured data from documents across multiple formats using a Rust core with language bindings.

The tool solves the problem of processing diverse document types through a unified interface. Rather than integrating separate libraries for each format, Xberg provides a single polyglot system built on Rust that handles extraction across numerous file types. The core engine performs text extraction, metadata retrieval, image and table extraction, and structured data parsing, with support for optical character recognition through Tesseract integration and code intelligence across many programming languages.

Xberg suits projects that need to ingest documents programmatically without managing format-specific dependencies. It works well for document processing pipelines, retrieval-augmented generation systems, and applications requiring consistent extraction behavior across heterogeneous file types. The tool offers multiple access patterns: direct language bindings for integration into applications, a command-line interface for scripting, a REST API for remote processing, and an MCP server for integration with compatible tools. Teams working in Python, Node.js, Go, Java, Ruby, PHP, C#, Elixir, or other supported languages can use native bindings rather than wrapping external processes.

Development activity shows consistent maintenance with regular updates to the codebase. The project maintains comprehensive documentation and uses automated tooling for README generation and verification. The core Rust implementation receives ongoing refinement, and the binding ecosystem across multiple languages is actively supported. The tool includes both CLI and server deployment options, indicating attention to different operational contexts.