xberg-io/xberg

Project overview

A polyglot document extraction library providing 15 language bindings around a unified Rust core to extract text, tables, and metadata from 97+ formats without requiring manual OCR configuration. It supports CLI, library, REST API, and MCP server interfaces for developers building document processing pipelines.

Project type

MCP · RAG · Document Processing

Use cases

Documents & Office · Knowledge Q&A · Data Analysis

Deployment

Refer to project documentation

License

MIT

Best for

• Developers, data teams, and AI engineers who need to extract structured data and clean text from varied document formats for analysis or RAG pipelines.

Key capabilities

• Extracts clean text, tables, and metadata from 97+ formats including PDFs, Office documents, images, HTML, email, and archives.
• Runs as an MCP server exposing 9 extraction tools, 3 prompts, and 4 resources for IDE agents like Claude or Cursor.
• Runs as a REST API server handling all formats via a single POST endpoint and streaming large files.
• Performs NER, redaction, summarization, translation, QR code detection, page classification, and keyword extraction.

Limitations and risks

• Minimum hardware requirements and supported operating systems are not documented.
• Telemetry practices are not documented.
• Provider-hosted embeddings, structured extraction, and VLM OCR rely on optional external services from OpenAI, Anthropic, or Google, and local embeddings or reranking require optional ONNX models.

Getting started

• Installation is rated as easy, offering simple one-line commands for most languages such as pip install xberg or brew install xberg-io/tap/xberg. Users can extract text immediately using the CLI (xberg extract document.pdf) or by importing the library.

Evidence and sources

• GitHub project description: A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Avail…
• README: pip install xberg
• README: Extract from 97 formats | PDFs, Office, images, HTML, email, archives, scientific publications, and code — intelligent MIME detection, streaming for large files.
• README: Extract clean text, tables, and structured data from documents and code — no format detection, no OCR setup, no stitched-together libraries. One engine, 15 language bindings, runs…
• README: brew install xberg-io/tap/xberg

Reviewed at: 2026-07-16T11:13:03Z