xberg
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
What is xberg?
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
Overview of xberg
What it is
Xberg is a polyglot document intelligence engine with a Rust core. It extracts text, metadata, images, tables, and structured data from 107 formats across 141 file extensions, plus code intelligence for 371 languages. It provides 15 language bindings, a CLI, a REST API, and an MCP server.
Key features
- 107 document formats: PDFs, Office documents, images, HTML, email, e-books, and structured data across 141 file extensions with intelligent MIME detection.
- Audio & video transcription: Speech-to-text from MP3, M4A, WAV, WebM, and MP4 via Whisper ONNX (requires the
transcriptionfeature). - OCR on demand: Multiple backends (Tesseract, PaddleOCR, Candle, VLM) with fallback chains, confidence scores, and language auto-detection.
- Layout & tables: ML layout models (PP-DocLayout-V3, RT-DETR) and table structure (TATR, SLANet) reconstruct reading order and cell grids for clean Markdown.
- Code intelligence: Functions, classes, imports, symbols, and docstrings from 371 programming languages with syntax-aware chunking for RAG pipelines.
- Structured extraction: Schema-driven JSON from any document via local (Ollama, LM Studio, vLLM) or hosted LLMs, no prompt engineering required.
- Multiple deployment modes: Library, CLI (14 commands), REST API (
xberg serve), MCP server, Docker, and Helm.
Use cases
- Extracting text and tables from PDFs, scanned images, and office documents.
- Building RAG pipelines with code intelligence and embeddings.
- Transcribing audio and video files for content analysis.
- Automating document processing workflows via CLI or REST API.
- Integrating document intelligence into applications using one of 15 language bindings.
Getting started
sh pip install xberg sh brew install xberg-io/tap/xberg
License and pricing
MIT license. Open source.
Based on the project's public README and repository metadata.