xberg-io/xberg

Health v2 · maintenance only

Adoption not part of the score

9400 stars · 590 forks observed · 2026-10-11

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Xberg is a polyglot document intelligence framework with a Rust core that extracts text, metadata, tables, images, and structured data from 100+ file formats, plus code intelligence for 371 languages. It ships 15 language bindings, a CLI, a REST API, and an MCP server, with OCR, audio transcription, web crawling, and LLM-based structured extraction built in.

Use cases

• extract text and tables from pdfs to markdown
• parse resumes and office documents into structured data
• ocr scanned documents into searchable text
• transcribe audio and video files with whisper
• build a rag pipeline over documents with embeddings
• extract entities and json matching a schema from documents
• crawl a url and extract page content
• parse functions and imports from source code files

When to choose

• you need one engine for many document formats instead of stitching libraries together
• you want native-speed extraction with bindings for your language of choice
• you need OCR, transcription, crawling, and structured extraction in a single API
• you want an MCP server or REST API for document extraction

When to avoid

• you only need simple pdf text extraction and a lightweight tool suffices
• your CPU lacks AVX/AVX2 and you need ONNX-dependent features like PaddleOCR or embeddings
• you need HEIC/AVIF decoding on wasm or android targets
• you require a pure-permissive license build since libheif is LGPL

Facets

framework · maturity active

parser ocr pdf rag nlp machine-learning web-scraping cli sdk mcp data-generation artificial-intelligence pdf files developer-tools rust python go jvm dotnet ruby php elixir wasm cli cross-platform windows document-intelligence text-extraction pdf-to-markdown table-extraction whisper-transcription ffi-bindings rest-api code-intelligence embeddings entity-extraction natural-language-processing retrieval-augmented-generation data-engineering nodejs docker linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="xberg-io/xberg")