# xberg-io/xberg

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 15 language bindings — Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript — plus CLI, REST API, and MCP server.

Repository: https://github.com/xberg-io/xberg
Canonical: https://ross.abutalabs.com/products/xberg
Homepage: https://docs.xberg.io
Language: Rust
License: MIT
License Family: permissive
Topics: text-extraction, document-intelligence, metadata-extraction, pdf-extraction, pdfium, python, rag, table-extraction, tesseract, ffi, golang, java, node, ruby, rust, wasm, elixir, php, bun, csharp
Last push: 2026-08-26T11:06:09+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 41
- inputs: {"age_days": 579, "days_push": 7, "days_rel": 29, "gap_med": 0.0, "n_releases_24m": 31}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9222, forks 576 (observed 2026-08-28T04:10:28.944780+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: parser, ocr, pdf, rag, nlp, machine-learning, web-scraping, cli, sdk, mcp, data-generation
- domain: artificial-intelligence, pdf, files, developer-tools
- platform: rust, python, go, jvm, dotnet, ruby, php, elixir, wasm, cli, cross-platform, windows
- tags: 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
- xberg-io/xberg (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.944780+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:23:16.802983+00:00, confidence not recorded.
  - readme: https://github.com/xberg-io/xberg (fetched 2026-08-28T04:10:28.944780+00:00, sha db3f274d6a09)
  - homepage: https://docs.xberg.io (fetched 2026-08-29T08:23:10.071348+00:00, sha 4d806a46bd59)
  - site_page: https://docs.xberg.io/getting-started/quickstart (fetched 2026-08-29T08:23:10.080489+00:00, sha 94c976b8b01e)
  - site_page: https://docs.xberg.io/getting-started/installation (fetched 2026-08-29T08:23:10.083468+00:00, sha 065d1fc5763c)
  - site_page: https://docs.xberg.io/features (fetched 2026-08-29T08:23:10.085872+00:00, sha 9854ab2097cc)
- Data as of 2026-08-30T08:39:29.467469+00:00.