// rag · xberg-io/xberg

xberg

xberg é um projeto de RAG e conhecimento de código aberto de xberg-io (xberg-io/xberg no GitHub). Tem 9.388 estrelas no GitHub e 590 forks, é publicado sob a licença MIT e foi atualizado pela última vez no GitHub em 8 de outubro de 2026.

Polyglot document intelligence in Rust — extract text, tables and structured data from 106 formats.

★ 9,4 mil estrelas⑂ 590 forksMITatualizado out 2026

Ver no GitHub ↗Official site ↗

▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.

// dados do projeto

Dados do projeto

Repositório: xberg-io/xberg
Estrelas no GitHub: 9.388
Forks: 590
Licença: MIT
Última atualização no GitHub: 8 de outubro de 2026
Categoria: RAG e conhecimento
Tipo de ficha: Guia de instalação completo
Site oficial: Official site

// como funciona

Como funciona

Clarify your goal
Pick the binding for your stack (Python, Node, CLI, Docker or MCP) and the document types you need to extract, including whether OCR is required.
Get the project
Clone xberg-io/xberg from GitHub (or use the install path in the run steps below) and skim its README for the parts relevant to your goal.
Install and configure
Install the package for your language — for Python that is a single pip install — or pull the Docker image for the server modes.
Run your first task
Extract one real document and inspect the structured output (text, tables and metadata), then wire it into your pipeline or MCP client.

// recursos

Por que as pessoas gostam tanto

106 formats, one API

Extract text, metadata, images, tables and structured data from 106 formats across roughly 140 file extensions and 56 MIME aliases.

Fifteen bindings plus servers

Use it from fifteen language bindings, or as a CLI, REST API or MCP server for agent tooling.

Code intelligence for 371 languages

Beyond documents, xberg understands code across 371 languages for mixed code-and-docs corpora.

Multiple OCR backends

Choose Tesseract (native or WASM), PaddleOCR via ONNX, the pure-Rust Candle backend, or vision LLMs for scanned pages.

Structured LLM extraction

Pull schema-shaped structured data out of documents with LLM-backed extraction when rules are not enough.

Enrichment built in

Entity recognition, PII redaction (phone, email, SSN, cards, addresses), summarisation, translation and page classification are included.

// execute você mesmo

Execute você mesmo

Clone the repository
Get the source from the official GitHub repository for xberg.
```
git clone https://github.com/xberg-io/xberg.git
cd xberg
```
Install for Python
Install the Python binding exactly as the README's installation table shows.
```
pip install xberg
```
Or run the Docker image
Run the published container image for the server/CLI deployment modes.
```
docker run ghcr.io/xberg-io/xberg:latest  # see README for the exact mode arguments
```

// casos de uso

O que você pode criar

Extracting clean text and tables from PDFs and Office files for a RAG index
Redacting PII from documents before they are shared with an LLM
Giving a coding agent an MCP server that can read design docs and scanned PDFs
Processing a mixed archive of documents and source code with one extraction tool

// perguntas frequentes

Perguntas frequentes

Who maintains xberg?

xberg-io, through the xberg-io/xberg repository, with documentation at docs.xberg.io.

Is xberg free to use?

Yes — the project is open source under the MIT license as recorded for this listing. You can use, modify and distribute it under the MIT terms.

Does xberg need a paid API key?

Core extraction and OCR run locally with no key. Optional vision-LLM OCR and LLM extraction/enrichment use a provider you configure, with your own key.

How does xberg compare to calling a hosted document-parsing API?

Hosted parsers charge per page and require uploading documents. xberg is a local Rust engine you embed in your own stack across fifteen languages — you operate it yourself, and only optional LLM features need a provider.

How do I get started with xberg?

Os outros projetos de RAG e conhecimento com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se xberg não for o ideal para você.

MarkItDown★ 193,5 mil
MarkItDown — Microsoft tool that converts PDFs, Office files, images and more to clean Markdown for LLMs, MIT
Dify★ 157,8 mil
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or…
ragflow★ 91,6 mil
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…
PaddleOCR★ 90,8 mil
Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages
MinerU★ 82,5 mil
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms

// mais em rag

Mais em RAG e conhecimento

Projetos de RAG e conhecimento próximos no catálogo, os mais próximos em estrelas de xberg: continue explorando dos dois lados dele.

cocoindex★ 11,7 mil
Incremental engine that keeps RAG indexes and agent context fresh by processing only the delta.
paper-qa★ 9,3 mil
PaperQA2 — high-accuracy RAG for answering questions from scientific papers, with citations you can check.
txtai★ 13,0 mil
All-in-one AI framework for semantic search, LLM orchestration and language model workflows.
deeplake★ 9,2 mil
Deep Lake — a multimodal datalake and vector store for AI, with version control and training streaming.
LEANN★ 13,0 mil
The smallest vector index in the world: private RAG over everything on your laptop with 97% less storage.
Utopia★ 8,4 mil
Utopia — an open-source enterprise world model: a bitemporal knowledge substrate that learns from your documents and gives agents a governed, auditable memory

Baixe o xberg

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.

Ver no GitHub ↗← Mais ferramentas de RAG e conhecimento