xberg-io

xberg

Rust-core document-intelligence engine with 15 language bindings: turns 96 formats — PDF, Office, images, audio, code — into clean text, tables and RAG-ready chunks. Library, CLI, REST or MCP.

8,653 520 Rust MITupdated yesterday

ocr rag local

View on GitHub Dispute this mapping →

Curator's take

The polyglot pick: reach for Xberg when your stack spans Rust, Python, Node, Go, the JVM or WASM and you want ONE extraction engine instead of a per-language pipeline. Handles 96 formats — PDFs, Office, images, audio/video (Whisper), even source code (306 languages, syntax-aware chunking) — with pluggable OCR (Tesseract/PaddleOCR/VLM), no GPU, and library/CLI/REST/MCP entry points. It's the v1 successor to Kreuzberg. Don't reach for it if you only need max-fidelity parsing of messy scanned PDFs (a dedicated VLM like MinerU or olmocr wins there), or if you're Python-only and already committed to LlamaIndex's own readers.

Mapped by ShipWithAI editors · links verified

README.md

Xberg

Extract clean text, tables, and structured data from documents and

Continue your stack

What teams reach for next — and why each earns a place beside xberg. Ranked by curator confidence.

Pairs well with

Chroma

Open-source embedding database for building AI apps with retrieval.

Why it fitsNatural RAG pairing: Xberg does the front half (parse → clean text → syntax-aware chunks → local or hosted embeddings) and Chroma stores and retrieves those vectors. Xberg feeds the index; Chroma serves the queries.

LlamaIndex

Data framework for connecting custom data sources to LLMs — ingestion, indexing, retrieval.

Why it fitsXberg is a stronger document reader/extraction layer than LlamaIndex's built-in loaders; plug it in as the ingestion front-end (96 formats, OCR, transcription, chunking) and let LlamaIndex handle indexing, retrieval and query orchestration.

Alternative to See all + compare →

MinerU

Heavyweight document-to-markdown/JSON parser — PDFs plus Office (docx/pptx/xlsx) through layout analysis and OCR into LLM-ready output for RAG and agentic pipelines. 73k stars, self-hostable.

Why it fitsBoth turn documents (PDFs, Office) into LLM-ready text/JSON for RAG. MinerU is a heavyweight Python/VLM parser tuned for max-fidelity layout + OCR; Xberg is a lightweight polyglot engine spanning 96 formats and 15 language bindings with pluggable OCR. Pick MinerU for the hardest scanned/complex PDFs, Xberg for breadth and multi-language embedding.

olmocr

Open toolkit that linearizes messy PDFs — scans, tables, equations, handwriting — into clean ordered Markdown with a self-hosted vision-language model. Built for LLM training data and RAG ingestion.

Why it fitsSame end goal — clean, ordered Markdown from PDFs for RAG/training ingestion. olmocr is a dedicated self-hosted vision-language model that excels on scans, tables and handwriting; Xberg is a general extraction framework where OCR is one pluggable backend. Use olmocr when OCR quality is the bottleneck, Xberg when you need many formats and language bindings.

Unlimited-OCR

Baidu's open OCR VLM that parses entire multi-page documents in one shot — 'unlimited' long-horizon parsing pushing DeepSeek-OCR further. MIT weights on HF; serve via transformers, vLLM or SGLang.

Why it fitsEngine vs model: xberg parses 96 formats deterministically; Unlimited-OCR throws a VLM at whole documents. Same slot in a RAG ingestion pipeline.