xberg

xberg-io/xberg

Polyglot document intelligence framework with a Rust core.

8.6k

Stars

508

Forks

12

Open issues

28

Watchers

Rust MITLast pushed Jul 7, 2026

Overview

Extracts text, metadata, images, and structured information from various document formats using multiple programming language bindings including Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno), CLI, REST API, or MCP server.

Categories

Data & Retrieval

Tags

document-intelligence metadata-extraction pdf-extraction table-extraction text-extraction rag

Similar tools

JavaGuide

Snailclimb/JavaGuide

Java guide for backend interviews & AI application development covering system design, LLMs, Agents, and RAG.

157k 46kJavaScript

firecrawl

firecrawl/firecrawl

The API to search, scrape, and interact with the web at scale.

147k 8.5kTypeScript

langchain

langchain-ai/langchain

The agent engineering platform.

awesome-llm-apps

Shubhamsaboo/awesome-llm-apps

Shubhamsaboo/awesome-llm-apps

PaddleOCR

PaddlePaddle/PaddleOCR

Transforms images/PDFs into structured data for AI systems with high accuracy.

graphify

Graphify-Labs/graphify

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more)

Install

cargo add xberg

crates.io Docs / website

README

Xberg

Rust

Python

Node.js

WASM

Java

PHP

Ruby

Elixir

Dart

Kotlin

Extract clean text, tables, and structured data from documents and code — no format detection, no OCR setup, no st