Xberg.io
Official@xberg-io · Germany
Polyglot document intelligence with a Rust core — extract structured data from 97+ formats
Agent Skills by Xberg.io
Showing 31 vetted skills indexed across 1 GitHub repositories.
xberg-ioextracting-code-structure
Extract functions, classes, imports, and exports from source files using ts-pack process.
xberg-iochunking-for-llms
Split source code into syntax-aware chunks for LLM context windows.
xberg-iodetecting-languages
Detect programming languages from files or snippets without extensions.
xberg-ioparsing-source
Generate syntax trees from source code using tree-sitter.
xberg-iomanaging-parsers
Manage tree-sitter parser cache with prefetch, list, inspect, and clean commands.
xberg-iotree-sitter-language-pack
Parse and analyze code across 306 languages using tree-sitter grammars.
xberg-iousing-the-mcp-server
Parse source code and detect programming languages via the tree-sitter-language-pack MCP server.
xberg-iofetching-and-converting-urls
Convert live URLs into Markdown with preprocessing and JSON output.
xberg-ioconverting-html
Convert HTML files to Markdown while preserving structure and formatting.
xberg-iohtml-to-markdown
Convert HTML files to Markdown with metadata and table extraction.
xberg-ioextracting-tables
Extract HTML tables and convert them to Markdown and structured JSON.
xberg-ioextracting-metadata
Extract titles, descriptions, language, and Open Graph tags from HTML documents.
xberg-iocrawling-a-site
Crawl websites with depth, page limits, concurrency, and robots.txt compliance.
xberg-ioautomating-the-browser
Automate browser interactions to scrape JavaScript-loaded dynamic web content.
xberg-ioserving-the-api
Serve crawlberg engine operations via an HTTP API with Firecrawl v1 protocol.
xberg-iomapping-urls
Parse sitemaps and extract links from HTML with custom filters and output formats.
xberg-ioheadless-fallback
Scrape JavaScript-heavy web pages using headless-Chrome as a fallback.
xberg-ioscraping-html-to-markdown
Convert a single web page to Markdown with metadata.
xberg-iocrawlberg
Scrape webpages and convert HTML content to Markdown.
xberg-iopicking-a-format
Determines optimal text/markdown/json/etc. output formats for extracted documents based on consumer needs.
xberg-iobatch-extraction
Extract text and metadata from multiple PDF files concurrently.
xberg-iochunking
Split text into chunks by size, overlap, and chunker type.
xberg-ioextracting-with-ocr
Extract machine-readable text from scanned PDFs and images using OCR engines.
xberg-ioxberg
Extract text, tables, and metadata from PDFs using OCR.
Frequently Asked Questions About Xberg.io
FAQPage SchemaWhat specific data extraction tasks does Xberg.io support?▼
Xberg.io enables the extraction of structured data from 97+ formats, including HTML table parsing, PDF text and metadata retrieval, and source code syntax tree generation. It supports advanced operations like OCR for scanned documents and converting dynamic web content into clean Markdown.
Which technical personas benefit most from these capabilities?▼
Data engineers, backend developers, and search infrastructure architects benefit from these capabilities. The platform is designed for those building retrieval-augmented generation systems, codebase analysis engines, or large-scale web scraping pipelines requiring high-fidelity document conversion and syntax-aware text chunking.
What are the primary dependencies for running Xberg.io operations?▼
The core operations rely on tree-sitter for source code parsing and headless-Chrome for rendering dynamic web content. Users must manage environment configurations for OCR engines and ensure compatibility with the provided Rust-based processing modules for local or server-side execution.