Skip to content

Ecosystem

Xberg Pro and Enterprise are proprietary, self-hosted platforms built on the Xberg ecosystem: open-source, MIT-licensed libraries for extraction, crawling, conversion and retrieval. Most of these projects have one Rust core, and alef generates their bindings for other languages.

Xberg is the open-source content-intelligence engine inside both commercial products. It extracts text, tables and metadata from 107 formats, with OCR and code intelligence. Use it as a library, CLI, REST API, MCP server or Docker image. Documentation is at docs.xberg.io.

Pro and Enterprise customers can use Core alongside their deployment at no cost. See Core, Pro and Enterprise.

The official client SDKs cover the extraction API served by Pro and Enterprise. One client library targets either deployment. Full API documentation is at docs.sdks.xberg.io, and SDKs shows how to install and configure them here.

Project What it does
crawlberg Web crawling and scraping with HTML to Markdown conversion and a headless Chrome fallback. Documentation: docs.crawlberg.xberg.io.
html-to-markdown A fast, lossless HTML to Markdown engine.
liter-llm A universal LLM API client with native bindings and a catalog of 170+ providers.
tree-sitter-language-pack Tree-sitter grammars and code-intelligence primitives.
sceptre EasyOCR’s accuracy in a single Rust binary, with no Python runtime.
alef The polyglot binding generator behind the per-language bindings.

Where each project appears in the platform

Section titled “Where each project appears in the platform”
  • Acquire. Pro and Enterprise crawl with crawlberg and convert HTML with html-to-markdown. See Pipeline.
  • Extract. Xberg and tree-sitter-language-pack do the extraction work in every tier.
  • Enrich. Structured extraction and LLM reranking reach model providers through liter-llm. See Structured extraction.