Xberg.io

Xberg

Open-source content intelligence with a Rust core and native bindings for every major language.

Ecosystem

xberg — the open-source content-intelligence engine: text, tables, and metadata from 100+ formats, with OCR, transcription, and code intelligence.
crawlberg — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
html-to-markdown — fast, lossless HTML→Markdown engine.
liter-llm — universal LLM API client with native bindings and a catalog of 170+ providers.
tree-sitter-language-pack — tree-sitter grammars for 300+ languages and code-intelligence primitives.
sceptre — EasyOCR's accuracy in a single Rust binary: CRAFT text detection and gen2 CRNN recognition over ONNX, with no Python runtime.
alef — the polyglot binding generator that produces every per-language binding across the polyglot repos.
sdks — official client SDKs for the extraction API served by Xberg Enterprise and Xberg Pro.

Polyglot — xberg, crawlberg, html-to-markdown, liter-llm, and tree-sitter-language-pack each have one Rust core, and alef generates their bindings for every major language, so each binding shares one API over the same core.
Runs anywhere — use xberg as a library, CLI, REST API, MCP server, or Docker image; it runs on CPU by default, with no GPU required.
Built for RAG — xberg ships chunking, local or provider-hosted embeddings, and reranking; tree-sitter-language-pack splits code into syntax-aware chunks.
MIT licensed — every repository above is MIT; bundled third-party components keep their own licenses (see each repo's ATTRIBUTIONS.md where present; xberg also ships THIRD_PARTY_LICENSES.md).

Built with care in Kreuzberg, Berlin.