Kreuzberg Ecosystem¶
Kreuzberg is an open-source document intelligence framework with a Rust core and bindings for many languages. It's maintained by the same team as a set of related open-source projects — each a separate tool for a different job, sharing the same Rust-first engineering approach. Explore their documentation:
- Kreuzberg Cloud — managed document extraction for AI pipelines: send a PDF, image, or Office file (80+ formats) and get back text, tables, and metadata. Includes a REST API, official SDKs (Python, TypeScript, Go, Dart), webhooks, and a no-signup sandbox.
- html-to-markdown — a high-performance, CommonMark-compliant HTML → Markdown converter.
- liter-llm — a universal LLM API client for 140+ providers, with bindings across languages.
- tree-sitter-language-pack — 300+ tree-sitter parsers with code intelligence and chunking.
- Kreuzcrawl — a high-performance web crawling engine with bindings for 11 languages.