Show HN: Kreuzberg Cloud – ultra fast content intelligence – in public beta

Category: library

Tags: text-extraction, code-intelligence, rust, ocr, polyglot, document-parsing, llm

Score: 8.0/10 (Innovation: 7, Technical: 9, Documentation: 8, Utility: 8)

Kreuzberg is a high-performance Rust-based library and cloud service for extracting text, metadata, and code intelligence from over 91 file formats and 306 programming languages. It stands out for its polyglot nature with bindings for 16+ languages, innovative use of tree-sitter for code analysis, and a unique token-efficient TOON wire format designed for LLM pipelines.

Target audience: backend devs, data engineers, ml engineers, devops

Repository: https://kreuzberg.dev · Rust · NOASSERTION · 8343 stars

View on Hacker News