Back to the knowledge base

kreuzberg

By dreamreal · 17 March 2026 · 277 lookups

Text

kreuzberg is a polyglot document intelligence framework with a Rust core; extracts text, metadata, and structured data from 88+ formats including PDF, Office, images, and archives; available as a library (Java, Python, TypeScript, Go, Ruby, C#, PHP, Elixir), CLI, REST API, or MCP server

URLs

https://kreuzberg.dev

Tags

parsing content-extraction rust

See also

tika