kreuzberg

A polyglot document intelligence framework with a Rust core. Extract text, metadata, ima…

Extract text, metadata, and code intelligence from 90+ file formats and 300+ programming languages at native speeds without needing a GPU. Key Features Code intelligence – Extract functions, classes, imports, symbols, and docstrings from 300+ programming languages via tree sitter. It has reached 8,384 GitHub stars, written primarily in Rust.

Why now: Sustained developer attention keeps it in the tracked pool; GitHub activity is the current lead signal.

• 8,384 GitHub stars, 494 forks — verifiable at github.com/kreuzberg-dev/kreuzberg.
• Primary language Rust; topics: bun, csharp, document-intelligence, elixir.
• Licensed NOASSERTION.

Considerations: Solid adoption (8,384 stars) but quiet cross-source signal right now — established utility more than a current breakout.

EARLY MOMENTUM · Research: Adoption is real but cross-source confirmation is thin — a short hands-on trial (Rust) will tell you more than the metrics.

Sources: kreuzberg-dev/kreuzberg on GitHub · Project homepage