Sign in Sign up
hex

kreuzberg

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

Latest release
4d ago
Releases
71
Known CVEs
0
First release
Jan 03, 2026
License
Elastic-2.0
View on Hex
Repository

Source

kreuzberg-dev/kreuzberg
Stars
8.5k
Forks
497
Open issues
8
Language
Rust
  • text-extraction
  • document-intelligence
  • metadata-extraction
  • pdf-extraction
  • pdfium
  • python
  • rag
  • table-extraction

Security score

No OpenSSF Scorecard available for this repository.

Packages from this repo

Insights

Activity

Total releases
71
Last 12 months
71
Cadence
~daily
Dependencies
3

Releases per month

last 12 months

Release mix

  • minor 9
  • patch 59
  • pre 2
71 releases
Dependencies

Depends on

4.9.9

Used by

Nothing tracked depends on this yet.

Releases
Version Released
4.9.9 patch
4.9.7 patch
4.9.5 patch
4.9.4 patch
4.9.3 patch
4.9.2 patch
4.9.1 minor
4.8.6 patch
4.8.5 patch
4.8.4 patch
4.8.3 patch
4.8.2 patch
4.8.1 patch
4.8.0 minor
4.7.4 patch
4.7.3 patch
4.7.2 patch
4.7.1 patch
4.7.0 minor
4.6.3 patch
1–20 of 71