Skip to content

@kreuzberg-dev Kreuzberg

Change the repository type filter

All

    Repositories list

    22 repositories

    • kreuzcrawl

      Public
      Rust
      •
      Other
      •0•4•0•0•Updated Apr 19, 2026Apr 19, 2026

    • kreuzberg

      Public
      A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and…
      rubypythonjava
      rubypythonjavarustgolangphpnodeelixircsharpffi
      Rust
      •
      Other
      •380•7.6k•10•1•Updated Apr 19, 2026Apr 19, 2026

    • kreuzberg-dev.r-universe.dev

      Public
      R-universe repository for Kreuzberg.dev
      0•0•0•0•Updated Apr 19, 2026Apr 19, 2026

    • homebrew-tap

      Public
      Ruby
      •1•0•1•0•Updated Apr 19, 2026Apr 19, 2026

    • alef

      Public
      Generate fully-typed, lint-clean language bindings for Rust libraries across 11 languages
      rubypythonc
      rubypythoncjavarustgolangphprtypescriptelixir
      Rust
      •
      MIT License
      •0•8•0•0•Updated Apr 19, 2026Apr 19, 2026

    • liter-llm

      Public
      Universal LLM API client — 142+ providers, 11 native language bindings, powered by Rust core
      pythonrustmachine-learning
      pythonrustmachine-learningstreamingtypescriptapi-clientpolyglotopenaillmanthropic
      Rust
      •
      MIT License
      •9•148•0•0•Updated Apr 19, 2026Apr 19, 2026

    • html-to-markdown

      Public
      High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kreuzberg team. Kreuzberg is a fast, polyglot document intelligence engi…
      htmlmarkdowntext-extraction
      htmlmarkdowntext-extractionhtml-convertertext-processinghocrmarkdown-converterrag
      HTML
      •
      MIT License
      •55•657•1•2•Updated Apr 19, 2026Apr 19, 2026

    • langchain-kreuzberg

      Public
      Langchain document loader for Kreuzberg
      airagdocument-intelligence
      airagdocument-intelligencellmlangchainkreuzberg
      Python
      •
      MIT License
      •0•4•0•0•Updated Apr 18, 2026Apr 18, 2026

    • tree-sitter-language-pack

      Public
      Comprehensive tree-sitter grammar compilation with polyglot bindings — Rust, Python, Node.js, Go, Java, Ruby, Elixir, PHP, C#, WASM, and CLI. 305+ languages.
      rubypythonjava
      rubypythonjavarustgolangsyntaxtree-sitterparsernodeelixir
      Rust
      •
      MIT License
      •52•332•0•0•Updated Apr 18, 2026Apr 18, 2026

    • actions

      Public
      Shared GitHub actions
      Shell
      •0•0•0•0•Updated Apr 17, 2026Apr 17, 2026

    • kreuzberg-txtai

      Public
      Kreuzberg integration for txtai — drop-in Textractor replacement and custom pipeline
      Python
      •
      MIT License
      •0•1•0•0•Updated Apr 16, 2026Apr 16, 2026

    • llama-index-kreuzberg

      Public
      LlamaIndex reader and node parser integrations for kreuzberg — 88+ format document extraction with element-aware splitting
      Python
      •
      MIT License
      •0•0•0•6•Updated Apr 16, 2026Apr 16, 2026

    • agno

      Public
      Build, run, manage agentic software at scale.
      Python
      •
      Apache License 2.0
      •5.3k•1•0•0•Updated Apr 14, 2026Apr 14, 2026

    • kreuzberg-crewai

      Public
      Extract text and metadata from 88+ document formats — PDF, DOCX, XLSX, HTML, images with OCR, and more — directly from your CrewAI agents.
      Python
      •
      MIT License
      •0•1•0•1•Updated Apr 14, 2026Apr 14, 2026

    • .github

      Public
      Kreuzberg is a fast, polyglot document intelligence engine with a Rust core. It extracts structured data from 88+ document formats using streaming parsers and b…
      rubypythonjava
      rubypythonjavarustgolangdatanodeffiwasmtesseract
      0•1•1•0•Updated Apr 10, 2026Apr 10, 2026

    • kreuzberg-spring-ai

      Public
      Spring AI DocumentReader integration for Kreuzberg document extraction engine
      Java
      •
      MIT License
      •0•1•1•0•Updated Apr 8, 2026Apr 8, 2026

    • kreuzberg-surrealdb

      Public
      Extract, chunk, and embed documents from 88+ formats directly into SurrealDB.
      embeddingsdocumentsrag
      embeddingsdocumentsragvector-searchsurrealdbkreuzberg
      Python
      •
      MIT License
      •1•11•0•0•Updated Mar 30, 2026Mar 30, 2026

    • haystack-integrations

      Public
      🚀 A list of Haystack Integrations, maintained by the community or deepset.
      139•0•0•0•Updated Mar 25, 2026Mar 25, 2026

    • haystack-core-integrations

      Public
      Additional packages (components, document stores and the likes) to extend the capabilities of Haystack
      Python
      •
      Apache License 2.0
      •248•0•0•0•Updated Mar 25, 2026Mar 25, 2026

    • ai-rulez

      Public
      MIT License
      •0•3•0•0•Updated Mar 25, 2026Mar 25, 2026

    • paddle-to-onnx

      Public
      C++
      •
      Apache License 2.0
      •0•1•0•0•Updated Mar 16, 2026Mar 16, 2026

    • pdfium-render

      Public
      A high-level idiomatic Rust wrapper around Pdfium, the C++ PDF library used by the Google Chromium project.
      Rust
      •
      Other
      •118•2•0•0•Updated Dec 25, 2025Dec 25, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.