Projects sharing features with Kreuzberg

A fast, helpful, and open-source document parser

Textract is a multi-format text extraction tool and parser. It provides a unified interface to extract plain text from a variety of sources, including documents, images, and audio files. The system functions as a document content parser for PDFs and spreadsheets, an image text extractor using optical character recognition, and a speech-to-text transcriber for audio recordings.

PDF-Extract-Kit is a document extraction toolkit designed to convert PDF documents into structured formats such as Markdown, HTML, and LaTeX. It functions as a multi-stage parsing framework that combines a document layout analyzer, a formula recognition engine, an OCR text extractor, and a table extraction system. The project focuses on recovering complex document elements by translating images of mathematical formulas and tabular structures into editable source code. It utilizes model-driven layout analysis to identify structural elements in reports and textbooks while ignoring noise like wa

unioffice is a comprehensive document processing suite that provides a PDF document processor, an Open XML document library, a document security toolkit, and a document content extractor. It is designed to programmatically create, read, and modify Word, Excel, and PowerPoint files, as well as generate and edit PDF documents. The project is distinguished by its native language implementation of the Open XML standard, which removes native binary dependencies to simplify container deployments. It features advanced capabilities for digital document security, including hardware-based PDF signing,

WeKnora is a multi-tenant retrieval-augmented generation (RAG) knowledge platform and autonomous AI agent framework. It transforms raw documents into queryable knowledge bases and integrates large language models with vector databases to provide grounded AI responses. The system also functions as a Model Context Protocol (MCP) tool server, exposing knowledge search and agentic capabilities to external AI clients. The platform distinguishes itself through an autonomous agent framework that utilizes iterative reasoning, tool calling, and web search to solve multi-step tasks. It implements a sta

llmware is a Python framework for AI agent orchestration and model management, designed to coordinate multi-model workflows and autonomous agents. It provides a unified model catalog and standardized interface to execute specialized language models for complex research, analysis, and structured data generation. The project distinguishes itself through its heavy emphasis on local execution and quantized inference, allowing models to run on private infrastructure using CPU, GPU, and NPU acceleration via runtimes like ONNX and OpenVino. It features a specialized ability to translate natural lang

Kotaemon is an orchestration framework designed for building modular, agentic workflows that integrate document processing, retrieval-augmented generation, and multi-step reasoning. It provides a comprehensive platform for developing document-based question answering systems, allowing users to chain language models, prompt templates, and external tools into complex, automated pipelines. The system distinguishes itself through a highly modular architecture that emphasizes component-based composition and schema-driven data exchange. It supports autonomous agents capable of decomposing complex q

FOCA is a digital forensics metadata analyzer and open-source intelligence tool used to extract hidden information from various document types. It functions as a metadata extraction tool that isolates technical data and EXIF information from PDFs, office documents, and SVG files. The system integrates an open-source intelligence scanner that identifies and downloads target files from the web using multiple search engine APIs. This allows for the automated discovery and acquisition of remote web assets for batch analysis and digital evidence gathering. The software provides capabilities for d

MisakaTranslator is a real-time game translation tool designed to extract text from games and manga and provide machine translations via external engines. It functions as a text extractor using both memory hooking to retrieve raw text directly from running processes and optical character recognition to convert images of in-game text into editable strings. The tool includes a speech synthesizer to read translated dialogue and sentences aloud. To maintain accuracy, it utilizes a custom translation dictionary to manage specialized word lists and manual phrase mappings for character names and loc

Text-Grab is a desktop utility that captures text from screen regions, images, PDFs, and native user interface elements using on-device optical character recognition (OCR) and Windows UI Automation. It processes text entirely locally without sending data to external services, and extracts text directly from UI controls with perfect accuracy by reading the accessibility tree. The application also includes a persistent snippet dictionary for instant retrieval of frequently used text via a configurable system-wide hotkey. The tool supports building reusable extraction workflows by saving capture

Tesseract is an optical character recognition engine and tool designed to convert printed or handwritten text from images into machine-readable digital text. It functions as a multilingual text extractor and a document digitization pipeline that transforms scanned images into structured digital formats. The project includes a framework for training custom scripts and language-specific models, allowing the engine to recognize new languages or unique fonts through custom training data. Its capabilities cover automated text extraction, digital archive digitization, and the export of recognized

This project is a multi-protocol API simulation and mocking system designed to replace external dependencies during development and testing. It provides an API mocking server, a network traffic proxy, and specialized simulators for language model services and identity providers. The system distinguishes itself through deep AI simulation capabilities, including the emulation of language model providers and Model Context Protocol servers using JSON-RPC 2.0. It supports multi-turn conversational logic, state tracking for AI chat APIs, and the visualization of agent execution through call graphs

GOT-OCR2.0 is an end-to-end optical character recognition system and document text extractor. It utilizes a unified transformer architecture to recognize and extract plain and formatted text from diverse images and documents. The system features a multi-crop processing method that divides high-resolution or dense documents into smaller sections to maintain recognition detail. It also includes a renderer that transforms recognized text into HTML to preserve the original structure and layout of the document. The project provides a framework for fine-tuning pre-trained models on custom datasets

Layout-parser is a deep learning document layout parser and image analysis framework. It provides a toolkit for extracting structural information and layout patterns from scanned documents and digital images, transforming them into programmatic data structures for automated analysis. The framework integrates layout detection with optical character recognition to convert tabular regions into machine-readable data. It utilizes neural networks to identify and classify structural elements within document images without relying on manual rule-based systems. The system covers a broad range of docu

OpenViking is a multi-tenant context server and knowledge base administration system designed to provide AI agents with persistent long-term memory. It enables the indexing of diverse documents and codebases to support retrieval-augmented generation, allowing agents to recall past interactions, user preferences, and learned experiences across sessions. The project is distinguished by its use of a URI-based virtual filesystem to organize memories, resources, and skills. It implements a tiered context loading system that balances retrieval precision with token budgets by structuring data into a

This project is a PDF data extraction tool and document preprocessor designed to convert PDF files into structured formats such as Markdown, JSON, and HTML. It functions as an OCR document parser for scanned files, an accessibility automator for generating PDF/UA compliant metadata, and a loader for AI orchestration frameworks like LangChain. The software distinguishes itself through specialized handling of complex document elements, including the conversion of mathematical formulas into LaTeX and the generation of natural-language descriptions for charts and images. It utilizes recursive seg

pypdf is a Python library for parsing, manipulating, and generating PDF documents. It provides high-level operations for document processing, such as merging multiple files into one or splitting a single document into smaller files. The project includes specialized tools for managing interactive elements, including the creation and modification of annotations, hyperlinks, and form fields. It also supports advanced metadata management, allowing for the extraction and modification of standard document properties and XML-based XMP metadata. Beyond basic structural changes, the library covers pa

This project is a reference implementation and application template for Retrieval-Augmented Generation (RAG). It integrates Azure OpenAI with Azure AI Search to enable conversational chat interfaces that provide grounded responses based on private enterprise data. The system is distinguished by its multimodal AI interface, allowing it to process and reason over combined text, image, and PDF content. It employs a hybrid search architecture that combines vector and keyword retrieval with semantic reranking to prioritize the most relevant documents for prompt augmentation. The project covers a

pdfminer is a Python library for parsing PDF files to extract text, analyze layouts, decrypt content, and convert documents into HTML or XML formats. It functions as a text extraction engine and layout analysis tool designed to retrieve characters and words while preserving the structural organization of the original document. The project provides utilities for converting PDF content into structured HTML or XML to maintain visual layout and a decryption tool for unlocking restricted documents using encryption keys. It identifies the positions and groupings of text elements to reconstruct page

NeMo-Retriever is a framework designed for building end-to-end document ingestion and retrieval-augmented generation pipelines. It provides a suite of tools for processing, classifying, and structuring diverse file formats, transforming raw enterprise data into searchable information assets for generative artificial intelligence applications. The system distinguishes itself through its specialized capabilities for parsing complex document layouts, including tables, charts, and infographics, using integrated optical character recognition and multi-modal extraction. It utilizes a microservice-b

This project is a Python framework for building autonomous AI agents capable of executing independent tasks through goal-oriented instructions. It provides a library of tools for managing system operations and processing multimodal data. The framework features a sandboxed system execution environment that restricts shell commands and file access to protect the host system. It also includes an automated OCR text extraction pipeline for converting printed or handwritten text from images and documents into digital formats. Connectivity is handled through a modular tool integration system and a

Zerox is a multimodal document parser and OCR tool that uses vision models to convert PDF files and images into structured Markdown text. It functions as a visual layout extraction engine, leveraging large multimodal models to digitize documents while maintaining their original structural formatting. The system differentiates itself through the use of coordinate-based element mapping and multimodal layout analysis to identify structural elements like tables, charts, and headers. It utilizes rasterization to convert vector PDF pages into high-resolution bitmaps, ensuring consistent input for t

Paper2gui is a multi-modal AI toolkit and model GUI wrapper designed to deploy and run various artificial intelligence models through a visual interface. Its primary purpose is to provide a way to execute complex AI research papers and models without requiring manual software installation or coding. The project distinguishes itself by using a wrapper-based model interface that abstracts command line arguments into visual input fields, utilizing template-driven UI generation to create parameter sliders and forms based on the specific requirements of the underlying model. It includes a centrali

Upsonic is a Python framework and orchestrator for building autonomous AI agents. It provides the infrastructure to develop self-operating systems that execute complex workflows and manage tasks independently using a scripting language. The project functions as an agentic tool integration layer, connecting agents to third-party data sources and external service APIs through standardized communication protocols. To ensure security, it includes an isolated execution environment that restricts shell and file operations to a specific workspace to prevent path traversal and dangerous commands. Ad

localGPT is a private AI knowledge base and retrieval-augmented generation application. It provides a local document indexer, a hybrid search engine, and an inference interface to enable chatting with private documents and managing a self-hosted information repository without sending data to external servers. The system distinguishes itself through a dual-pass verification pipeline that ensures generated answers are grounded in retrieved sources, accompanied by explicit source attribution. It employs a hybrid retrieval approach combining semantic vector search with keyword matching and rerank

PDFPatcher is a specialized suite of PDF utility tools designed for editing navigational bookmarks, modifying document structure, managing metadata, and processing pages. It provides a toolkit for altering PDF structures and properties without changing the original content stream. The project is distinguished by its focus on bookmark management, featuring bulk editing and the ability to generate clickable bookmarks from visual tables of contents using optical character recognition. It also includes capabilities for font optimization through substitution and embedding to ensure consistent char

pdfplumber is a PDF data extraction library and layout analysis tool used to retrieve text, tables, and geometric objects from PDF files using precise coordinate-based analysis. It functions as a layout analyzer and table parser that identifies the bounding boxes and visual coordinates for every character and image on a page. The library distinguishes itself through visual debugging capabilities, allowing users to render PDF pages as images and draw annotations to verify the position of extracted data. It employs line and intersection analysis to identify cell structures and convert unstructu