Open-source alternatives to Franc

Kreuzberg is a document extraction engine that converts PDFs, Office files, images, and over 90 other formats into clean, structured text and metadata. It is built around a compiled Rust core that can be used as a native library, a command-line tool, a REST API server, or a WebAssembly module for browser-based processing. The system is designed to run entirely on self-hosted infrastructure, with no data leaving the user's environment. What distinguishes Kreuzberg is its breadth of integration surfaces and its pipeline architecture. It exposes extraction capabilities through native bindings fo

Chinese-Vicuna is a Chinese large language model and instruction-following AI based on the LLaMA architecture. It is specifically designed for natural language understanding and generation in the Chinese language, utilizing an instruction-tuned model to follow complex user prompts across conversations. The project provides a LoRA fine-tuning framework and quantization systems to enable model adaptation and inference on consumer hardware. It implements quantized inference to reduce memory usage on both CPUs and GPUs, supported by a low-level C++ implementation to minimize system resource requi

搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。

DeepLX is a self-hosted translation API server that provides free access to DeepL translation services without requiring a paid API token or account. It functions as a token-free proxy, enabling programmatic text translation between languages through a single HTTP endpoint. The server accepts JSON-based requests with source and target language parameters, supporting automatic source language detection and validation of language codes. It processes each translation request independently in a stateless manner, and offers optional bearer token authentication to restrict access to authorized clie

py-googletrans is a Python translation library that serves as a wrapper for the Google Translate service. It provides programmatic tools for automated text translation and language detection. The library includes a language detection tool to identify the source language of a text string when the origin is unknown. To maintain stable connectivity, it utilizes translation request routing to direct traffic across alternative service domains. The project covers core translation services, including the ability to convert single strings or batches of text into specified destination languages.

Write-good is a command-line text analysis tool and English prose linter designed to identify grammatical errors and stylistic weaknesses. It functions as a readability optimization tool that scans documents to identify passive voice and wordy phrases. The system serves as a customizable prose style checker, allowing for the definition of specific language rules and forbidden terms to enforce project-specific writing guidelines. The tool provides capabilities for automated text analysis, style guide enforcement, and technical writing quality improvement. It supports the integration of custom

Presidio is a PII detection and anonymization framework designed to identify and mask personally identifiable information in text. It functions as a PII recognition pipeline and a data masking engine, using a combination of machine learning, regular expressions, and rule-based logic to locate sensitive entities. The system acts as an NER model orchestrator, allowing for the integration of external named entity recognition models and PII detectors to support multi-language privacy scrubbing. It employs a plugin-based recognizer architecture that can be extended with custom recognizers, deny-li

PhotoPrism is a self-hosted digital asset management platform designed to organize, classify, and manage large collections of photos and videos on personal infrastructure. It functions as a private alternative to cloud-based services, ensuring that all media remains under the user's control. The platform utilizes neural-network-based media analysis to automatically detect objects, faces, and locations, providing a comprehensive, AI-powered approach to library organization. The project distinguishes itself through its containerized architecture, which simplifies deployment and lifecycle manage

This repository is a comprehensive collection of reference implementations and sample libraries for the Universal Windows Platform. It provides practical examples of how to use Windows Runtime APIs to build cross-device applications, including detailed guidance on XAML-based declarative user interfaces and DirectX-integrated rendering. The project distinguishes itself by providing a wide array of hardware integration suites, covering low-level communication with USB, Serial, I2C, SPI, and GPIO peripherals. It includes specialized implementations for mixed reality holographic rendering, advanc

Qwen2-VL is a multimodal large language model and vision language model designed to process and reason across text, images, and video content. It functions as a visual reasoning engine and a visual agent framework, capable of interpreting visual data to perform object detection, document parsing, and spatial reasoning. The model is distinguished by its ability to act as a video understanding model, processing hour-long videos with second-level indexing and event recall. It further differentiates itself through a visual agent capability that interacts with software interfaces and robotic hardw

pdfminer.six is a programmatic tool for extracting text, layout information, and metadata from PDF documents into machine-readable formats. It functions as a document parser that converts internal PDF objects and structures into accessible data objects for analysis. The project includes utilities for decrypting RC4 and AES encrypted files to enable content extraction. It also provides a layout analyzer to identify fonts, colors, and text locations to determine the organizational structure of pages. The system covers a broad range of extraction capabilities, including the retrieval of embedde

LanguageTool is a multilingual grammar and style checking engine designed to detect spelling, grammar, and writing errors across multiple languages. It provides automated proofreading capabilities that can be deployed as a self-hosted server or executed as a standalone local desktop application. The project distinguishes itself through a flexible rule development framework, allowing linguistic patterns to be defined via XML or implemented as custom Java classes. It utilizes n-gram frequency modeling for confused word detection and supports neural word embeddings to improve disambiguation betw

openai-translator is a cross-platform translation tool and language learning utility available as a browser extension and desktop application. It functions as a client for large language model APIs to translate, summarize, and polish text across different digital environments. The project differentiates itself by integrating optical character recognition to translate text extracted from images and screenshots. It also includes a language learning workflow that allows users to save new vocabulary to a digital book and use text-to-speech synthesis for pronunciation. The tool provides broad tex

This repository provides the pre-trained neural network and legacy data files used by Tesseract to recognize and extract printed text from images. It serves as a multilingual training data repository and a collection of Long Short-Term Memory models designed for high-accuracy optical character recognition across various global scripts and languages. The data includes specialized models for analyzing image layouts to determine text rotation and script direction. It provides the necessary language-specific datasets and linguistic patterns required to enable Tesseract OCR engines to function. T

python-goose is a Python library for web scraping and content extraction. It functions as an HTML boilerplate remover and article parser designed to isolate primary text and metadata from web pages by stripping away navigation, layout noise, and non-essential elements. The tool features multilingual processing capabilities, utilizing language-specific stop-word analyzers to identify and extract primary content across different languages. It also identifies and collects embedded media, including source URLs and embed codes for lead images and videos associated with an article. The library cov

MNBVC is a dataset pipeline and toolkit designed for the collection, cleaning, and normalization of massive text and code corpora used to train large language models. It provides specialized tools for harvesting source code, commit histories, and repository metadata from version control platforms, alongside a multilingual text corpus collector for gathering parallel text and academic papers. The project distinguishes itself through comprehensive capabilities for processing diverse document types, including a PDF-to-text converter that transforms complex layouts and formulas into structured JS

CopyTranslator is a clipboard-based translation tool and multi-engine translation client that monitors the system clipboard to provide automatic language conversion. It functions as an assistant that integrates large language models, cloud translation APIs, and digital dictionaries to produce context-aware translations and side-by-side reading views. The application includes a specialized PDF text cleaner to remove formatting artifacts and line breaks from copied content. It also features an optical character recognition extractor to convert images or screen captures into editable text for im

Pretext is a canvas-based text layout engine designed to calculate precise text dimensions and line breaks for custom rendering. It serves as a rich text measurement tool and a cross-browser typography normalizer, enabling the determination of pixel-perfect widths and heights for mixed inline content without relying on browser CSS. The project distinguishes itself through its ability to handle complex typography and dynamic layouts. It implements language-specific segmentation rules for CJK and Hangul scripts and corrects emoji width variances between DOM and canvas rendering. Additionally, i

This is a scikit-learn automated machine learning framework designed to optimize model selection and hyperparameters. It functions as an automated model selector and hyperparameter optimization tool for classification and regression tasks, utilizing an automated ensemble builder to combine high-performing models for increased predictive accuracy. The system features a distributed search engine that uses Dask for parallel machine learning optimization across CPU cores or clusters. It implements a budget-based evaluation strategy through successive halving to prioritize promising model configur

Yi is a bilingual language model and foundation model designed for natural language processing, reasoning, and reading comprehension in both English and Chinese. It is built as a transformer-based architecture capable of general purpose text generation and conversational tasks. The model is distinguished by its ability to function as a long context system, processing and analyzing extended input sequences up to 200k tokens. It also supports quantized versions that use low-bit precision to reduce memory footprints, enabling execution on consumer-grade hardware. The project covers a broad rang

Agent Squad is a multi-agent system orchestrator and language model agent orchestration framework. It serves as an AI workflow automation engine and tool integration layer designed to coordinate teams of specialized agents to solve complex tasks through routing, parallel execution, and state management. The project is distinguished by its ability to dynamically compose purpose-specific agents on-demand and route requests based on intent, language, or domain expertise. It supports advanced coordination patterns, including parallel subtask distribution, sequential task pipelines, and the abilit

GLM-4 is a large language model and fine-tuning framework designed for human-like text production, complex reasoning, and multilingual conversation. It functions as a multimodal system capable of processing high-resolution visual content and as a long-context model designed to analyze documents with a context window of up to one million tokens. The project differentiates itself through a function calling interface that enables AI agent development by connecting the model to external APIs and real-time web browsing. It includes specialized capabilities for generating functional programming cod

Dango-Translator is an OCR translation system and multi-engine translation client designed to extract text from images or screens and replace it with translated content. It functions as an image text translator and real-time screen translator, utilizing optical character recognition to convert text between different languages automatically. The software distinguishes itself through coordinate-based image typesetting and a glossary manager. These tools allow for the replacement of original image content with translated text in the same area and the use of specialized dictionaries to ensure con

This application is a cross-platform desktop utility designed for automated translation, optical character recognition, and speech synthesis. It functions as a modular client that integrates various local and remote language services, allowing users to process text through hotkeys, clipboard monitoring, or direct input. The software distinguishes itself through a plugin-based architecture and a built-in automation framework. By exposing a local network interface, it enables external applications and scripts to programmatically trigger its translation and recognition workflows. Users can furth

EasyOCR is a deep learning-based computer vision library designed to perform optical character recognition on images and video frames. It functions as a comprehensive pipeline that automates the transformation of visual text into machine-readable strings, enabling the digitization of physical documents, forms, and receipts into searchable data. The engine distinguishes itself through a multi-stage processing workflow that combines convolutional neural networks for spatial feature extraction with sequence-based decoding mechanisms. This architecture allows the system to identify and interpret

Sonic is a high-performance, lightweight search backend designed to provide real-time full-text search and autocomplete capabilities for applications. It functions as a persistent indexing server that maps text terms to object identifiers, allowing developers to integrate rapid search functionality without storing raw document content directly within the search engine. The system distinguishes itself through a specialized graph-based index that enables real-time word prediction and typo correction. Communication is handled via a custom, low-latency binary protocol over raw TCP sockets, which

Newspaper is a Python library designed for scraping, parsing, and analyzing web-based information. It functions as a framework for automated news aggregation and large-scale web content extraction, providing tools to download, clean, and structure text, metadata, and media from diverse online sources. The project distinguishes itself through a pipeline-oriented architecture that combines heuristic-based content extraction with natural language processing. It automatically identifies and isolates article bodies from web page boilerplate while simultaneously performing language detection, keywo