Awesome GitHub RepositoriesSelective Text Processors

Markdown Here is a browser extension that enables rich text composition within web-based editors that lack native formatting support. By transforming plain text markdown syntax into rendered HTML, it allows users to draft professional emails and documents using standard markup, including headers, tables, and footnotes, directly inside their browser. The tool distinguishes itself through a bidirectional transformation engine that supports both the conversion of markdown to HTML and the reversion of rendered content back into its original source code. This state-preserving functionality allows

TextMate is a programmable text editor designed for software development and project management. It functions as a highly customizable environment where users can define language-specific behaviors, syntax highlighting rules, and automated workflows to suit their individual development needs. The editor distinguishes itself through a modular, bundle-based extensibility model that allows for deep integration with system shell commands. By piping document buffers through external scripts and command-line tools, users can perform complex text transformations, automate file lifecycle tasks, and b

Harper is a local English linter and grammar checker designed as an IDE writing assistant. It operates as a language server that provides real-time spelling and grammar analysis for markdown and code comments, processing all linguistic data on the local device to ensure privacy and eliminate cloud dependencies. The tool is specialized for technical documentation, featuring the ability to identify and ignore text within code fences and inline blocks to prevent false positives. It allows for personalized configuration through custom dictionaries and the use of suppression comments to exclude sp

chatGPTBox is a browser extension that integrates large language model chat interfaces and AI tools directly into the web browsing experience. It functions as an AI productivity toolkit and API client, allowing users to access AI assistants via a floating chat interface without leaving their active webpage. The project distinguishes itself by offering context-aware assistance and website-specific adaptations based on the current URL. It further enhances the browsing experience by displaying AI-generated responses alongside standard search engine results and providing a system to route chat re

Read Frog is an AI-powered immersive translation browser extension that functions as a bilingual reading assistant and text explanation tool. It connects to over 20 AI providers, including OpenAI and Anthropic, with configurable endpoints, API keys, and model settings, enabling translation and explanation of web content directly in the browser. The extension distinguishes itself through several integrated capabilities. It translates webpage content by placing translations directly next to the original text for side-by-side comparison, and can process content from PDFs, videos, and comics. It

Obsidian Copilot is an AI assistant plugin for Obsidian that brings conversational AI directly into your note-taking vault. It allows you to chat with multiple large language models, create and execute custom prompts, and edit notes through natural conversation, all without leaving your workspace. The plugin distinguishes itself by offering complete model flexibility, supporting OpenAI, Anthropic, Google, local, and self-hosted models with no vendor lock-in. It stores all chat history, system prompts, and custom commands as plain Markdown files in your vault, ensuring full data ownership and

Este proyecto es una hoja de referencia de ciencia de datos y guía de estudio de aprendizaje automático. Proporciona una colección curada de fórmulas, definiciones y resúmenes de modelos diseñados para una búsqueda rápida durante el desarrollo de proyectos y la preparación de entrevistas técnicas. El recurso se entrega como un recurso educativo PDF estático. Organiza frameworks técnicos complejos y conceptos teóricos de aprendizaje automático en un documento portátil de diseño fijo para asegurar una presentación visual consistente en diferentes dispositivos. El contenido cubre referencias de conceptos de aprendizaje automático y síntesis de conocimiento de ciencia de datos, específicamente adaptados para la revisión de exámenes y la síntesis de frameworks teóricos.

React Email Editor is a drag-and-drop visual builder for creating responsive email templates, built as a React embeddable component. It also serves as an AI-powered email designer, a collaborative email design tool, and a React component library for composing emails programmatically with JSX. The editor represents designs as structured JSON and supports multi-format rendering for email clients, web pages, and PDF. What distinguishes this editor is its deep AI integration: users can generate full email templates from natural language, rewrite text with chosen intent, produce multiple text vari

Fengshenbang-LM es un ecosistema de modelos de lenguaje chino y framework de preentrenamiento diseñado para el desarrollo y ajuste fino de modelos de lenguaje grandes de miles de millones de parámetros. Sirve como una tubería de procesamiento de lenguaje natural y plataforma de IA cross-modal capaz de generar contenido a través de diferentes modalidades, incluyendo generación de texto a imagen y predicción de estructuras de proteínas. El proyecto proporciona un adaptador de modelo específico del dominio para aplicar modelos preentrenados a industrias especializadas como la salud, las finanzas y el derecho. Utiliza un sistema de configuración distribuido y fragmentación de datos (data sharding) para gestionar el entrenamiento de modelos a gran escala a través de múltiples nodos de cómputo. El framework cubre una amplia gama de capacidades, incluyendo procesamiento de lenguaje natural en chino, transformación automatizada de texto y generación de contenido multimodal. Además, admite tareas de lenguaje general como traducción, programación y clasificación de texto. Los flujos de trabajo de predicción y ajuste fino (fine-tuning) posteriores se gestionan y ejecutan a través de una interfaz de línea de comandos.

VoiceInk is a system-wide speech-to-text dictation tool that converts spoken audio into text using local or cloud AI models. It functions as a local AI transcription engine and a context-aware voice assistant, allowing users to insert transcribed text directly into any active application on the operating system. The project distinguishes itself through the use of custom vocabulary management, which trains transcription engines to recognize industry-specific technical terms, professional terminology, and personal names. It further enhances output by using large language models to refine raw tr

Local-File-Organizer is a local-first file classification system that uses on-device machine learning models to categorize documents and media into structured directories. It functions as an automated file classifier and asset manager that leverages local inference to sort files based on content, meaning, and metadata. The project emphasizes privacy by performing all data processing and analysis on the local device, eliminating the need to send sensitive files to external cloud services. It utilizes local models to analyze text and image content to generate descriptive filenames and thematic

Scramble is an artificial intelligence-powered browser extension designed to assist with text processing, editing, and writing directly within web pages. It functions as a text editor that allows users to highlight content on any webpage and transform it through summarization, correction, or rewriting. The tool distinguishes itself by providing a provider-agnostic abstraction layer, enabling users to connect to various local or cloud-based language models by configuring their own authentication keys and endpoints. It supports custom prompt engineering, allowing users to define and save person

El modelado de temas contextualizado (Contextualized topic modeling) es un framework que integra arquitecturas de deep learning con distribuciones de frecuencia de palabras estadísticas para extraer temas coherentes de grandes colecciones de documentos. Combinando embeddings basados en transformers preentrenados con inferencia variacional, el sistema identifica patrones ocultos en el texto mientras mantiene la interpretabilidad de los modelos generativos tradicionales. La librería se distingue por mapear diversos idiomas en un espacio semántico compartido, permitiendo el descubrimiento y clasificación de temas a través de datasets multilingües sin requerir datos de entrenamiento específicos del idioma. Además, soporta modelado temático supervisado, permitiendo a los usuarios incorporar etiquetas de categoría conocidas o feedback humano durante el proceso de entrenamiento para dirigir el espacio latente hacia resultados específicos. El kit de herramientas proporciona una suite completa de utilidades para la preparación de datos de lenguaje natural, incluyendo limpieza de texto y la transformación de corpora en formatos duales adecuados tanto para representaciones vectoriales densas como para análisis de frecuencia dispersa. Estas capacidades soportan un rango de enfoques, incluyendo descubrimiento zero-shot y flujos de trabajo de clasificación iterativos con intervención humana (human-in-the-loop).