Natural language processing - summarization, sentiment analysis, topic detection and more.

A React hook for analyzing text.

Simple yet fast concordancer in an Electron app

CmpStr is a lightweight, fast and well performing package for calculating string similarity

Summarizes emails with artificial intelligence. Based on the main topic of a message, the most important information is extracted.

Cloud-based service for uploading, scraping, and managing PDF/DOCX documents. Features include title sorting, content search with highlights, rule-based classification, and storage stats. Integrated with cloud platforms for scalable document analytics.

Twitter scraper and natural language processing platform

Advanced MCP server providing comprehensive text transformation and formatting tools. TextToolkit offers over 40 specialized utilities for case conversion, encoding/decoding, formatting, analysis, and text manipulation - all accessible directly within your AI assistant workflow.

The Open Data Innovation Project (ODIN) project seeks to make textual data repositories useable rather than simply available by processing and visualizing text data for human sensemaking.

Cloud-based service for uploading, scraping, and managing PDF/DOCX documents. Features include title sorting, content search with highlights, rule-based classification, and storage stats. Integrated with cloud platforms for scalable document analytics.

Next.js/SQLite app for qualitative coding and content analysis; prototype currently in (sometimes) working alpha.

ThreatShield AI-powered threat detection system using GROQ to analyze audio, image, and text data. It extracts insights and flags potential threats in real-time across multiple media formats.

Stylometric Stenography LLM Generation Attribution DRM/DLP

Custom Selected Word Count for Obsidian

A simple React app to count words, sentences, paragraphs, and estimate reading time in real time.

💬 A JS/TS framework for opening the possibilities for what you can do with text.

CLI for the CmpStr library supporting string normalization, similarity scoring, phonetic indexing, matrix comparison and more

This project is a Chrome extension that processes text from paragraphs on web pages using Natural Language Processing (NLP). It extracts noun phrases from the text and highlights them dynamically using a shadow DOM.

A Next.js web application for comprehensive text analysis and document insights. Upload PDF, DOCX, or TXT files to get detailed analytics including word statistics, sentiment analysis, readability scores, and interactive visualizations.

A web application that converts voice/audio into text using speech-to-text technology and applies Natural Language Processing (NLP) techniques for analysis, including word frequency, sentiment classification, and data visualization