#nlp

sentenizer — rule-based NLP library for sentence segmentation with russian language support

Fast and accurate natural language detection. Detector written in Javascript. Nito-ELD, ELD.

NLTK Source

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.

A powerful dataset generator for Rasa NLU, inspired by Chatito

x402 Micropaid MCP Server — 51 Baidu AI tools for global developers. Pay-per-call with USDC, PayPal, or Alipay. No Chinese phone number needed.

Topic Modelling for Humans

Odinson is a powerful and highly optimized open-source framework for rule-based information extraction. Odinson couples a simple, yet powerful pattern language that can operate over multiple representations of text, with a runtime system that operates in near real time.

A Python wrapper of the official ROUGE-1.5.5.pl script and a re-implementation of full ROUGE metrics.

Hangul syllable decomposition and synthesis using jamo.

This is a text generation method which returns a generator, streaming out each token in real-time during inference, based on Huggingface/Transformers.

Python Library for AI/LLM Agent Development with UI-Driven Workflows and Actions

A small version of UniDic for easy pip installs.

Kex is a python library for unsupervised keyword extraction from a document, providing an easy interface and benchmarks on 15 public datasets.

Python implementation of the Rapid Automatic Keyword Extraction algorithm using NLTK.

结巴中文分词

A tool for connecting natural language commands with callbacks.

Gamified, event-driven Telegram bot for language learning. Built with Go microservices, it leverages gRPC, Kafka, PostgreSQL, and multi-instance Redis. Features algorithmic tasks, the Shiritori word game, smart caching, and a local NLP pipeline (Vosk/RHVoice/Ollama) for offline voice and AI chatting. Designed for high resilience and scale.

bag-of-words calculator in javascript

BERT score for text generation

FM-index is the fastest full text search algorithm using a compressed index file. This is FM-index for JSX/JS/AMD/Common.js.

Extract Keywords from sentence or Replace keywords in sentences.

Convert number words (eg. twenty one) to numeric digits (21)

Evidence graphs for parsing argumentation structure