N

natural-language-processing

ChronicleCRM is an AI-native relationship intelligence platform designed to turn every lead, interaction, and decision into a fully traceable record. Built around natural language capture, prospect memory, and modular industry workflows, it combines CRM functionality with human accountability and auditable AI assistance. The system ensures that every recommendation is explainable, every action has an owner, and every workflow is transparent from input to outcome. https://roxanneardary.com/chroniclecrm/

LumenAudio is a modular, AI-driven audio mesh for modern vehicles that unifies music, radio, podcasts, and self-hosted media into a single intelligent system. Built around a plugin-based architecture, it integrates paid streaming services and open-source platforms through secure adapters while using voice-first natural language control and context-aware AI to adapt playback to driving conditions, user behavior, and real-time intent. https://roxanneardary.com/lumenaudio/

NeuroText is an open source AI-powered platform that lets you build, collaborate, and execute projects through any messaging service — including SMS, WhatsApp, iMessage, Signal, Telegram, Slack, and Discord. It turns natural language prompts into code, apps, scripts, and projects instantly. With AI-assisted coding, multi-platform integration, collaborative tools, secure execution, and extensibility through plugins, NeuroText makes coding accessible, interactive, and conversational. https://roxanneardary.com/neurotext/

A natural language API that delivers podcast info for the Oremi Personal Assistant.

https://demsking.gitlab.io/oremi-kansa-agent

A natural language API that returns radio stream info for the Oremi Assistant.

https://demsking.gitlab.io/oremi-rediyo-agent

Multi-source RAG pipeline with hybrid vector + keyword retrieval, LLM-powered concept knowledge graph, adaptive search weighting, and evaluation framework.

[2025] European news intelligence platform with dual-layer AI sentiment analysis. Tracks media narrative shifts across 12 sources using VADER baseline + Gemini nuance, vector embeddings for semantic search, and interactive relationship mapping with real-time trend visualization.

This project is designed to analyze text for the presence of sarcasm. It uses machine learning models to classify input text and determine whether it contains sarcasm.

The project utilizes the following technology stack:

FastAPI - for creating the API interface and handling requests Docker - for packaging the application and its dependencies into a container Machine learning models for text sarcasm classification

Natural Python is an LLM REPL which is an intermediary between you (who speaks in natural language) and the computer (who speaks Python).

Java implementation of some of the commonly used algorithms in the realm of "Natural Language Processing".

Your own API endpoint to perform NLP functions like semantic search, sentence embedding, etc.