M

machine learning

🐤 AI chat & search summaries in DuckDuckGo, powered by the latest LLMs

🤖 AI browser extensions & userscripts to augment your web experience

Provides biomedical plotting archetypes fully interoperable with the matplotlib API.

AI chat & search summaries in Google Search, powered by the latest LLMs

AI chat & search summaries in Brave Search, powered by the latest LLMs

The main project for OctoMY™ - Ready-to-run robot software

Your very own Assistant. Because you deserve it.

💬 Epic prompts to turbo-charge your LLM chatbots.

A landcover classification tool based for humans. Classifier does "traditional" supervised and unsupervised learning. Image segmentation and soon also object detection

Bandicoot: user-friendly C++ library for GPU accelerated linear algebra, integrating with CUDA, OpenCL, Vulkan

Finally a smart RSS reader which doesn't suck ass or your data.

Hybrid cloud-edge ML system for predictive rain control with automated retraining, monitoring, and Raspberry Pi hardware actuation.

Genetics Algorithms and Genetic Programming library. https://genetics4j.org

Practical tasks on Deep Learning (DL) and Neural Networks (NN). 🤖

These projects form an open-source suite of AI infrastructure tools built for modularity, security, and self-hosted deployment, allowing users to maintain full ownership and control of their systems and data. They deliver interoperable AI functions including automation, data retrieval, encryption, and identity management that can be applied across many different industries. https://roxanneardary.com/ai-infrastructure/

The real estate specifications focus on shifting property data away from centralized listing platforms into locally hosted, machine-readable systems that users can fully control. Each property is structured as a modular dataset with consistent formatting for spatial, financial, and descriptive attributes, allowing it to be reused across applications and AI systems without platform dependency. On top of this foundation, the design incorporates encryption-first principles and blockchain-inspired verification concepts to ensure tamper-resistant records, traceable ownership changes, and secure handling of sensitive information, creating a hybrid model of local control with distributed-style trust and transparency. https://roxanneardary.com/real-estate-specifications/

Blockchain specifications define an institutional blockchain system built on distributed custody using Multi-Party Computation (MPC), where no single entity can access or control private keys. All transactions are governed through policy engines, role-based permissions, and full audit logging instead of centralized custody. It supports tokenization and multi-chain interoperability for real-world assets like real estate and financial instruments, with deployment across on-prem, sovereign cloud, and hybrid environments. The result is a secure, auditable infrastructure for programmable assets with built-in compliance and institutional control. https://roxanneardary.com/blockchain/

∞ Generate endless answers from all-knowing ChatGPT (on any topic!)

VERA (Video Extraction and Recognition Analysis) is a fully on-premises video OCR pipeline for extracting and recognizing text (license plates, street signs, billboards) from dashcam/driving footage. Built with PaddleOCR 3.x, OpenCV, FastAPI, PostgreSQL, and MinIO, with a PySide6 desktop GUI. Consists of two components: vera-engine (OCR pipeline, backend API, CLI) and vera-desktop (GUI layer). No cloud inference, all processing runs locally.