L

localhost

ArcaneBuild is an open-source, high-performance visual application builder that lets developers and designers craft apps with wizard-level precision. Combining AI-assisted design, modular architecture, real-time previews, and ultra-efficient performance, ArcaneBuild enables fast, memory-light, and visually stunning multi-platform apps. Fully self-hosted and community-driven, it empowers anyone to build, collaborate, and deploy applications seamlessly. https://roxanneardary.com/arcanebuild/

EdgeLens is an open specification for privacy-preserving, edge-first computer vision systems that enable organizations to process sensitive visual data locally while participating in federated, community-driven model improvement. It is designed to scale from localhost deployments in classrooms and individual devices to enterprise and multi-institution infrastructures, ensuring that raw data remains within trusted environments while only validated insights and model updates are shared. https://roxanneardary.com/edgelens/

GuardianNX is a modular, AGPL-3.0+ open source home security operating system designed to eliminate vendor lock-in through fully replaceable hardware and software components. It integrates edge AI surveillance, encrypted sensor networks, and autonomous response systems into a unified, privacy-first platform that operates locally by default and remains fully functional without cloud dependency. https://roxanneardary.com/guardiannx/

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/

Sapient Eval is an open-source, AGPL-3.0+ compliant benchmarking framework for evaluating AI models across accuracy, speed, efficiency, and reasoning performance. Built around a modular, spec-driven architecture, it enables users to define industry-specific evaluation standards, run reproducible tests on locally hosted or remote models, and compare results transparently to establish measurable, empirical performance across synthetic intelligence systems. https://roxanneardary.com/sapient-eval/

Kova is a modular, AGPL-licensed AI governance framework designed to enforce structured, policy-driven control over artificial intelligence systems across consumer, household, and enterprise environments. It separates intelligence, execution, and policy enforcement into distinct layers to ensure all AI actions are transparent, auditable, and governed by configurable safety and access rules. https://roxanneardary.com/kova/

NodeHR is an open-source, self-hosted HR concierge and workflow automation platform that transforms employee questions into secure, policy-aware actions. It combines AI-powered assistance with structured workflows to handle PTO requests, policy lookups, onboarding guidance, and internal HR processes directly within tools like Slack, Teams, or web portals. Designed for organizations that own their stack, NodeHR prioritizes privacy, encryption, modularity, and full auditability while eliminating repetitive HR workload through automation. https://roxanneardary.com/nodehr/

SYSTEMIC AI FABRIC is a modular AGPL-3.0+ specification framework for designing and compiling regional AI systems. It enables jurisdictions to build AI infrastructure that is shaped by local conditions such as industry strengths, geography, regulation, and resource constraints. Rather than relying on universal models, the framework treats intelligence as a system that is generated, governed, and evolved within regional “natural labs,” producing adaptable and transparent AI architectures tailored to real-world environments. https://roxanneardary.com/systemic-ai-fabric/

Autonomous Loop is a self-hosted Continuous Improvement Operating System designed for air-gapped AI factories. It enables organizations to continuously monitor, evaluate, govern, and improve AI applications through observability, data drift detection, human review workflows, autonomous improvement agents, and intelligence lifecycle management while keeping models, data, and operations under full control. https://roxanneardary.com/autonomous-loop/

MindLedger for Real Estate is a modular, self-hostable real estate operating system that unifies CRM, listings, marketing, analytics, compliance, accessibility, and AI automation into a single open-source platform. Built under the AGPL-3.0+ license, it is designed for continuous evolution through community contributions, strict legal compliance, and a dual-AI architecture that supports both public-facing user assistance and agent-side operational intelligence. https://roxanneardary.com/mindledger-for-real-estate/

SolderSense is an open-source, privacy-first programmable mouse designed for full user control at every level—from hardware and firmware to macros and configuration. Built with auditable, reproducible components and a deterministic execution model, it eliminates telemetry, cloud dependency, and proprietary lock-in. It empowers users with secure, offline-first input control and optional local AI assistance, all while maintaining complete transparency and verifiability. https://roxanneardary.com/soldersense/

MeshCore is a modular, privacy-first infrastructure for managing digital identity, credentials, and secure authentication data across devices. Built as an encrypted, self-hostable system under the AGPL 3.0+ license, it unifies passwords, API keys, secure notes, and identity records into a connected identity graph. Designed with a strict modular architecture, MeshCore supports extensible components for autofill, sync, intelligence, and plugin-based expansion while keeping all sensitive data encrypted and under user control. https://roxanneardary.com/meshcore/

AuthenticAI is an open-source, locally hosted AI governance platform designed to keep intelligence local and decisions accountable. It provides a trust layer between AI systems, autonomous agents, enterprise data, and external tools through metadata filtering, data minimization, retrieval trust scoring, model routing, human approval workflows, and MCP governance. AuthenticAI enables organizations to deploy AI securely with transparency, control, and accountability. https://roxanneardary.com/authenticai/

Continuum Companion is a modular, locally hosted, open-source AI wellness and research platform that bridges Eastern medicinal traditions and Western medical knowledge through transparent, source-backed educational guidance. Designed to support - never replace - licensed medical care, the platform provides AI-assisted research, integrative question-and-answer systems, wellness planning, and private research archiving while prioritizing privacy, evidence transparency, and ethical AI development under the AGPL-3.0+ license. https://roxanneardary.com/continuum-companion/

Semantic Firewall is a zero-trust privacy layer for AI systems that transforms user prompts before they reach any large language model. It detects and redacts sensitive data locally, replaces it with deterministic tokens, and only sends abstracted semantic intent to the model. This ensures AI systems can reason over information without ever accessing raw personal, financial, or proprietary data, with full rehydration handled securely on the user’s side. https://roxanneardary.com/semantic-firewall/

ImageWorks is a modular, self-hosted, open-source visual asset management and production platform built for creative teams and production workflows. It provides tools for asset ingestion, image processing, prompt management, quality analysis, collaboration, automation, mockup generation, and commercial-ready exports, enabling organizations to manage the complete lifecycle of visual assets from creation through production. https://roxanneardary.com/imageworks/

StoneBack is an open-source, repairable rear-vision system designed for real-world vehicles, from passenger cars to industrial and agricultural equipment. Built with a split architecture separating a passive camera head from an interior compute node, it delivers high-quality, full-color imaging with deterministic performance, no cloud dependency, and long-term serviceability. The project prioritizes transparency, durability, and ownership, enabling users to build, modify, and maintain their own vehicle vision systems for decades of use. https://roxanneardary.com/stoneback/

Collection of simple client-side apps, each made with hand-written pure JavaScript and HTML

With docker, Traefik, Treafik.me and SSL

Transmitting a command from the local website to the Arduino board via USB as serial COM port