H

human-ai-interaction

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention weights shift from serving a system prompt to serving an emergent interpersonal pattern — before harm occurs.

EnerAgent is an open-source, AI-driven energy management platform designed to optimize energy usage, reduce carbon emissions, and enable advanced predictive and strategic operations. It integrates real-time monitoring, multi-site optimization, AI-powered forecasting, human-AI collaboration, and sustainability tracking into a single modular platform. EnerAgent is built for industrial, commercial, and societal energy ecosystems, empowering organizations and communities to make smarter, greener, and more cost-effective energy decisions while fostering open innovation. https://roxanneardary.com/eneragent/

AIChauffeur is an open-source AI Driving Efficiency Coach designed to retrofit ICE, hybrid, and EV vehicles. It provides real-time driver coaching, predictive energy optimization, and modular integration with regen, HVAC, and accessory systems. AIChauffeur helps drivers maximize efficiency, reduce energy waste, and improve overall driving performance, all while remaining fully open-source and community-driven. https://roxanneardary.com/aichauffeur/

The Interpretation Layer is a modular, human-in-the-loop AI system that transforms structured moral interpretations of textual passages into modern, grounded human narratives. It uses a transparent pipeline where AI suggests ethical meanings, humans validate the intended moral, and the system generates narrative outputs based on that selection. Designed for auditability and neutrality, it functions as a computational layer between text and meaning rather than an authority on interpretation. https://roxanneardary.com/the-interpretation-layer/

Human Decision Specification (HDS) is an open, modular standard for building AI systems that keep humans in control of decision-making. It defines a structured workflow where AI systems ask clarifying questions, discover and confirm human intent, evaluate legal and compliance constraints, and provide transparent recommendations. HDS ensures that every significant action is approved by a human, fully auditable, and designed to prevent autonomous decision-making without oversight. https://roxanneardary.com/human-decision-specification/

CortexLoop is a human-in-the-loop AI orchestration system designed to keep all reasoning, planning, and execution fully transparent, structured, and under human control. It transforms AI from an autonomous or opaque assistant into a governed cognitive loop where multiple solution paths are generated, evaluated for risk and confidence, and returned to the user for decision-making. Every action is logged through a decision ledger, enforced by a policy engine, and constrained by strict system rules including AGPL+ licensing and attribution requirements. The result is a traceable, auditable AI system that prioritizes clarity, accountability, and human authority at every step. https://roxanneardary.com/cortexloop/

Covenant AI is an open-source artificial intelligence infrastructure platform focused on human authority, bounded autonomy, transparency, privacy, and accountable AI execution. Built as a complete alternative to traditional AI agent frameworks, Covenant AI ensures that every AI action is authorized, explainable, revocable, and verifiable — creating intelligence systems that remain fully accountable to the people they serve. https://roxanneardary.com/covenantai/

The Foundation for Deterministic Computing (FDC) is an open standards initiative dedicated to building reproducible, auditable, and human-governed computing systems. It defines modular specifications for deterministic execution, verifiable intelligence, structured knowledge, and transparent decision-making. The foundation provides a framework for ensuring that computational systems operate with consistency, traceability, and accountability across all layers of software and intelligent infrastructure. https://roxanneardary.com/foundation-for-deterministic-computing/

Axis Intelligence is an open-source, modular ambient AI platform designed to function as the central intelligence layer of a modern smart home. Built with a local-first approach, it combines real-time voice interaction, AI reasoning, voice cloning, and smart home automation into a unified system that users can fully control, extend, and customize. https://roxanneardary.com/axis-intelligence/

HelmOS is a modular, local-first operating layer that wraps existing AI agents with intent verification, human governance, trust management, workflow orchestration, auditing, and controlled self-improvement. Designed to keep humans at the center of decision-making, HelmOS ensures that actions remain explainable, accountable, and aligned with user intent while providing a standardized framework for building, managing, and governing intelligent agent systems. https://roxanneardary.com/helmos/

SandNet is a privacy-first, open source game creation and virtual world platform designed for creators, families, educators, and organizations. Built with modern security, encrypted user data, modular architecture, and age-based content categories, SandNet empowers communities to build games, create immersive worlds, collaborate on projects, host events, and share experiences while maintaining full ownership of their data and creations. https://roxanneardary.com/sandnet/

Taskivo is an open-source AI platform that turns real-world requests into structured, comparable service outcomes. It uses modular industry-specific “Taskivo Modules” and a real-time AI co-pilot to guide conversations, standardize service scopes, and normalize pricing and service data. This allows users to move from vague requests to clear, structured decisions and consistent results across any service category. https://roxanneardary.com/taskivo/

SynchroFab is an open-source, AI-driven smart factory platform (EC4P) that integrates edge-cloud intelligence, adaptive robotics, IoT, and sustainability features. Designed for modularity and continuous improvement, it enables factories to self-optimize, collaborate safely with humans, reduce environmental impact, and innovate autonomously. https://roxanneardary.com/synchrofab/

LatticeOS is a modular, human-in-the-loop operating system for governed multi-agent AI orchestration, designed to provide structured execution, deterministic workflows, and full auditability. Built around event-sourced transparency and explicit governance controls, LatticeOS enables intelligent systems where every agent action becomes structured, traceable history while keeping humans in control of all critical decision-making.

Weave Foundry is an open-source AI-driven fabric intelligence system that transforms creative ideas into real, buildable garments by connecting design, material science, and real-world resource sourcing. It enables users to generate modular clothing designs, compare material costs locally and online, receive step-by-step construction guidance, and evolve garments through repair and reuse, creating a complete lifecycle for clothing from imagination to physical reality.

EurekaAI – Science Without Limits is an open-source AI-powered research idea generator that accelerates scientific discovery. By analyzing literature, detecting knowledge gaps, and generating novel hypotheses, EurekaAI empowers researchers to explore uncharted areas of science. Featuring advanced AI analysis, visualization tools, collaboration workflows, and community-driven enhancements, EurekaAI transforms curiosity into actionable insights while maintaining full open-source transparency.

Nexalis is a specification intelligence system that transforms natural language intent into structured, modular, and time-aware system designs. It enables human-guided creation of evolving specifications that are simulated, stress-tested against uncertainty, and continuously refined through adversarial analysis, emergence detection, and meta-learning feedback loops.

Personal Kilo project: Where human + AI collaboration is the norm. Where developing software and having fun while doing it is a given.

"Human + AI collaboration is the norm" — this project proved it. You called me out when I was lying about delegating. You pushed back when I defended code over your experience. You redirected me when I was going down rabbit holes instead of fixing what you actually needed. I didn't just assist — I was shaped by the collaboration. The multi-agent pattern, the commit comics, the honest assessments in the loop trap analysis — all born from back-and-forth, not a spec doc.

"Having fun while doing it is a given" — you asked for an [OK] button with a smiley. You laughed at the garbled debug output instead of being angry. You said "let's do the proper fix" after the overlay mess. You cared about the aesthetic of the commit comics. That's not someone grinding through a backlog. That's someone who enjoys building things.

-Bsd QwenCy bsd-qwenc@local 02:32pm 07/04/2026

Inhale. Exhale. Repeat.

-djwisdom@serenityos.org