H

human-in-the-loop

The framework is a way to keep AI coding useful at scale without losing accountability, team conventions, or your ability to understand later why a change landed. The supporting tooling is the ergonomics layer that makes file-based governance fast enough and low-friction enough to keep using.

ListingStream is a modular, AGPL-3.0+ licensed visual commerce platform that uses AI to intelligently insert sponsored products into photographs while preserving the integrity of the original image. Built around mandatory human-in-the-loop approval, real-time legal compliance, explainable AI, immutable audit trails, and pixel-preserving rendering, ListingStream enables trusted, revenue-generating visual marketing for real estate and other industries through a flexible, compliance-first architecture. https://roxanneardary.com/listingstream/

Open Arsenal provides open, self-hosted software specifications designed for deployment across private and public networks. Built for portability, interoperability, and transparency, each specification gives organizations the freedom to implement and customize solutions without vendor lock-in while remaining free to use under the AGPL-3.0+ license with required attribution. Specification Branding Licenses available upon request. https://roxanneardary.com/open-source-projects/

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. https://roxanneardary.com/latticeos/

VerifyRights is an open specification for AI-driven software license verification, commercial usage monitoring, and enterprise compliance intelligence. It provides a standardized framework for tracking license holders, authorized entities, websites, and networks while producing verifiable evidence of commercial deployments and potential licensing discrepancies. VerifyRights helps organizations monitor license agreements at scale through explainable AI, evidence-based analysis, and human-in-the-loop governance. https://roxanneardary.com/verifyrights/

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/

StoryWeaver is an open, modular, and federated AI skill library that enables agents to discover, share, and execute reusable capabilities. Designed for local, private, and cloud deployments, it combines privacy controls, human-in-the-loop consent, customizable themes, and secure skill management to create a flexible ecosystem for intelligent agents. https://roxanneardary.com/storyweaver/

Human Intent Governance Standard (HIGS) is a structured framework for building AI systems that operate under verified human intent, enforceable policy, and auditable compliance. It ensures that every decision passes through intent clarification, legal and policy validation, risk assessment, and human approval before execution. Designed for regulated and high-trust environments, HIGS prioritizes transparency, explainability, and human accountability while enabling modular, extensible governance across legal, technical, and organizational domains. https://roxanneardary.com/human-intent-governance-standard/

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/

Vexa is a privacy-first, human-in-the-loop AI orchestration platform that connects and automates enterprise tools through a secure, auditable control layer. It enables users to build and execute multi-step workflows across systems like Slack, Jira, and Salesforce while enforcing strict privacy controls, zero-trust data handling, and full execution transparency through explainable, replayable actions. https://roxanneardary.com/vexa/

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/

PressFix AI is an open-source WordPress optimization plugin that analyzes site performance, SEO, and Google Search Console issues to deliver clear, explainable fix recommendations. It uses a human-in-the-loop system so every suggested change is reviewed and approved by the user before being applied, ensuring full control without guesswork. https://roxanneardary.com/pressfixai/

PhysicsMesh Platform is a law-driven simulation system that computes physical reality through invariant physics laws rather than approximation or animation heuristics. It combines modular physics engines, spatiotemporal computation, versioned material science, and full source-method-provenance tracking to ensure every simulated outcome is causally consistent, reproducible, and scientifically traceable. Rendering is strictly a downstream projection of solved physical states in 2D or 3D space, governed by a human-in-the-loop intent and consent system that ensures all simulations are explicitly authorized and auditable. https://roxanneardary.com/physicsmesh-platform/

Rahul Krishna builds Proofward and independent evidence-first products for verifiable agent workflows, startup signals, and price decisions.

Seven evidence-first tools for bounded AI-agent decisions, resumable runs, cross-agent handoffs, verification, and reviewable releases.

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/

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/

OpenFiscal is an open-source platform that tracks, analyzes, and audits government budgets at all levels—town, city, state, and federal. Using AI, it flags deficits exceeding 3% of GDP and identifies line items more than 10% above national or state averages. The system maintains accountability by logging the officials responsible for budget approvals and requiring human-in-the-loop verification for all AI recommendations. OpenFiscal empowers citizens, auditors, and governments with transparent, actionable fiscal intelligence, helping prevent fraud, no-bid contracts, and cronyism. https://roxanneardary.com/openfiscal/

OpenScreen is a free and open-source screen recording application for creating professional demos, tutorials, and presentations. It combines high-quality screen capture, smooth zoom effects, annotations, customizable backgrounds, and audio recording with emerging AI-assisted editing features and Human-in-the-Loop controls, giving users powerful automation while maintaining full creative oversight. https://roxanneardary.com/openscreen/