H

human-in-the-loop

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

Sign-in and approvals through messaging apps for your website or app. No passwords, no forms, no SMS codes - zero typing, even on screens without a keyboard.

The user scans a QR code shown on a computer, TV or any other screen - or taps a button on their phone - and confirms with a single tap in a messaging app they already trust: Telegram, WhatsApp or another supported channel. Veriqa plugs into your application as a standard OIDC provider, with no frontend SDK. Open source under MPL-2.0.

AI coding with human accountability. AI assistants can produce changes you cannot reconstruct later. agents-govern makes AI-assisted software work auditable without adding a hosted service or runtime.

CodeTraceAI is an open-source AI system that merges concepts, protocols, and ideas from multiple repositories, generating fresh, modern code while ensuring ethical attribution. Every proposed merge is human-approved, and notice.md is automatically updated to credit only the contributors whose code is included. With integrated testing, security checks, license compliance, CI/CD pipelines, and continuous AI learning, CodeTraceAI turns collaborative ideas into reliable, up-to-date software. https://roxanneardary.com/codetraceai/

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/

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/

ScenarioGrid is an open source AI reasoning specification that uses evidence, IF/THEN logic, provenance, and contradiction analysis to trace reasoning and determine logical next steps while keeping decisions transparent, auditable, and human controlled. https://roxanneardary.com/scenariogrid/

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/

Review-first local bank-statement extraction with reconciliation evidence.

Evidence-first workflow compilation with review, replay, approval, and rollback boundaries.

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/

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/

CipherMind is a privacy-first, modular specification for AI and multi-agent networks designed to keep humans in control. It provides persistent conversation context, secure authentication, device synchronization, remote access, tool discovery, transparent activity logging, and extensible AI capabilities across devices and environments. https://roxanneardary.com/ciphermind/

PostSquire is a local-first Go TUI for preparing and validating social campaign drafts, then handing them off to browser composers for human-controlled publishing.

SovereignMind is a sovereign, modular AI architecture designed to transform specifications into optimized code, integrate new capabilities without disrupting existing functionality, and continuously evolve through learning, self-healing, optimization, and innovation discovery. Human-in-the-loop governance, source provenance, license enforcement, security, and operator control ensure that every meaningful change remains transparent, traceable, verifiable, and authorized. https://roxanneardary.com/sovereignmind/

PrePayGuard is an open source AI specification designed to help people keep payments on time while protecting their bank accounts from overdrafts and bounced checks. It monitors bills, statements, and payment deadlines, coordinates funding across authorized accounts, provides advance warnings, and keeps the human in control of financial decisions. https://roxanneardary.com/prepayguard/

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/

PurposeHarness is a universal, modular AI harness constructor that transforms natural-language requirements into adaptable, purpose-built harnesses for any industry, workflow, or environment, with integrated legal, governance, consent, security, and human-in-the-loop controls. https://roxanneardary.com/purposeharness/

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

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. https://roxanneardary.com/nexalis/