Constrained deep learning is an advanced approach to training deep neural networks by incorporating domain-specific constraints into the learning process.

Abstract Constraint Transformation

Glass Box Framework — runtime constitutional verification for AI answers. Trust Cards with claim-level reasoning chains, formal ECS scoring, the 7-angle Glassbox Court red team, and deterministic audit logs. MCP-native.

🎓 Free course on deterministic AI verification and AISecOps. Learn fail-closed AI architecture, formal verification, audit integrity, MCP security, and trust-boundary engineering with QWED-AI.

Semantic Flow Language (SFL) is a framework that aligns human intent, AI reasoning, and executable logic. It ensures bidirectional synchronization between meaning and code, allowing for reliable, transparent, and verifiable AI-driven development across various environments.

sonmat (손맛) — Claude Code plugin that builds verification habits into AI-human collaboration

Four Tests Standard (4TS) - Vendor-neutral specification for verifiable AI governance

Open Source 24/7 Autonomous Agentic AI System

Deterministic verification middleware for banking and financial AI. NPV, IRR, loan amortization, and interest calculations with QWED precision.

Your AI agent implements the code. Canary Lab proves it works.

Verifiable onchain memory for trustless AI agents

Structured workflows that make LLMs think instead of guess — verification, exploration, feasibility, synthesis and architecture reasoning.

Records of experiments testing the reproducibility of LLM workloads on datacenter GPUs. Key novelty: Non-associativity is a "fingerprint" of an inference stack and implementation.

Mxsh - A universal shell that eliminates OS barriers. Use any command syntax on any platform with AI-powered security validation.

A Chrome extension that lets you chat with Gemini and Perplexity simultaneously. Type once, send to both, and cross-verify answers between them.

An advanced AI-powered fake news detection system that verifies text, images, and social media posts using Gemini AI, FastAPI, and Next.js. Includes a modern web interface, a lightweight Streamlit app, and a Chrome extension for real-time fake content detection. Built to combat misinformation with explainable AI results and contextual source links.

Independent verification layer for AI generated coding plans

Source-available governed AI control-plane architecture for evidence-gated proposals, staged execution, human review, certified resume, audited reentry, closeout ledgers, and exportable receipts. AI proposes. Humans decide. No AGI claims.

Governed verification and synthesis for Massive Intelligence (IM) outputs: configurable Thinker, Worker, and Verifier panels, model-as-judge, and Ed25519-signed, SHA-256-chained tamper-evident verdicts. Zero dependencies, node-free core, TypeScript-first.

Factuality Verification Pipeline