AI Safety Q&A web frontend

In situ interactive widgets for responsible AI 🌱

Document-first CLI for building agent workflows in Markdown and JSON.

All AIs are sycophants.

Work safely with AI agents like Claude Code, Cursor, Kiro

An ethics-first, transparent AI reasoning assistant. Built to be self-hosted by anyone.

AI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency, and JSON/format quality on any OpenAI, Anthropic, or local client.

Free OpenGuardrails for n8n nodes with SOTA performance

The [SEED] Foundry - The Startup Ethical Economic Design - Decision Matrix for Social Technology Founders

A synthetic hippocampus for AI systems. Safety-first hypergraph-based associative memory architecture designed to explore persistent, coherent, and inspectable memory for AI. Transparent reasoning through spreading activation.

Browser extension that detects PII in AI chat inputs and lets you redact before sending.

AI response safety/ethics/accuracy checker - by A0 (currently not maintained)

Proving that the neural network really did learn its safety property

The AI Safety Incident Dashboard is an interactive frontend application designed to enhance your frontend development skills. This project focuses on creating a user-friendly interface to view and log hypothetical AI safety incidents, aligning with HumanChain's mission of promoting AI safety

🛡️ Verify AI outputs with llmverify for Node.js, ensuring safety and accuracy without sacrificing privacy.

A framework for training, deploying, and red teaming AI chatbot widgets. Upload custom datasets, evaluate bot performance with adversarial prompts, and deploy robust, testable chatbots as embeddable widgets — all through a unified interface.

The website for the paper "Control Tax: The Price of Keeping AI in Check." The paper: https://arxiv.org/abs/2506.05296

🛡️ 17KB justice-driven AI bias detection suite born from fighting for Jahmere Webb's freedom. Real-time bias analysis for chat interfaces, development environments & codebase mapping. <10ms speed, 84.9% accuracy, zero dependencies. Mission: 15% revenue supports criminal justice reform.

🔐 Multi-layered security middleware for mcp-forge — namespace firewalls, parameter validation, LLM intent verification, and human-in-the-loop approval gates for MCP tool calls.

Public Coordination Layer derived from OSIE Architecture © 2025 Chris Meadows / Omni Institute