A Socratic supervision layer for AI coding agents.

OWASP Foundation web repository

Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2.

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.

🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.

Agent Skills for traceable requirements, independent verification, human approval gates, and auditable AI-assisted engineering. Supports Claude Code, Cursor, VS Code, and GitHub Copilot; ISO 9001/27001 aligned (design phase), GxP-aware.