A Socratic supervision layer for AI coding agents.

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.

Prompt injection scanner for AI coding tools (Claude Code / Codex / etc). Runs DeBERTa/Llama transformers via Candle or ONNX in Rust