Guardrail Python Packages

pop-pay

The runtime security layer for AI agent commerce

radlab-llm-router-plugins

A companion repository for llm-router containing a collection of pipeline-ready plugins. Features a masking interface for anonymizing sensitive data and a guardrail system for validating input/output safety against defined policy rules.

verity-guard

Fail-closed verify-before-you-act gate for AI agents — one-line adapters for LangChain, LangGraph, CrewAI, OpenAI Agents, and the Vercel AI SDK. Signed, re-verifiable verdicts; pay-per-call via x402.

trialcheck

Audit completed A/B experiment readouts for SRM, peeking risk, practical significance, guardrail movement, and pre-period imbalance. Zero dependencies. Structured PASS/WARN/FAIL reports in JSON, Markdown, and HTML.