@probelabs/vow

A sacred covenant between machine and man. Accountability gates for AI agents.

v0.7.14 URL: https://unpkg.com/@probelabs/vow@0.7.14

Open Browse Files

ai accountability consent gate commit agent git-hooks husky claude ethics ai-safety developer-tools cli cross-platform

@creedspace/mcp-server

Universal MCP server for Creed Space - AI safety guardrails in 10 seconds

v1.0.8 URL: https://unpkg.com/@creedspace/mcp-server@1.0.8/dist/index.js

Open Browse Files

mcp model-context-protocol ai-safety creed-space claude llm guardrails

intentguard

Mathematical foundation for AI trust measurement. Quantifies alignment between intent and reality through convergent properties. The only system that makes AI trust measurable, insurable, and legally defensible.

v1.8.2 URL: https://unpkg.com/intentguard@1.8.2/lib/index.js

Open Browse Files

ai-safety trust-measurement ai-alignment trust-debt mathematical-foundation convergent-properties orthogonal-categories unity-architecture regulatory-compliance eu-ai-act intent-reality drift-detection

@pv-bhat/vibe-check-mcp

Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety

v2.5.1 URL: https://unpkg.com/@pv-bhat/vibe-check-mcp@2.5.1/build/index.js

Open Browse Files

mcp mcp-server vibe-check vibe-coding metacognition ai-alignment llm-agents autonomous-agents reflection agent-oversight ai-safety prompt-engineering

ai-sdk-guardrails

Input and output guardrails middleware for Vercel AI SDK.

v5.0.1 URL: https://unpkg.com/ai-sdk-guardrails@5.0.1/dist/index.js

Open Browse Files

ai guardrails vercel-ai-sdk typescript validation safety streaming security content-filtering prompt-injection ai-safety