A policy layer in front of your AI agent's payments. Set spending limits, require human approval over a threshold, and get a tamper-evident log of every decision. Zero dependencies.

PagerDuty routing adapter for human approval delivery.

Framework-independent, fail-closed human approval middleware for consequential AI agent tool calls.

MCP server for ViaHuman - Add human approval gates to LLM workflows

OKed for the Claude Agent SDK. A ready-made PreToolUse hook that gates sensitive tool calls behind a human approval push to your phone.

Agent-safe Obsidian vault access for Pi: auto-detect, retrieve, validate, plan, write, edit, manage, and explicitly destroy Markdown with human approval.

OKed plugin for OpenClaw. Gates skill and tool calls behind a human approval push to your phone.

Security gateway for Model Context Protocol servers: policy enforcement, secret redaction, prompt-injection screening, tool rug-pull detection, rate limiting, human approval gates, and audit logging — one drop-in proxy, zero infrastructure.

Honest project board for Claude Code. Reads your transcripts and git deterministically — no LLM — and labels every claim by evidence: file, test, human approval, or not verified. Local-first.

Multi-AI workflow framework — structured plan → cross-review → human approval → execution pipeline for AI coding agents

Human approval guardrails for agent-controlled repositories, deployments, and production-facing actions.

Filesystem-first framework for durable backend AI agents that run anywhere.

Interface Design Gate for Pi plus contract-first skill: pause and require human approval of contract/API shape before implementation lands.

MCP server that proposes Signal messages and groups but sends nothing without explicit human approval via a local web GUI.

ConnectWise MCP server for LLM agents — Claude, local Qwen via LM Studio, Cursor, Codex. PSA Lite free read-only desk + full PSA/RMM tool calling with human approval. Self-hosted, BYOM. Private beta (public soon): pulsatrix.ca

A human-approval gate for the dangerous things an AI agent does.

MCP server for governed AI workflows — invoice OCR, AML triage, credit review, and custom contracts with human approval gates and audit trails

n8n community node for ClearedBy — gate an action behind policy + human approval before your workflow proceeds.

GitOps-driven chaos engineering pipeline with human approval gate

Pi-family policy gate between an AI agent and an onchain wallet: propose a payment, the gate allows it, holds it for human approval, or blocks it, with an append-only receipt log. Sits downstream of a crypto screener; pairs with pi-gate.