DashClaw governance for OpenClaw — policy enforcement, human approval, and decision recording for every tool call.

MCP server that lets Claude order food on DoorDash — search, compare real fee-included totals, build carts, and place orders behind a human approval dialog.

MCP server for Billy (billy.dk) accounting — connect Claude and other AI assistants to your Danish bookkeeping: invoices, bills, journal entries, trial balance, bank reconciliation. With human-approval write protection.

pendpost is a free, open-source (MIT), local-first social media planner where an AI agent drafts and schedules posts across Instagram, Facebook, LinkedIn, YouTube, X, Telegram, Discord, Mastodon, Nostr, WordPress, and Ghost behind a human approval gate yo

OKed for Claude Code - zero-code human approval for sensitive actions

AgentMemo MCP server — persistent memory and human approval for AI agents

LoopPause MCP server — pause agent execution and route human approval requests

Model Context Protocol (stdio) server for HumanStep — let agents create human-approval decisions and close the loop (wait / continuations).

MCP server that lets AI agents make purchases with human approval. Local-first payments, encrypted credentials, budget controls.

MCP server for Sanction — spend, tool, and provisioning authorization with human-approval grants, token budgets, and an encrypted credential vault for autonomous AI agents.

Transactional guard proxy for MCP agents: impact diff, human approval gate, saga compensation, hash-chained audit log.

Deployment-approval governance Pack — human approval gates (ESCALATE), destructive-action confirmation (REQUEST_CONFIRMATION), ramp clamping (REWRITE), CI-gate DEFER, and release gates (Item 14).

MCP server for Agent Pocket — remote human approval bridge for AI agents

Run the CodyRelay relay on your own machine: multi-agent coding loop with human approval gates. Your code and AI subscription never leave your computer.

Buy-side x402/HTTP-402 paying-fetch client for AI agents, under operator-owned spending policy (caps, allow/deny, human approval, trust checks, local receipts). Non-custodial.

Append-only project-local learning ledger for Pi with two separate trust gates: manual human approval, and a bounded auto-safe machine gate that is on by default in Pi-trusted projects. Selective fork of Matt Devy's pi-continuous-learning.

Declare your domain ontology once — get agent-facing docs and runtime enforcement (typed MCP server, human approval, audit log). Under active development.

Record a captioned demo video of any web app with one command — then grow into autonomous CWS/X/YouTube launch assets with final-file QA and a human approval gate.

Turn a signed provider webhook into a **durable signal** a parked flow can `await`. This is the inbound edge that lets a durable run pause on an external event — a `/qa run` comment, a preview deploy, a payment, a human approval — and resume crash-safe wh

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.