dingdawg-loop

Name: loop protocol
Author: dingdawg

DingDawg Loop Protocol (DDLP) — safe scheduled AI agents with governance gates.

Every loop execution is verified, receipted, and fail-closed. MCP-native. Works with CrewAI, LangGraph, Claude Code, and Cursor.

Install

npx dingdawg-loop

Or as an MCP server in Claude Desktop / Claude Code:

{
  "mcpServers": {
    "dingdawg-loop": {
      "command": "npx",
      "args": ["dingdawg-loop"]
    }
  }
}

DDLP wraps any scheduled agent action with a governance gate that:

Evaluates the loop description before execution
Blocks destructive, financial, or sensitive operations until policy thresholds are met
Signs every execution with an Ed25519 receipt
Provides full audit history per loop

Tool	Description
`register_loop`	Register a new scheduled loop with name, description, cron, and governance policy
`execute_loop`	Run one cycle of a registered loop — governance gate fires before any action
`list_loops`	List all registered loops with status, last execution, and receipt count
`pause_loop`	Pause a running loop — no executions until resumed
`resume_loop`	Resume a paused loop
`loop_audit`	Retrieve the full signed receipt audit trail for any loop

DDLP classifies every loop at registration time. High-risk categories require elevated approval:

Destructive operations — file deletion, database mutations, DROP statements
External communications — email sends, Slack messages, webhook calls
Financial operations — any spend, transfer, or payment action
Sensitive data access — PII reads, credential access, health records
Bulk operations — mass updates, batch sends, bulk deletes

Works with any MCP-compatible AI client:

BUSL-1.1 — see LICENSE