Integrations

OpenClaw

What it does

Loop Engine provides the decision governance layer for OpenClaw workflows. OpenClaw handles agentic reasoning and tool orchestration; Loop Engine governs which actions are authorized, by whom, under what policy, and records full attribution for each transition.

This is the Sense → Decide → Govern pattern in practice:

• OpenClaw retrieves context and reasons over it (Decide)
• Loop Engine evaluates policy and transition guards (Govern)
• Action executes only after the loop permits it (Execute)

Quick setup

1. Install

   ⧉

   1npm install @loop-engine/adapter-openclaw @loop-engine/sdk

2. Wire Loop Engine into an OpenClaw workflow

   ⧉

   1import { createLoopSystem } from "@loop-engine/sdk";
   2import { OpenClawAdapter } from "@loop-engine/adapter-openclaw";
   3 
   4const loopSystem = await createLoopSystem({
   5  loops: [procurementLoop]
   6});
   7 
   8const openclaw = new OpenClawAdapter({ loopSystem });

3. Define the governed decision point

   ⧉

   1const proposal = await openclaw.proposeAction({
   2  workflowId: "procurement-workflow",
   3  action: "submit_purchase_order",
   4  input: { vendor: "Acme Medical Devices", amount: 9200 }
   5});
   6 
   7await loopSystem.transition({
   8  aggregateId: proposal.aggregateId,
   9  signal: proposal.signalId,
   10  actor: proposal.actor,
   11  evidence: proposal.evidence
   12});

How it works

1. OpenClaw agent proposes an action
2. Adapter maps proposal to a Loop Engine signal
3. Runtime evaluates guards and policies
4. Human approval gate pauses when required
5. Approved transition executes and is fully audited

Configuration reference

| Option | Type | Default | Description | |---|---|---|---| | loopSystem | LoopSystem | required | Runtime instance used for governed transitions | | signalMap | Record<string, string> | {} | Optional action-to-signal mapping override | | defaultActor | Actor | ai-agent/openclaw | Fallback actor attribution metadata | | | | — | Optional hook before transition submission |