Acme Agent Supply provides a modular platform that continuously monitors OpenClaw AI agent stacks, delivering real‑time topology, activity metrics, and a 0‑100 reliability score to detect silent failures, configuration drift, and runtime issues. The system includes automated alerting, incident‑response guidance via the Agent911 cockpit, and tools for manual fleet intervention and backup verification, with a free tier and optional subscription modules for deeper protection.
Funding
Funding not disclosed
Founders
Product
Problem
Operators of OpenClaw agent stacks often lack real‑time visibility into runtime health, making silent failures, configuration drift, and backup verification difficult to detect before they cause service disruption. Without automated monitoring and guided recovery, mean time to recovery (MTTR) can be high and reliability scores remain low.
Solution
ACME Agent Supply offers a modular mission‑management platform that continuously monitors OpenClaw agents, scores stack reliability, and guides incident response. The free Triage/RadCheck module provides read‑only topology, activity rates, and a 0‑100 reliability score to surface early warnings. Sentinel detects silent failures, InfraWatch tracks configuration drift, and Watchdog flags loops, stalls, and double‑runs. When an issue arises, the Agent911 cockpit presents evidence‑based recovery steps, while Recall enables manual fleet intervention and Lazarus verifies that backups can be restored. Customers can start with the free tier and add protection modules on a subscription basis, creating a fully wired resilience layer without lock‑in.
Target Audience
Primary customers are reliability engineers and operators managing OpenClaw AI agent deployments who need continuous health monitoring and structured recovery workflows.
Features
- Real‑time agent topology and activity metrics displayed in a read‑only dashboard
- Runtime alerts and a 0‑100 reliability score (RadCheck) that quantify stack health
- Sentinel continuous silent‑failure detection and InfraWatch config‑drift monitoring
- Watchdog heartbeat and liveness checks for loops, stalls, and double‑runs
- Agent911 recovery cockpit with evidence‑first incident guidance
- Recall manual intervention tool for fleet‑wide actions during outages
- Lazarus backup readiness verification that confirms restore capability before incidents
- Open‑source, SHA‑verified installation with GPG‑signed packages