A runtime watchdog that isolates OpenClaw plugins into monitored worker threads and kills any plugin that blocks the gateway event loop for more than 5 seconds
OpenClaw plugins (especially Active Memory, Dreaming, and provider bridges) run in the same Node.js event loop as the gateway. When one plugin blocks, it starves everything: Telegram polling stops receiving messages, API responses go blank, and conversations fail silently. Seven bug reports in April 2026 alone document cascade failures from a single plugin blocking the loop. This watchdog spawns each plugin in its own worker thread with a heartbeat monitor, kills and restarts any plugin that exceeds the event loop latency threshold, and logs the exact stack trace that caused the block.
Demand Breakdown
Social Proof 5 sources
Gap Assessment
3 tools exist (ClawMetry, PM2, Microsoft node-native-watchdog) but gaps remain: No per-plugin isolation, no event loop monitoring, no automatic restart or circuit breaker for misbehaving plugins; Operates at process level not plugin level. Cannot isolate individual OpenClaw plugins or detect which plugin blocks the event loop.
Features4 agent-ready prompts
Competitive LandscapeFREE
| Product | Does | Missing |
|---|---|---|
| ClawMetry | Real-time observability dashboard for OpenClaw agents showing token costs, session history, and cron jobs | No per-plugin isolation, no event loop monitoring, no automatic restart or circuit breaker for misbehaving plugins |
| PM2 | General-purpose Node.js process manager with restart on crash and basic monitoring | Operates at process level not plugin level. Cannot isolate individual OpenClaw plugins or detect which plugin blocks the event loop |
| Microsoft node-native-watchdog | Kills the current Node.js process if the event loop is unresponsive | Nuclear option only. Kills the entire gateway instead of isolating the offending plugin. No granularity, no diagnostics, no recovery |
Sign in to unlock full access.