Loading...
Loading...
4-tier autonomous self-healing system for OpenClaw Gateway with persistent learning, reasoning logs, and multi-channel alerts. Features Claude Code as Level 3 emergency doctor for AI-powered diagnosis and repair.
npx skill4agent add ramsbaby/openclaw-self-healing openclaw-self-healing"The system that heals itself — or calls for help when it can't."
Level 1: Watchdog (180s) → Process monitoring (OpenClaw built-in)
Level 2: Health Check (300s) → HTTP 200 + 3 retries
Level 3: Claude Recovery → 30min AI-powered diagnosis 🧠
Level 4: Discord Alert → Human escalationbrew install tmux
npm install -g @anthropic-ai/claude-code# Copy template to OpenClaw config directory
cp .env.example ~/.openclaw/.env
# Edit and add your Discord webhook (optional)
nano ~/.openclaw/.env# Copy scripts
cp scripts/*.sh ~/openclaw/scripts/
chmod +x ~/openclaw/scripts/*.sh
# Install LaunchAgent
cp launchagent/com.openclaw.healthcheck.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist# Check Health Check is running
launchctl list | grep openclaw.healthcheck
# View logs
tail -f ~/openclaw/memory/healthcheck-$(date +%Y-%m-%d).log| Script | Level | Description |
|---|---|---|
| 2 | HTTP 200 check + 3 retries + escalation |
| 3 | Claude Code PTY session for AI diagnosis (v1) |
| 3 | Enhanced with learning + reasoning logs (v2) ⭐ |
| 4 | Discord/Telegram notification on failure |
| - | Visualize recovery statistics (NEW) |
~/.openclaw/.env| Variable | Default | Description |
|---|---|---|
| (none) | Discord webhook for alerts |
| | Gateway health check URL |
| | Restart attempts before escalation |
| | Claude recovery timeout (30 min) |
# Run manually
bash ~/openclaw/scripts/gateway-healthcheck.sh
# Expected output:
# ✅ Gateway healthy# Inject a config error (backup first!)
cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.bak
# Wait for Health Check to detect and escalate (~8 min)
tail -f ~/openclaw/memory/emergency-recovery-*.log