Self-healing stability monitor for AI agents - 5 core checks + 15 extended checks, auto-recovery, health scoring
Self-Healing Stability Monitor for AI Agents
Version: 0.12.6
Author: Dream
License: MIT
aegis-protocol initInitialize configuration file
aegis-protocol statusShow system health summary
aegis-protocol checkRun full health check
aegis-protocol healExecute automatic recovery
aegis-protocol configView current configuration
# Initialize
python3 aegis-protocol.py init
# Check health
python3 aegis-protocol.py check
# Auto recover
python3 aegis-protocol.py heal
# View config
python3 aegis-protocol.py config
File: ~/.openclaw/workspace/.watchdog-config.json
{
"thresholds": {
"sessionTimeoutMinutes": 60,
"pm2RestartAlert": 50,
"diskUsagePercent": 90,
"memoryUsagePercent": 95,
"contextUsagePercent": 80
}
}
| Category | Checks |
|---|---|
| System | CPU, Memory, Disk, Zombies, FD, Connections |
| Services | PM2, Nginx, Docker, Cron |
| AI Agent | Sessions, Context, Tasks, Loops |
| Security | SSL, Updates, Git |
| Maintenance | Backup, Cleanup, Network |
| Score | Status |
|---|---|
| 90-100 | Excellent |
| 70-89 | Good |
| 50-69 | Warning |
| 0-49 | Critical |
# Unit tests
python3 -m pytest tests/ -v
# Coverage
python3 -m pytest tests/ --cov=aegis_protocol -v
Coverage: 82%
Tests: 20+ passing
| Metric | Value |
|---|---|
| Type hints | >90% |
| Test coverage | 82% |
| Documentation | 100% |
| Bugs | 0 |
Aegis Protocol - The Never-Sleeping Guardian 🌀