OpenClaw 自愈系统：4层AI驱动网关监控与自动恢复解决方案

openclaw-self-healing by ramsbaby/openclaw-self-healing

659 周安装量

31 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/ramsbaby/openclaw-self-healing --skill openclaw-self-healing

自动化开发运维监控

🇨🇳中文介绍

OpenClaw 自愈系统

"能够自我修复的系统——当无法自愈时会寻求帮助。"

专为 OpenClaw Gateway 设计的 4 层自主自愈系统。

架构

Level 1: Watchdog (180s)     → 进程监控 (OpenClaw 内置)
Level 2: Health Check (300s) → HTTP 200 检查 + 3 次重试
Level 3: Claude Recovery     → 30 分钟 AI 驱动诊断 🧠
Level 4: Discord Alert       → 人工介入升级

特色功能 (v2.0)

全球首创 将 Claude Code 作为第 3 层紧急"医生"
持续学习 - 自动记录恢复文档 (症状 → 原因 → 解决方案 → 预防措施)
推理日志 - 可解释的 AI 决策过程
多渠道告警 - 支持 Discord + Telegram
指标仪表盘 - 成功率、恢复时间、趋势分析
生产环境测试 (2026年2月5-6日已验证恢复)
集成 macOS LaunchAgent

快速设置

1. 安装依赖

brew install tmux
npm install -g @anthropic-ai/claude-code

2. 配置环境变量

# 将模板复制到 OpenClaw 配置目录
cp .env.example ~/.openclaw/.env

# 编辑并添加你的 Discord webhook (可选)
nano ~/.openclaw/.env

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

FlyClaw：零登录航班聚合查询工具，Python实现多源航班信息与价格搜索

4,000,000 周安装

Vercel React 最佳实践指南 | 58条Next.js性能优化规则与代码重构

255,700 周安装

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

136,300 周安装

Azure Data Explorer (Kusto) 查询技能：KQL数据分析、日志遥测与时间序列处理

98,500 周安装

# 复制脚本
cp scripts/*.sh ~/openclaw/scripts/
chmod +x ~/openclaw/scripts/*.sh

# 安装 LaunchAgent
cp launchagent/com.openclaw.healthcheck.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist

# 检查 Health Check 是否在运行
launchctl list | grep openclaw.healthcheck

# 查看日志
tail -f ~/openclaw/memory/healthcheck-$(date +%Y-%m-%d).log

脚本	层级	描述
`gateway-healthcheck.sh`	2	HTTP 200 检查 + 3 次重试 + 升级
`emergency-recovery.sh`	3	Claude Code PTY 会话进行 AI 诊断 (v1)
`emergency-recovery-v2.sh`	3	增强版，包含学习 + 推理日志 (v2) ⭐
`emergency-recovery-monitor.sh`	4	失败时发送 Discord/Telegram 通知
`metrics-dashboard.sh`	-	可视化恢复统计数据 (新增)

所有设置通过 ~/.openclaw/.env 文件中的环境变量进行：

变量	默认值	描述
`DISCORD_WEBHOOK_URL`	(无)	用于告警的 Discord webhook
`OPENCLAW_GATEWAY_URL`	`http://localhost:18789/`	Gateway 健康检查 URL
`HEALTH_CHECK_MAX_RETRIES`	`3`	升级前的重启尝试次数
`EMERGENCY_RECOVERY_TIMEOUT`	`1800`	Claude 恢复超时时间 (30 分钟)

测试第 2 层 (健康检查)

# 手动运行
bash ~/openclaw/scripts/gateway-healthcheck.sh

# 期望输出：
# ✅ Gateway healthy

测试第 3 层 (Claude 恢复)

# 注入一个配置错误 (请先备份！)
cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.bak

# 等待健康检查检测到问题并升级 (~8 分钟)
tail -f ~/openclaw/memory/emergency-recovery-*.log

MIT 许可证 - 你可以随意使用它。

由 @ramsbaby + Jarvis 🦞 构建

🇺🇸English

OpenClaw Self-Healing System

"The system that heals itself — or calls for help when it can't."

A 4-tier autonomous self-healing system for OpenClaw Gateway.

Architecture

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 escalation

What's Special (v2.0)

World's first Claude Code as Level 3 emergency doctor
Persistent Learning - Automatic recovery documentation (symptom → cause → solution → prevention)
Reasoning Logs - Explainable AI decision-making process
Multi-Channel Alerts - Discord + Telegram support
Metrics Dashboard - Success rate, recovery time, trending analysis
Production-tested (verified recovery Feb 5-6, 2026)
macOS LaunchAgent integration

Quick Setup

1. Install Dependencies

brew install tmux
npm install -g @anthropic-ai/claude-code

2. Configure Environment

# Copy template to OpenClaw config directory
cp .env.example ~/.openclaw/.env

# Edit and add your Discord webhook (optional)
nano ~/.openclaw/.env

3. Install Scripts

# 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

4. Verify

# Check Health Check is running
launchctl list | grep openclaw.healthcheck

# View logs
tail -f ~/openclaw/memory/healthcheck-$(date +%Y-%m-%d).log

Scripts

Script	Level	Description
`gateway-healthcheck.sh`	2	HTTP 200 check + 3 retries + escalation
`emergency-recovery.sh`	3	Claude Code PTY session for AI diagnosis (v1)
`emergency-recovery-v2.sh`	3	Enhanced with learning + reasoning logs (v2) ⭐
`emergency-recovery-monitor.sh`	4	Discord/Telegram notification on failure
`metrics-dashboard.sh`

Configuration

All settings via environment variables in ~/.openclaw/.env:

Variable	Default	Description
`DISCORD_WEBHOOK_URL`	(none)	Discord webhook for alerts
`OPENCLAW_GATEWAY_URL`	`http://localhost:18789/`	Gateway health check URL
`HEALTH_CHECK_MAX_RETRIES`	`3`	Restart attempts before escalation
`EMERGENCY_RECOVERY_TIMEOUT`

Testing

Test Level 2 (Health Check)

# Run manually
bash ~/openclaw/scripts/gateway-healthcheck.sh

# Expected output:
# ✅ Gateway healthy

Test Level 3 (Claude Recovery)

# 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

License

MIT License - do whatever you want with it.

Built by @ramsbaby + Jarvis 🦞

Weekly Installs

659

Repository

ramsbaby/opencl…-healing

GitHub Stars

First Seen

Feb 9, 2026

Security Audits

Gen Agent Trust HubFail SocketFail SnykWarn

Installed on

openclaw608

opencode606

gemini-cli602

codex601

kimi-cli589

github-copilot589