Openclaw Self Healing — AI skill for Claude Code
32+ 4-tier autonomous crash recovery for Claude Code and any service — 64% auto-resolved, LLM-agnostic (Claude/GPT-4/Gemini/Ollama), Prometheus metrics.
How to install Openclaw Self Healing
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Ramsbaby/openclaw-self-healing and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Openclaw Self Healing does
**Stop getting paged at 3 AM. Let AI fix your crashes automatically.**
Alternatives in AI
- Ccstatusline — by sirmalloc - A highly customizable status line formatter for Claude Code CLI that displays model info, git b 5.5k ★
- Context Dump — Dump current context for model switch or context limit recovery 508 ★
- Codebase Digest — 🗜️ Codebase-digest is your AI-friendly codebase packer and analyzer 375 ★
README
🦞 OpenClaw Self-Healing System
*Autonomous AI-Powered Recovery for Any Service*
**Stop getting paged at 3 AM. Let AI fix your crashes automatically.**
[](https://github.com/Ramsbaby/openclaw-self-healing/releases) [](#-quick-start) [](LICENSE) [](https://github.com/ramsbaby/openclaw-self-healing/stargazers) [](README.md) [](README.md) [](README.md) [](https://github.com/Ramsbaby/openclaw-self-healing/actions/workflows/lint.yml)
[🚀 Quick Start](#-quick-start) · [🎬 Demo](#-demo) · [🏗️ Architecture](#️-architecture) · [📖 Docs](docs/)
[](README.ko.md)
If this saved your night 🌙, a ⭐ helps others find it.
🎬 Demo
*4-tier recovery in action: KeepAlive → Watchdog → AI Doctor → Alert*
🔥 Why This Exists
**This system wraps any long-running service with autonomous crash recovery.** OpenClaw Gateway is the primary example — a self-hosted AI gateway for Claude/GPT-4 routing — but the watchdog/recovery architecture adapts to any service.
Your service crashes at midnight. A basic watchdog restarts it — but what if the config is corrupted? The API rate limit hit? A dependency broken?
**Simple restart = crash loop.** You get paged. Your weekend is ruined.
**This system doesn't just restart — it understands and fixes root causes.**
🆚 Why openclaw-self-healing vs. rolling your own
| Feature | Basic Watchdog | supervisord | openclaw-self-healing |
|---|---|---|---|
| Auto-restart on crash | ✅ | ✅ | ✅ |
| HTTP health polling | ❌ | ❌ | ✅ |
| Crash loop prevention (backoff) | ❌ | partial | ✅ exponential backoff |
| Config validation before start | ❌ | ❌ | ✅ Level 0 preflight |
| AI root-cause diagnosis | ❌ | ❌ | ✅ Claude / GPT-4 / Gemini / Ollama |
| Auto-fix corrupted config | ❌ | ❌ | ✅ |
| Multi-channel alerts (Discord/Slack/Telegram) | ❌ | ❌ | ✅ |
| Prometheus metrics | ❌ | ❌ | ✅ |
| Works on macOS + Linux + Docker | partial | ✅ | ✅ |
| Zero vendor lock-in | ✅ | ✅ | ✅ MIT |
...
Related Skills
Octoroute
Smart HTTP router for local LLMs (Ollama, LM Studio, llama.cpp). Rule-based + LLM-powered routing, health chec
Pantheon
The AI Development Operating System — Persistent memory, crash recovery, and multi-instance coordination for C
Agent Observability Stack
Self-hostable observability for LLM agents + a Linux host (Intel iGPU/NPU + NVIDIA RTX 3090 eGPU aware): Prome
Aura Code
Model-agnostic autonomous coding agent with a reproducible benchmark harness, adaptive turn budgets, and domai
Apply Agent
LLM agent that tracks job applications by reading your inbox read-only. Built with LangGraph, Claude or a loca
Local LLM Agentic Coding
Install a free local LLM (Ollama) and connect Claude Code or OpenCode to it, with an honest hardware reality-c
Related Agents
Delegate
Expert LLM delegation specialist that seamlessly connects to external language models including GPT-4, GPT-3.5
Codex Debugger
Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenA
Observability Engineer
OpenTelemetry, distributed tracing, structured logging, metrics specialist — Grafana, Datadog, Prometheus