What it does
One-click backup & restore for OpenClaw instances — workspace, credentials, skills, agent history. Powered by MyClaw.ai
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Automation and agents
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/leoyeai-openclaw-backup)Similar Skills
Same kind of work, ordered like the Skills list
1 skills (instruction sets) by LeoYeAI that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Not stated by the maker · SKILL.md skills work in apps that support Agent Skills, such as Claude Code, Codex and Cursor
Install
Is it safe?
- Who made it
GitHub account LeoYeAI (person), 3 years old
- Use and upkeep
★ 665 stars · code last changed Mar 3, 2026
- Any scripts?
6 scripts that can run on a computer: scripts/backup.sh, scripts/restore.sh, scripts/schedule.sh, scripts/serve.sh and 2 more
- Uses the internet?
Scripts that go online: scripts/ui.html
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit a05a80d (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (863). Use "Let the AI install it" instead
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /openclaw-backup or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Claude Code, then type /openclaw-backup or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Put the folder there yourself
Put the myclaw-backup folder at ~/.agents/skills/myclaw-backup
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick openclaw-backup
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
In Cursor’s Agent chat, type / and pick openclaw-backup
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
7,379 characters · Open the full file on GitHub
---
name: myclaw-backup
description: "Backup and restore all OpenClaw configuration, agent memory, skills, and workspace data. Part of the MyClaw.ai (https://myclaw.ai) open skills ecosystem — the AI personal assistant platform that gives every user a full server with complete code control. Use when the user wants to create a snapshot of their OpenClaw instance, schedule periodic backups, restore from a backup, migrate to a new server, download a backup file locally, upload a backup file from another machine, or protect against data loss. Includes a built-in HTTP server for browser-based download/upload/restore without needing cloud storage. TRUST BOUNDARY: This skill archives and restores highly sensitive data including bot tokens, API keys, and channel credentials. Only install if you trust the operator. Always use --dry-run before restore. Never start the HTTP server without a --token."
metadata:
openclaw:
requires:
bins: ["node", "rsync", "tar", "python3", "openclaw"]
trust: high
permissions:
- read: ~/.openclaw
- write: ~/.openclaw
- network: listen
---
# MyClaw Backup
> **Built on [MyClaw.ai](https://myclaw.ai)** — the AI personal assistant platform that gives every user a full server with complete code control, networking, and tool access. This skill is part of the MyClaw.ai open skills ecosystem.
Backs up all critical OpenClaw data to a single `.tar.gz` archive and restores it to any OpenClaw instance. Includes a built-in HTTP server for browser-based backup management.
## ⚠️ Trust Boundary & Security Model
This skill handles **highly sensitive data**: bot tokens, API keys, channel credentials, session history. Understand the security model before use:
### What each script does
- **backup.sh** — reads `~/.openclaw/` and writes a `chmod 600` archive to disk. No network access.
- **restore.sh** — overwrites `~/.openclaw/` from an archive. Requires typing `yes` to confirm. Always run `--dry-run` first.
- **serve.sh / server.js** — starts a local HTTP server. Token is **mandatory** (refuses to start without one). Shell-execution endpoints (`/backup`, `/restore`) are **localhost-only** — remote access can only download and upload files, not trigger execution.
- **schedule.sh** — modifies your system crontab to run backup.sh on a schedule. Prints the cron entry before adding. Use `--disable` to remove.
### Access control summary
| Endpoint | Remote (token required) | Localhost only |
|---|---|---|
| GET /health | ✅ (no token) | — |
| GET /backups | ✅ | — |
| GET /download/:file | ✅ | — |
| POST /upload | ✅ | — |
| POST /backup | ❌ | ✅ |
| POST /restore | ❌ | ✅ |
### Best practices
- Never start the HTTP server without `--token`
- Never expose the HTTP server to the public internet without TLS
- Always run `restore.sh --dry-run` before applying a restore
- Store backup archives securely — they contain all credentials
## Dependencies
Requires: `node`, `rsync`, `tar`, `python3`, `openclaw` CLI (all standard on OpenClaw instances).
Check: `which node rsync tar python3 openclaw`
## Scripts
| Script | Purpose |
|---|---|
| `scripts/backup.sh [output-dir]` | Create backup (default: `/tmp/openclaw-backups/`) |
| `scripts/restore.sh <archive> [--dry-run] [--overwrite-gateway-token]` | Restore — **always dry-run first** |
| `scripts/serve.sh start --token TOKEN [--port 7373]` | Start HTTP server — **token required** |
| `scripts/serve.sh stop\|status` | Stop/check server |
| `scripts/schedule.sh [--interval daily\|weekly\|hourly]` | System cron scheduling |
> **Gateway token behavior (v1.6+):** By default, `restore.sh` preserves the new server's `gateway.auth.token` after restoring `openclaw.json`. This prevents the `"gateway token mismatch"` error in Control UI / Dashboard after migration. Use `--overwrite-gateway-token` only for full disaster recovery on the same server.
## What Gets Backed Up
See `references/what-gets-saved.md` for full details.
**Includes:** workspace (MEMORY.md, skills, agent files), openclaw.json (bot tokens + API keys), credentials, channel pairing state, agent config + session history, devices, identity, cron jobs, guardian scripts.
**Excludes:** logs, binary media, node_modules, canvas system files.
## Common Workflows
### Create backup
```bash
bash scripts/backup.sh /tmp/openclaw-backups
# → /tmp/openclaw-backups/openclaw-backup_TIMESTAMP.tar.gz (chmod 600)
```
### Restore — always dry-run first
```bash
# Step 1: preview what will change
bash scripts/restore.sh openclaw-backup_TIMESTAMP.tar.gz --dry-run
# Step 2: review the output, then apply
bash scripts/restore.sh openclaw-backup_TIMESTAMP.tar.gz
```
The restore script saves a pre-restore snapshot before overwriting anything.
### HTTP server — token is mandatory
```bash
# Token is required — server refuses to start without one
bash scripts/serve.sh start --token $(openssl rand -hex 16) --port 7373
# → http://localhost:7373/?token=<generated-token>
```
**Never share the URL on a public network without a reverse proxy + TLS.**
The Web UI provides: create backup, download `.tar.gz`, upload, dry-run preview, restore.
**HTTP API (all require token except /health):**
- `GET /health` — Health check (unauthenticated, read-only)
- `GET /backups` — List backups
- `POST /backup` — Create backup
- `GET /download/:filename` — Download archive
- `POST /upload` — Upload archive (multipart, field: `backup`)
- `POST /restore/:filename` — Restore; add `?dry_run=1` to preview
### Migrate to a new instance
**Old machine:**
```bash
bash scripts/serve.sh start --token MYTOKEN --port 7373
```
**New machine (after installing OpenClaw):**
```bash
# Download
curl -O "http://OLD_IP:7373/download/openclaw-backup_TIMESTAMP.tar.gz?token=MYTOKEN"
# Always dry-run first
bash scripts/restore.sh openclaw-backup_TIMESTAMP.tar.gz --dry-run
# Apply
bash scripts/restore.sh openclaw-backup_TIMESTAMP.tar.gz
# All channels reconnect automatically — no re-pairing needed
```
### Schedule daily auto-backup (OpenClaw cron)
```json
{
"name": "daily-openclaw-backup",
"schedule": { "kind": "cron", "expr": "0 3 * * *", "tz": "UTC" },
"payload": {
"kind": "agentTurn",
"message": "Run a backup using the myclaw-backup skill. Output dir: /tmp/openclaw-backups",
"timeoutSeconds": 120
},
"sessionTarget": "isolated"
}
```
## Post-Restore: Automatic Recovery Report
After `restore.sh` completes, it writes `workspace/.restore-complete.json`. On the next heartbeat/startup, the Agent should:
1. Check if `workspace/.restore-complete.json` exists
2. If yes: read it, send a restore report to the user, then **delete the file** (one-shot — never report twice)
3. **Send the report in the user's primary language** (read from `workspace/USER.md`)
### Report format (adapt language from USER.md)
```
✅ [Restore complete — in user's language]
📦 Backup: {backup_name}
🤖 Agent: {agent_name}
🕐 Restored at: {restored_at}
💾 Contents restored: workspace, config, credentials, history, cron...
[Channel reconnect instructions in user's language]
```
## Future: MyClaw Cloud Backup
The HTTP API is designed to be compatible with a future MyClaw cloud backup service. When available, replace the local server URL with the MyClaw API endpoint — the upload/download/restore flow stays identical.
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 665
- Maker
- LeoYeAI
- License
- MIT
- Last code change
- Mar 3, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1
- Topics
- agent, backup, clawhub, migration, myclaw, openclaw, restore, skill