MyClaw Backup

Built on 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 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

✅ | — |

Best practices

• - Never start the HTTP server without INLINECODE9
• 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: INLINECODE16

Scripts

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

CODEBLOCK0

Restore — always dry-run first

CODEBLOCK1

The restore script saves a pre-restore snapshot before overwriting anything.

HTTP server — token is mandatory

CODEBLOCK2

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)
• INLINECODE31 — List backups
• INLINECODE32 — Create backup
• INLINECODE33 — Download archive
• INLINECODE34 — Upload archive (multipart, field: backup)
• INLINECODE36 — Restore; add ?dry_run=1 to preview

Migrate to a new instance

Old machine:
CODEBLOCK3

New machine (after installing OpenClaw):
CODEBLOCK4

Schedule daily auto-backup (OpenClaw cron)

CODEBLOCK5

Post-Restore: Automatic Recovery Report

After restore.sh completes, it writes workspace/.restore-complete.json. On the next heartbeat/startup, the Agent should:

1. 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)

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.