openclaw-backup
One-click backup & restore for OpenClaw instances, workspace, credentials, skills, agent history. Powered by MyClaw.ai
Runs with mockssource: GitHubhomepageShellMITcommit a05a80d554a3
Shell, MIT licensed. The project labels itself: agent, backup, clawhub, migration, myclaw, openclaw, restore and skill.
openclaw-backup runs, with stand-ins for the services it depends on. An Argusic agent installed it in 7 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The openclaw-backup skill is fully operational: backup.sh creates 600-permission archives containing workspace, openclaw.json, credentials, skills, agents/sessions, devices, identity, scripts, and cron jobs; restore.sh applies with gateway token preservation and a pre-restore snapshot;
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- rsync not installed in container - all scripts depend on it4 minutes
- Install time
- 7 minutes
- Cold machine to finish
- 7 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- backup.sh creates valid tar.gz (verified via tar tzf) with 30 files across 10 categories; restore.sh --dry-run reports all sections; HTTP server returns 200 on /health, lists backups, creates backups via POST /backup, enforces 401 on bad token and 403 on remote /restore; serve.sh start/stop/status cycle works. Full spec: curl -s http://localhost:PORT/health -> {status:ok}, curl -s -X POST http://localhost:PORT/backup?token=X -> {message:"Backup created",filename:...}, curl -s http://localhost:PORT/backups?token=X -> {backups:[...]}, curl -s -o /dev/null -w "%{http_code}" http://localhost:PORT/backups?token=wrong -> 401.
- Model tokens used
- 139,226
- Exact commit tested
- a05a80d554a3
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
placed rsync.real + libpopt.so.0 in ~/.local/bin with wrapper script for LD_LIBRARY_PATH,
patched backup.sh and restore.sh to prepend ~/.local/bin to PATH
=== Script patches applied ===
scripts/backup.sh: added 'export PATH="${HOME}/.local/bin:${PATH}"' after set -euo pipefail
scripts/restore.sh: same patch applied via sed
Now let me format the final ARGUSIC_RESULT:
exec
/bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 7…
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 7, "errors": [{"msg": "rsy…
tokens used
139,226Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 7 minutes to install, slower than the median of the 140 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 141 agent projects Argusic has installed and timed, openclaw-backup was the 76th fastest to reach a running state, and 94 of 141 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.02 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openclaw-backup)Questions
- Does openclaw-backup run?
- openclaw-backup runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 7 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test openclaw-backup?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a05a80d554a3. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test openclaw-backup?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does openclaw-backup take to install?
- 7 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does openclaw-backup need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing openclaw-backup?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does openclaw-backup compare with the alternatives?
- Of the 141 agent projects Argusic has installed and timed, openclaw-backup was the 76th fastest to reach a running state, and 94 of 141 reached one at all.
- Where is the evidence for openclaw-backup?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.