Assistant operations

OpenClaw assistant backup and recovery checklist

A private assistant is only reliable if you know how to rebuild it after a broken config, lost machine, or failed deployment.

Use this checklist to protect the small set of files and decisions that make an OpenClaw Telegram assistant personal: workspace context, persona files, Telegram access settings, deployment notes, queues, and recovery steps.

What to protect

Back up the assistant brain, not just the app

Most recovery pain comes from missing context: what the assistant should know, who may talk to it, which channels are connected, and how the project was deployed.

Workspace context

Keep copies of AGENTS.md, SOUL.md, USER.md, IDENTITY.md, TOOLS.md, task notes, templates, and any project-specific memory that would be hard to recreate.

Access and secrets map

Do not paste secrets into docs. Record where bot tokens, model keys, app passwords, and deployment credentials live, who owns them, and how to rotate them.

Deployment recipe

Capture the machine, DNS, Vercel/GitHub links, scheduler, queues, and validation commands needed to prove the assistant is working again.

Backup checklist

  1. Commit public website, templates, and non-secret project files to git before deployment.
  2. Keep private assistant context in a protected local backup or encrypted vault, separate from public repos.
  3. Document Telegram bot username, allowed user IDs, group IDs, topic IDs, and access policy choices.
  4. Record which model provider path is active and where credentials are stored.
  5. Save scheduler details for daily checks, publishing queues, and any background automation.
  6. Keep deployment notes for domains, DNS records, Vercel project, GitHub repo, and verification files.
  7. Store a short recovery command list: install, authenticate, start gateway, test Telegram DM, check logs, and verify production URLs.

Recovery drill

Do a small restore drill before you need it. On a clean machine or separate folder, pull the repo, restore only the documented private files, reconnect credentials from the vault, and verify one end-to-end loop: Telegram message, assistant reply, log evidence, and no accidental public exposure.

What not to back up carelessly

  • Plain-text bot tokens, model API keys, session cookies, or app passwords.
  • Private user notes that do not need to travel with the assistant.
  • Large generated logs unless they are needed for troubleshooting or compliance.
  • Old scheduled queues that could be imported twice and create duplicate posts.

Keep recovery boring

The best recovery plan is small enough to use under stress. Back up the files that define the assistant, record where secrets live, and keep a repeatable validation path. If the assistant can be rebuilt without guessing, the setup is much safer to operate.