# digitalknk/openclaw-runbook

Unofficial OpenClaw runbook for running agents day to day without burning money, exposing your gateway, or trusting random automation.

Repository: https://github.com/digitalknk/openclaw-runbook
Canonical: https://ross.abutalabs.com/products/openclaw-runbook
Homepage: https://digitalknk.github.io/openclaw-runbook/
Language: Astro
License: MIT
License Family: permissive
Topics: ai-agents, openclaw, runbook, security-hardening, self-hosting, tailscale
Last push: 2026-05-26T07:01:09+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 35, longevity 14
- inputs: {"age_days": 204, "days_push": 99, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1103, forks 96 (observed 2026-08-28T04:03:36.067186+00:00)

## What it is
An unofficial, opinionated runbook (built as an Astro documentation site) for operating OpenClaw AI agents day to day with a focus on cost control, security hardening, and safe automation. It includes a main guide plus sanitized config examples, security prompts, heartbeat/cron patterns, and Tailscale-first remote access guidance.

## Use cases
- run openclaw agents long-term without runaway costs
- secure an openclaw gateway from public exposure
- set up tailscale-based remote access to an agent dashboard
- evaluate third-party agent skills safely
- configure model routing and fallbacks to control spend
- harden agents against prompt injection from untrusted content
- set up heartbeat and cron automation for agents
- deploy openclaw on a vps safely

## When to choose
- you already run OpenClaw and want a predictable, secure, cost-aware operating setup
- you need concrete config examples, security prompts, and automation patterns
- you want a Tailscale-first access model instead of exposing ports

## When to avoid
- you need official OpenClaw documentation or a beginner install guide
- you want a model leaderboard or ClawHub installation walkthrough
- you expect a one-size-fits-all config rather than opinionated guidance

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, security, agent-framework, configuration-management
- domain: self-hosted, security, developer-tools, documentation
- platform: self-hosted, cli
- tags: openclaw, runbook, tailscale, security-hardening, cost-control, prompt-injection, astro, unofficial-docs, ai-agents, web-server

## Member repositories
- digitalknk/openclaw-runbook (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:36.067186+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:45:31.892864+00:00, confidence not recorded.
  - readme: https://github.com/digitalknk/openclaw-runbook (fetched 2026-08-28T04:03:36.067186+00:00, sha 1faf9d9a4a02)
  - homepage: https://digitalknk.github.io/openclaw-runbook/ (fetched 2026-08-29T12:48:11.170348+00:00, sha af87fafb07a7)
- Data as of 2026-08-30T08:39:29.467469+00:00.