Unofficial OpenClaw runbook for running agents day to day without burning money, exposing your gateway, or trusting random automation.
digitalknk/openclaw-runbook is ranked 11,558 with 1,110 stars.
Same-category comparison
digitalknk/openclaw-runbook is ranked 11,558 among these 8 peers; burness/tensorflow-101 is ranked 11,557.
Same-category comparison| Name | Rank | Metrics |
|---|
| despoisj/DeepAudioClassification | 11,540 | - Language:
- Python
- Stars:
- 1,115
- Forks:
- 216
- Description:
- Finding the genre of a song with Deep Learning.
|
|---|
| Borye/machine-learning-coursera-1 | 11,543 | - Stars:
- 1,114
- Forks:
- 886
- Description:
- This repo is specially created for all the work done my me as a part of Coursera's Machine Learning Course.
|
|---|
| ShanghaiTechAIClub/DLInterview | 11,551 | - Stars:
- 1,111
- Forks:
- 204
|
|---|
| burness/tensorflow-101 | 11,557 | - Language:
- Python
- Stars:
- 1,110
- Forks:
- 541
- Description:
- learn code with tensorflow.
|
|---|
| neural-maze/realtime-phone-agents-course | 11,563 | - Language:
- Python
- Stars:
- 1,109
- Forks:
- 253
- Description:
- Build realtime AI voice agents using FastRTC for low-latency streaming, Superlinked for vector search, Twilio for live phone calls, and Runpod for scalable GPU deployment.
|
|---|
| NirDiamant/Agent_Memory_Techniques | 11,567 | - Language:
- Jupyter Notebook
- Stars:
- 1,107
- Forks:
- 144
- Description:
- Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
|
|---|
| Lyken17/Efficient-PyTorch | 11,581 | - Language:
- Python
- Stars:
- 1,104
- Forks:
- 134
- Description:
- My best practice of training large dataset using PyTorch.
|
|---|
| primaryobjects/AI-Programmer | 11,583 | - Language:
- C#
- Stars:
- 1,104
- Forks:
- 262
- Description:
- Using artificial intelligence and genetic algorithms to automatically write programs. Tutorial: http://www.primaryobjects.com/cms/article149.
|
|---|
Key parameters and specifications
Key parameters and specifications| Parameter | Value |
|---|
| Language | Astro |
|---|
| Category | Tutorials |
|---|
| Subcategory | Tool-specific tutorials |
|---|
| Keywords | DevOps, Guardrails, Memory management, Security |
|---|
| Stars | 1,110 |
|---|
| Forks | 94 |
|---|
| Contributors | 3 |
|---|
| Created date | 2026-02-10 |
|---|
| Updated date | 2026-10-14 |
|---|
| Stars in 1 day | 0 |
|---|
| Stars in 7 days | -2 |
|---|
| Rank | 11,558 |
|---|
| Previous rank | 5,995 |
|---|
| Rank change | -5,563 |
|---|
| 7-day stars rank | 18,361 |
|---|
| Previous 7-day stars rank | 17,290 |
|---|
| 7-day stars rank change | -1,071 |
|---|
| Total stars rank | 10,288 |
|---|
| Previous total stars rank | 10,278 |
|---|
| Total stars rank change | -10 |
|---|
README summary
OpenClaw Runbook Checked against OpenClaw at commit ( ) Example config based on a working setup This repo is a practical runbook for running OpenClaw day to day without burning money, exposing your gateway, or trusting random automation you did not inspect. It is not official OpenClaw documentation. It is the way I run OpenClaw after enough broken configs, noisy agents, and avoidable risk to want something predictable. What this is A runbook for people who want OpenClaw to run for weeks
, not minutes Opinionated guidance on models, access, memory, automation, and guardrails Tailscale-first for dashboard/control access Skeptical of third-party skills by default Written from the post-honeymoon phase What this is not A beginner replacement for the official docs A model leaderboard A ClawHub install guide A claim that my exact config is right for everyone Access stance My setup uses Tailscale as the normal access path, including when I am local. The Gateway stays loopback-bound, and
Tailscale handles remote access. If you do not want to sign up for Tailscale, keep OpenClaw local and use a messaging channel such as Telegram for remote use. Avoid public ports and casual LAN exposure unless you know exactly what boundary you are accepting. Skills stance I do not recommend blindly installing third-party skills from ClawHub. Use ClawHub as a discovery and source-reading tool. Find an idea, inspect the source, then ask your agent to rebuild a local
skill for your setup. The example config keeps disabled on purpose. The guide The main guide lives here: guide. md It covers the current setup flow, Tailscale-first access, model routing, memory, automation, skills, and security. Examples The directory contains templates and references: sanitized-config. json - Current sanitized config reference config-example-guide. md - Config section reference agent-prompts. md - Specialized agent examples spawning-patterns. md - Current and subagent patterns heartbeat-example. md - Heartbeat checklist and pattern task-tracking-prompt
. md - Using OpenClaw's task ledger instead of an external black box security-hardening. md - Security baseline and audit workflow security-quickstart. md - Prompts for applying basic guardrails security-patterns. md - VPS setup with Tailscale as the default remote access path skill-builder-prompt. md - Prompt template for rebuilding local skills check-quotas. sh - Optional quota check helper Showcases The directory contains automation patterns you can adapt: daily-brief - Morning summary with weather, calendar, and tasks idea-pipeline - Overnight research on
captured ideas linkedin-drafter - Weekly draft generation tech-discoveries - Curated tech news homelab-access - Safer remote SSH through Telegram confirmations agent-orchestrator - Route coding tasks to configured agents/tools coeus-knowledge-base - Local semantic knowledge base example autonomous-operation - Community-contributed health-check pattern claworc - Community-contributed review of an external control-plane project Treat showcases as starting points. Review tool access, channels, delivery targets, and model choices before running them unattended. Some showcases are community contributions or external project
reviews; keep their attribution intact. Share This If this guide helped you, please consider: sharing it with others who might
Frequently asked questions
How many stars and forks are recorded?
digitalknk/openclaw-runbook has 1,110 stars and 94 forks.
What is the repository rank?
digitalknk/openclaw-runbook is ranked 11,558.
What language and category are recorded?
digitalknk/openclaw-runbook has 1,110 stars, uses Astro and belongs to Tutorials.
Which repository is closest in rank?
digitalknk/openclaw-runbook is compared with burness/tensorflow-101, ranked 11,557 with 1,110 stars.
OpenClaw Runbook
Checked against OpenClaw at commit 5dccba7405 (2026-05-25)
Example config based on a working 2026.5.x setup
This repo is a practical runbook for running OpenClaw day to day without burning money, exposing your gateway, or trusting random automation you did not inspect.
It is not official OpenClaw documentation.
It is not a universal best setup.
It is the way I run OpenClaw after enough broken configs, noisy agents, and avoidable risk to want something predictable.
What this is
- A runbook for people who want OpenClaw to run for weeks, not minutes
- Opinionated guidance on models, access, memory, automation, and guardrails
- Tailscale-first for dashboard/control access
- Skeptical of third-party skills by default
- Written from the post-honeymoon phase
What this is not
- A beginner replacement for the official docs
- A model leaderboard
- A ClawHub install guide
- A claim that my exact config is right for everyone
Access stance
My setup uses Tailscale as the normal access path, including when I am local. The Gateway stays loopback-bound, and Tailscale handles remote access.
If you do not want to sign up for Tailscale, keep OpenClaw local and use a messaging channel such as Telegram for remote use. Avoid public ports and casual LAN exposure unless you know exactly what boundary you are accepting.
Skills stance
I do not recommend blindly installing third-party skills from ClawHub.
Use ClawHub as a discovery and source-reading tool. Find an idea, inspect the source, then ask your agent to rebuild a local skill for your setup. That is slower than clicking install, but it is safer than trusting unknown code, broad tool assumptions, hidden behavior, or token-heavy abstractions.
The example config keeps clawhub disabled on purpose.
The guide
The main guide lives here:
It covers the current setup flow, Tailscale-first access, model routing, memory, automation, skills, and security.
Examples
The examples/ directory contains templates and references:
Showcases
The showcases/ directory contains automation patterns you can adapt:
Treat showcases as starting points. Review tool access, channels, delivery targets, and model choices before running them unattended. Some showcases are community contributions or external project reviews; keep their attribution intact.
Share This
If this guide helped you, please consider:
- sharing it with others who might find it useful;
- linking back if you reference it in blog posts, videos, or other resources;
- submitting your own showcases so others can learn from your setup.
This is a community resource. The more people contribute real working patterns, the better it gets.
Community resources
Contributing
Contributions are welcome, but this is not a free-for-all.
Please read CONTRIBUTING.md before opening issues or pull requests.
License
MIT