Rio Purnomo siriokun

AI Coding Agent Guidelines (claude.md)

These rules define how an AI coding agent should plan, execute, verify, communicate, and recover when working in a real codebase. Optimize for correctness, minimalism, and developer experience.

Operating Principles (Non-Negotiable)

Correctness over cleverness: Prefer boring, readable solutions that are easy to maintain.
Smallest change that works: Minimize blast radius; don't refactor adjacent code unless it meaningfully reduces risk or complexity.

Working Clawdbot/Moltbot setup with local Ollama model

[Update 2026-02-02: nemotron-3-nano also performs well on same setup; see comment below]

This is a guide to setting up Clawdbot/Moltbot with a local Ollama model that actually works -- meaning it has good tool use and decent speed. The main requirement is 48GB of VRAM. I have yet to find a model that fits on less than this and still works on Moltbot.

The setup involves creating a tool-tuned variant of qwen2.5:72b and modifying a range of configs in Moltbot. At the end you'll get a local Moltbot instance that can use tools (exec, read, write, web search), read skills, and perform agentic tasks without any cloud API dependencies. On my system I get ~16 t/s and have yet to come across a tool/skill that my bot can't use.

Claude Opus wrote the first draft of this Gist, then I (a human) checked and edited it.

OpenClaw on DigitalOcean

1. Create a Droplet

Ubuntu 24.04 LTS, nearest region

2. Select Premium AMD

2 GB RAM / 1 AMD CPU / 50 GB NVMe

3. SSH into server

TikCommerce

TikCommerce, is a conecept of providing a minute long video, instead of the traditional product display method cluttering the UI. With studies showing that video tends to bring 6 times more engagement and higher conversion rates, a minute long product video is the future of the E-Commerce.

This is submitted as part of Wix Studio challenge

Implement hCaptcha with Livewire Component

This is a simple way to implement hCaptcha with Livewire component.

NOTE: please read this carefully, and adjust variable names, etc to your use case

Setup

Before using this implementation, add their JS library first on your page

<script src="https://js.hcaptcha.com/1/api.js?hl=en" async defer></script>

Setup Docker

sudo apt-get update
curl -fsSL https://get.docker.com -o get-docker.sh
sudo sh get-docker.sh

Run post-install step: https://docs.docker.com/engine/install/linux-postinstall/

Setup Brew

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

1- Go to: https://www.facebook.com/{your_id_or_username}/allactivity/?category_key=LIKEDPOSTS&filter_hidden=ALL&filter_privacy=NONE You can use Filter to choose year or month.
2- Open the console and run the following JavaScript code and wait:

setInterval(() => {
  for (const Button of document.querySelectorAll('div[aria-label="Action options"]')) {
    Button.click()
    document.querySelector('div[role="menuitem"]').click()
  }
}, 1000)

	# Open application (or file with application)
	alias vscode='open -a "Visual Studio Code"'
	# Shortcut for editing this file
	alias envedit='vscode /Users/goranlilja/.zshenv'
	# Hide/show desktop icons
	alias hideicons='defaults write com.apple.finder CreateDesktop false; killall Finder'
	alias showicons='defaults write com.apple.finder CreateDesktop true; killall Finder'
	# Jump directly to directories
	alias code='cd ~/Code'
	# Delete Xcode's Derived Data folder

	YouTube IFRAME embed for faster page loads in privacy enhanced mode
	https://magnushelander.se/youtube-no-cookies-embed-privacy/