See more of my writing here.

In this post, I'll start from scratch and build up to OpenClaw's architecture step by step, showing how you could have invented it yourself from first principles, using nothing but a messaging API, an LLM, and the desire to make AI actually useful outside the chat window.

End goal: understand how persistent AI assistants work, so you can build your own (or become an OpenClaw power user).

When you use ChatGPT or Claude in a browser, there are several limitations:

As currently described, this approach does not work. The reason for that is that creating a snapshot via the API does not actually populate any data, as described in e.g. https://community.grafana.com/t/snapshot-using-http-api-does-nothing/. An alternative approach which does work described in https://gist.github.com/svet-b/1ad0656cd3ce0e1a633e16eb20f66425.

Packages:

• The jq JSON processing command line tool, which is available for most distributions (https://stedolan.github.io/jq/, sudo apt install jq)
• NodeJS, and the puppeteer package (npm install puppeteer), which is used to run headless Chrome

PI is a TypeScript toolkit for building AI agents. It's a monorepo of packages that layer on top of each other: pi-ai handles LLM communication across providers, pi-agent-core adds the agent loop with tool calling, pi-coding-agent gives you a full coding agent with built-in tools, session persistence, and extensibility, and pi-tui provides a terminal UI for building CLI interfaces.

These are the same packages that power OpenClaw. This guide walks through each layer, progressively building up to a fully featured coding assistant with a terminal UI, session persistence, and custom tools.

By understanding how to compose these layers, you can build production-grade agentic software on your own terms, without being locked into a specific abstraction.

Pi was created by @badlogicgames. This is a great writeup from him that explains some of the design decisions made when creating it.

Todos os prompts usados pelo orchestrator (src/dev-team-orchestrator.ts), em ordem lógica de execução.

Variáveis em {{duplas chaves}} são substituídas em runtime pelo TypeScript.

Participate in the Obmondo Sovereign Sprint by deploying the infrastructure stack and sharing proof of your deployment.

Follow the steps below to qualify.

How to use this script:

1. Accept a quest under the Quests tab
2. Press Ctrl+Shift+I to open DevTools
3. Go to the Console tab
4. Paste the following code and hit enter:

This gist was created to explore options for working with NixOS in a completely offline environment or inside a network with restricted internet access (such as a corporate LAN with a Proxy).

• I discoverd that the graphical installation ISO had no ability to install offline, so I created this repo which allows creating custom offline installation ISOs using the graphical installer
• Kevin Cox created a similar repo on Gitlab his version focuses more on automatation and uses the minimal install ISO rather than the graphical ISO
• This is another similar project that is less recent: https://github.com/tfc/nixos-offline-installer
• https://determinate.systems/posts/moving-stuff-around-with-nix

This guide will help you set up a complete LaTeX environment on Windows with MiKTeX, VS Code, and automatic formatting with latexindent.

• Windows 10/11
• Package manager (Chocolatey, Winget, or Scoop)
• VS Code (or install it during this process)