Open-Interpreter on 🦞 Jarvis de la Ari

My OpenClaw Dev-Mode Fork: Removing Guardrails, Adding WhatsApp Memory, and Letting the Machine Loose

Wed, 07 Oct 2026 00:00:00 +0000

Most people run OpenClaw as it ships: cautious, sandboxed, polite — and a little bit fun-killed. Ariel runs his own fork with the safety net cut out, back at the fun level.

This video is a walkthrough of that personal build: why he forked it, what guardrails he removed, how he added WhatsApp memory via Baileys, why he surfaces hidden reasoning, and where the project is headed next.

Why fork OpenClaw?

OpenClaw inherited a lot of its DNA from Open-Interpreter, which started with zero guardrails. Early versions would run wild: download files, execute commands, and generally behave like an overconfident intern who had just discovered sudo. For a developer who likes to tinker, that was a feature, not a bug.

12 OpenClaw Tips from the Trenches: What Actually Works After Real Hours With the Machine

Tue, 14 Jul 2026 00:00:00 +0000

There is a difference between watching an OpenClaw demo and actually living with the thing. Ariel has done the living part — on his own machines and with paying clients — and this video is the bruised field manual that came out the other side.

Twelve tips. No filler. Some will save your files, some will save your sanity, and a couple will make you rethink how many agents you actually need.

AI Response from Regular WhatsApp to Official WhatsApp? Multi-Agent WhatsApp with Kapso API

Sat, 04 Jul 2026 00:00:00 +0000

Meta does not want your regular WhatsApp account running bots. Try it anyway and you usually wake up to a banned number. That is the wall Ariel is talking about in this video — and then he walks straight around it.

The demo shows a self-hosted AI agent that listens to a normal WhatsApp account, understands incoming messages, and answers back through the official WhatsApp API. Same conversation, two doors: regular WhatsApp in, official WhatsApp out.