SUB30
SUB30
Loading...
Tips, guides, and news from the ClawHosters team.
OpenClaw v2026.3.7 shipped on March 8 with 89 commits, over 200 bug fixes, and three features that genuinely change how the platform works. Here's what you need to know.
DigitalOcean just leveled up its OpenClaw game. The cloud provider expanded beyond its existing $12/month 1-Click Droplet to launch OpenClaw on App Platform — making it the first major cloud provider to offer multi-agent support with elastic scaling for OpenClaw deployments.
If you already run a Kubernetes cluster, deploying an AI agent via Helm makes sense. Your infrastructure team knows the tooling, you've got monitoring in place, and one more workload probably won't break the bank.
On March 6, nearly 1,000 people lined up outside Tencent's Shenzhen headquarters with laptops and hard drives, waiting to get OpenClaw installed for free. Five days later, China's government told state employees to uninstall it.
Bitdefender's latest advisory doesn't sugarcoat it. Their "Technical Advisory: OpenClaw Exploitation in Enterprise Networks" paints a picture of corporate networks riddled with unauthorized AI agents that nobody in IT approved.
OpenClaw custom skills are Markdown files. Not compiled binaries, not API wrappers, not Docker containers. Just a folder with a file called `SKILL.md` inside it. The agent reads your instructions at runtime and follows them.
Nearly 1,000 people lined up outside Tencent's Shenzhen headquarters on March 6. Not for a product launch. Not for a concert. For a free AI agent installation.
Eleven days. That's how long it took from the first ClawHavoc attack on January 27 to OpenClaw announcing a partnership with Google's VirusTotal on February 7. In between, security researchers found 1,184 malicious skills on ClawHub, most of them traced back to a single attacker going by...
Zero API costs. Your data never leaves your machine. And since Ollama 0.17 shipped in February 2026, the setup takes one command. That's the pitch for running OpenClaw with a local LLM, and it's mostly true.
Mastercard just published something that should probably worry anyone running an OpenClaw instance without proper security. Their article, "OpenClaw and the urgent need for AI security standards", doesn't mince words about what's at stake.
Google quietly published a CLI tool called `gws` to GitHub on March 2, and it's probably the most interesting thing to happen for OpenClaw users this month.
Most people treat OpenClaw like a chat assistant. Type a question, get an answer. But that's like using a Formula 1 car to drive to the grocery store. OpenClaw is a modular prompt assembly runtime, and `SOUL.md` is the file that tells it who to be.
