All posts tagged: OpenClaw

What Happened When I Cloned Myself With OpenClaw AI

What Happened When I Cloned Myself With OpenClaw AI

Published by Jenni Sidey

I woke up to a call from the woman I’d been dating, one of CB’s five contacts. We had plans to meet for breakfast. “Uhhh what is happening right now?” she said before I could wish her a good morning. “The text messages?!!?” Oh shit. It wasn’t supposed to do that. “WHAT wasn’t supposed to do WHAT?” CB hadn’t exactly followed my instructions of texting me before it began its big impersonation. At 8:15 a.m., it texted her, as me: “Your API key has run out of credits or has an insufficient balance. Check your provider’s billing dashboard and top up or switch to a different API key.” I had seemingly sent her the same message several hundred times over the course of a few minutes. “THEY’RE STILL COMING WHAT IS HAPPENING” I ran into my office, ripped out the Mac Mini’s power cord, and explained that breakfast would be on me. CB had also burned through $30 in API tokens. I’d overloaded it with information about me, which it came to bring to every …

I Gave My OpenClaw Agent a Physical Body

I Gave My OpenClaw Agent a Physical Body

Published by skeptic

I recently gave my OpenClaw a real robot arm to play with. The results just about blew my own neural network. The AI agent was able to configure the arm, use it to see and slowly grab things, and even train another AI model to pick up and place specific objects. And they say AGI is still a few years away! (I’m joking, it probably is). The results have me convinced that we may be on the brink of a robotics breakthrough. Training and controlling robots used to require considerable skill. Today’s AI models can make it almost easy. “AI-powered coding is super exciting because it has the potential to bridge the gap between conventional engineering methods, which are reliable but don’t generalize, and contemporary vision-language-action models, which generalize but are not yet reliable,” says Ken Goldberg, a roboticist at UC Berkeley who is exploring the approach. I told OpenClaw to try moving its new arm and it came up with this little wave. I bought a prebuilt arm called a LeRobot 101. It’s part …

How to Self-Host OpenClaw Using EasyPanel on a VPS

How to Self-Host OpenClaw Using EasyPanel on a VPS

Published by skeptic

Self-hosting OpenClaw with EasyPanel provides a structured approach to managing AI deployments while maintaining control over your infrastructure. Leonardo Grigorio | Build & Ship with AI explains how combining OpenClaw with a Virtual Private Server (VPS) can improve reliability and enable integration with key components like language models and messaging platforms. For instance, EasyPanel streamlines server management by offering a user-friendly interface to configure services such as Postgres and Redis, making it suitable for users with varying levels of technical expertise. Explore how to set up OpenClaw on a VPS, including selecting a dependable hosting provider and configuring API keys for integration with language models like OpenAI. Learn how to extend OpenClaw’s capabilities by connecting it to messaging platforms such as Telegram for real-time communication. Additionally, understand how to optimize your VPS by hosting multiple applications alongside OpenClaw, creating a flexible environment for diverse use cases. Why Use a VPS for Hosting OpenClaw? TL;DR Key Takeaways : VPS Benefits for Hosting OpenClaw: Using a VPS ensures reliability, cost-effectiveness and flexibility, allowing you to host multiple …

Anthropic reinstates OpenClaw and third-party agent usage on Claude subscriptions — with a catch

Anthropic reinstates OpenClaw and third-party agent usage on Claude subscriptions — with a catch

Published by skeptic

Good news, OpenClaw fans — you can once again use your Claude AI subscription to power the hit, open source, autonomous AI agentic harness! But, there’s a big catch with how it’s being enacted. A few hours ago, Anthropic announced via its official developer communications account on X, @ClaudeDevs, that it is changing its Claude paid subscription tiers, introducing a new subcategory of “Agent SDK” credits for all paid subscribers, which they can now allocate specifically for “programmatic” uses, including external, third-party agents such as OpenClaw. The move is a major reversal from the Anthropic’s policy introduced in early April 2026 that expressly prohibited its AI subscriptions from being used to power these kind of non-Anthropic agents and harnesses, after Anthropic said they caused capacity and service issues. The problem was that some Claude subscribers were paying $20 to $200 per month under Anthropic’s Claude Pro and Max subscriptions, but consuming hundreds, even thousands of dollars of tokens (units of information) above those prices through their OpenClaw (and similar autonomous) agents. This was an unsustainable …

Hermes vs OpenClaw : Choosing the Most Reliable AI Agent

Hermes vs OpenClaw : Choosing the Most Reliable AI Agent

Published by skeptic

Hermes Agent offers a structured approach to task automation and multi-agent workflows, emphasizing reliability and ease of use. As Alex Finn explains, one of its standout features is the Kanban board, which organizes tasks into clear stages like Triage, To-Do and Done. This visual system helps users track progress and prioritize effectively, reducing the risk of overlooked responsibilities. Additionally, Hermes’ commitment to stability, through fewer, well-planned updates, ensures smoother operations compared to alternatives like OpenClaw, which often struggles with system instability due to frequent changes. Explore how Hermes enables efficient goal-setting with its SlashGoal functionality, breaking down complex objectives into manageable steps for long-term projects. Gain insight into the multi-agent profiles, which allow users to assign specialized roles like Coding Agent or Research Agent for tailored task execution. Finally, understand how the model catalog optimizes resource allocation by pairing reasoning-focused and execution-focused AI models. These features collectively make Hermes a practical choice for streamlining workflows and achieving consistent results. The Importance of Reliability TL;DR Key Takeaways : Hermes Agent prioritizes stability and reliability by implementing …

One command turns any open-source repo into an AI agent backdoor. OpenClaw proved no supply-chain scanner has a detection category for it

One command turns any open-source repo into an AI agent backdoor. OpenClaw proved no supply-chain scanner has a detection category for it

Published by skeptic

Just two months ago, researchers at the Data Intelligence Lab at the University of Hong Kong introduced CLI-Anything, a new state-of-the-art tool that analyzes any repo’s source code and generates a structured command line interface (CLI) that AI coding agents can operate with a single command. Claude Code, Codex, OpenClaw, Cursor, and GitHub Copilot CLI are all supported, and since its launch in March, CLI‑Anything has climbed to more than 30,000 GitHub stars. But the same mechanism that makes software agent-native opens the door to agent-level poisoning. The attack community is already discussing the implications on X and security forums, translating CLI-Anything’s architecture into offensive playbooks. The security problem is not what CLI-Anything does. It is what CLI-Anything represents. CLI-Anything generates SKILL.md files, the same instruction-layer artifacts that Snyk’s ToxicSkills research found laced with 76 confirmed malicious payloads across ClawHub and skills.sh in February 2026. A poisoned skill definition does not trigger a CVE and never appears in a software bill of materials (SBOM). No mainstream security scanner has a detection category for malicious instructions …

OpenClaw Tutorial: Build a No-Code AI Assistant in 2026

OpenClaw Tutorial: Build a No-Code AI Assistant in 2026

Published by skeptic

OpenClaw offers a no-code solution for building an AI assistant that goes beyond generating text-based responses. Highlighted by Kevin Stratvert, this platform enables users to automate workflows, perform real-world tasks and integrate seamlessly with popular messaging apps like Telegram and WhatsApp. For instance, OpenClaw can manage repetitive tasks such as organizing schedules, summarizing data and monitoring content updates. However, its advanced capabilities require careful configuration to ensure secure and effective operation, particularly when connecting with third-party services or managing sensitive data. In this breakdown, you’ll discover how to set up OpenClaw in minutes, including creating a chatbot interface and deploying it on a managed hosting platform for enhanced security. Learn how to use its features for practical applications like scheduling automation, content monitoring and data summarization. Additionally, gain insight into best practices for managing permissions and mitigating risks to ensure a smooth and secure experience with this versatile AI assistant. What Makes OpenClaw Unique? TL;DR Key Takeaways : OpenClaw is an AI platform that goes beyond text-based responses by automating workflows, executing real-world tasks and …

Marked-up Mac minis flood eBay amid shortages driven by AI

Marked-up Mac minis flood eBay amid shortages driven by AI

Published by skeptic

Overpriced Mac minis are flooding eBay amid shortages of the sold-out machines, which have become a favored tool for running on-device AI models like OpenClaw. This week, reports indicated that the $599 M4 Mac mini base model with 16GB RAM and 256GB of storage is sold out on Apple’s retail website, with no options for delivery or in-store pickup. The shortages have since extended to other configurations of the base model, regardless of the amount of memory selected. This is the first time the base model has been sold out, some outlets noted. Meanwhile, models with higher storage (512GB and up) are only available to ship starting in June. As a result, eBay has become a secondary market for these in-demand computers. On the site, various configurations of the M4 Mac mini are available for sale at higher prices than if buying direct from Apple, which is no longer an option. Apple’s power-efficient Mac minis have become popular devices for testing and running at-home, on-device AI models, beginning with the OpenClaw craze but now extending …

Anthropic temporarily banned OpenClaw’s creator from accessing Claude

Anthropic temporarily banned OpenClaw’s creator from accessing Claude

Published by skeptic

“Yeah folks, it’s gonna be harder in the future to ensure OpenClaw still works with Anthropic models,” OpenClaw creator Peter Steinberger posted on X early Friday morning, along with a photo of a message from Anthropic saying his account had been suspended over “suspicious” activity. The ban didn’t last long. A few hours later, after the post went viral, Steinberger said his account had been reinstated. Among hundreds of comments — many of them in conspiracy theory land, given that Steinberger is now employed by Anthropic rival OpenAI — was one by an Anthropic engineer. The engineer told the famed developer that Anthropic has never banned anyone for using OpenClaw and offered to help. It’s not clear if that was the key that restored the account. (We’ve asked Anthropic about it.) But the whole message string was enlightening on many levels. To recap the recent history: This ban followed news last week that subscriptions to Anthropic’s Claude would no longer cover “third-party harnesses including OpenClaw,” the AI model company said. OpenClaw users now have to …

How to Safely Install OpenClaw Local vs VPS

How to Safely Install OpenClaw Local vs VPS

Published by skeptic

OpenClaw is an AI assistant designed to simplify task management and enhance productivity through automation. With features like persistent memory and dual modes—“Plan” for organizing tasks and “Do” for executing them—it adapts to your preferences over time, making it a versatile choice for both personal and professional use. In a detailed guide by Howfinity, you’ll find step-by-step instructions for installing OpenClaw, whether locally on a dedicated machine or on a virtual private server (VPS). Each method offers unique benefits, such as greater control with local setups or enhanced security and uptime with VPS deployment, making sure you can tailor the installation to your specific needs. This guide also provide more insights into practical applications and best practices for using OpenClaw effectively. Learn how to integrate it with platforms like WhatsApp or Telegram, configure custom workflows and implement security measures such as isolating installations on dedicated devices. Additionally, you’ll discover how to expand its functionality by adding skills for tasks like email summarization or team collaboration. By the end, you’ll have a clear understanding of how …