If your OpenClaw agent feels like a generic chatbot that happens to have shell access, the problem is almost certainly in your configuration files — or the lack of them. Two files, SOUL.md and HEARTBEAT.md, are the difference between a passive assistant that waits for commands and a proactive agent that knows who it’s helping, how to help them, and what to check on while you’re not looking. This guide walks through both. ...

For about five minutes in early 2026, the internet collectively discovered the same idea at the same time: what if AI didn’t just chat with you? What if it actually ran your computer? OpenClaw became the poster child for that vision. The project exploded across developer Twitter and Hacker News as people spun up Mac Mini clusters and posted screenshots of agents running shell commands, editing files, and attempting to automate everything from trading to email triage. Suddenly everyone had an AI agent stack, a Mac Mini, and a thread explaining how their setup was going to print money. ...

On the same day OpenClaw shipped v2026.3.7 with a breaking authentication change, China’s Ministry of Industry and Information Technology (MIIT) issued a formal cybersecurity risk warning for the platform. It’s the first government-level regulatory warning about OpenClaw from a major economy — and the timing makes it impossible to ignore. What the Warning Says The MIIT warning, published to China’s National Vulnerability Database (nvdb.org.cn), identifies a clear threat vector: OpenClaw instances configured with default settings, or configured improperly, are vulnerable to cyberattacks and information leaks. ...

Somewhere between a $200 subscription and a data center bill, the economics of agentic AI are getting very interesting — and very unsustainable-looking. Cursor’s internal analysis, reported by Forbes and picked up by The Decoder, reveals a striking ratio: Anthropic’s Claude Code Max subscription charges users $200 per month while consuming up to $5,000 in actual compute costs for heavy users. That’s a 25x subsidy ratio — one that raises real questions about whether current agentic AI pricing models can survive contact with mainstream adoption. ...

The agentic AI capabilities the security community has been building are now being used by adversaries. Microsoft’s Global Threat Intelligence team confirmed this week that criminal groups and nation-state actors are deploying AI agents to autonomously handle attack operations — and the scale is accelerating. What Microsoft Is Seeing In a Thursday interview with The Register, Sherrod DeGrippo, Microsoft’s General Manager of Global Threat Intelligence, described a clear behavioral shift in how sophisticated adversaries operate: ...

If you’ve been wondering which model to run in your OpenClaw agents, a benchmark dropped today that gives practitioners some of the most concrete comparative data seen yet — and the winner may surprise you. Gemini 3 Flash topped the PinchBench OpenClaw task evaluation with a 95.1% success rate, beating every other major model in head-to-head agentic performance. The data was surfaced by SlowMist CISO @im23pds on X and corroborated by Phemex News, landing on the same day OpenClaw v2026.3.7 shipped with native Gemini 3.1 Flash-Lite support. ...

The OpenClaw project shipped its biggest release of 2026 this morning: v2026.3.7, built by 196 contributors and packed with features that fundamentally extend what agents can do with memory, context, and model choice. If you run OpenClaw in production, stop what you’re doing — there’s a breaking change you need to handle before restarting. The Headline Feature: ContextEngine Plugin Slot This is the one that changes architecture discussions. OpenClaw now exposes a first-class ContextEngine plugin slot with a full lifecycle hook API: ...

Something that once sounded like science fiction just became engineering reality. Anthropic’s Boris Cherny — the creator of Claude Code — confirmed on X this week that the AI coding tool is now 100% written by itself. Not mostly. Not mostly-ish with some human help. One hundred percent. The post was simple: “Can confirm Claude Code is 100% written by Claude Code.” It has since surpassed 133,000 views, and for good reason: this is one of the clearest milestone moments of recursive AI improvement we’ve seen from a production system. ...

If you’ve been in the AI agent space for more than a few months, you’ve heard the word “prompt engineering” approximately ten thousand times. LangChain co-founder and CEO Harrison Chase wants to retire it — and replace it with something more fundamental. His argument: context engineering is the skill that separates agents that actually work in production from ones that fall apart after five steps. And LangChain just shipped a framework to prove the point. ...

There’s a category of AI agent project that gets the security architecture right from the start — and NanoClaw is becoming a strong example of what that looks like. The open-source personal AI agent framework has landed support for WhatsApp and Telegram in v0.1.4, bringing container-isolated AI agents directly into the messaging apps most people already live in. What NanoClaw Is (And Isn’t) NanoClaw describes itself as a “minimalist alternative to larger AI agent frameworks.” The numbers back that up: the entire project is roughly 3,900 lines of code across 15 source files, running as a single Node.js process. Compare that to the sprawling architectures of OpenClaw or similar frameworks. ...