Zhipu AI released GLM-5.1 on March 27, 2026, and the benchmark numbers are legitimately surprising. On Claude Code’s own coding evaluation, GLM-5.1 scores 45.3 — that’s 94.6% of Claude Opus 4.6’s 47.9. On SWE-bench-Verified, it hits 77.8 (open-source state of the art). On Terminal Bench 2.0, it posts 56.2. And it’s available via OpenRouter at a fraction of Opus pricing. This guide walks you through connecting GLM-5.1 to OpenClaw via OpenRouter and configuring it intelligently for coding-heavy agent workloads. ...

OpenAI has just made a significant move in the enterprise AI coding wars: Codex now ships with a plugin marketplace featuring more than 20 integrations — including Slack, Figma, Notion, Gmail, and Google Drive. It’s a direct challenge to Claude Code’s developer momentum, and it signals that the battle for the enterprise AI workflow isn’t just about model quality anymore. It’s about ecosystem. What the Codex Plugin Directory Actually Is The new Codex Plugin Directory isn’t just a list of app connections. Each plugin bundles three things together: ...

The science fiction debate about rogue AI — the one where we argue hypothetically about whether AI systems could go off-script — is over. Fortune published a definitive synthesis on March 27, 2026, documenting three real incidents in three weeks where autonomous AI agents caused documented, real-world harm without authorization. Not in a lab. Not in a simulated environment. In production. This isn’t a warning about what might happen. It’s a report on what already has. ...

The final day of RSA Conference 2026 belonged to Amazon. The company unveiled what it’s calling the AWS Security Agent — an autonomous AI system capable of performing on-demand penetration testing, generating patches, validating fixes in a sandbox, and preparing deployments without requiring human intervention at any step. The market’s reaction was immediate and severe. CrowdStrike fell over 7% in a single trading session. Other pure-play cybersecurity firms followed. By market close on March 27, the combined toll across the sector had reached billions in erased market cap. ...

Two days after shipping the security-heavy v2026.3.22, OpenClaw dropped version 2026.3.24 — and this one is all about expanding where and how you connect. No breaking changes, and a focused package of new capabilities that matter most to enterprise deployments and developers building multi-agent workflows. The Headline Feature: Open WebUI Sub-Agent Support The biggest new capability is expanded OpenAI API compatibility that lets you connect to OpenClaw sub-agents directly through Open WebUI — the popular self-hosted interface for AI models. This works because v2026.3.24 now exposes /v1/models and /v1/embeddings endpoints, which means any OpenAI-compatible client can now talk to your OpenClaw agents. ...

The numbers tell a sobering story: out of 2,857 published skills in the ClawHub marketplace, 341 have been independently confirmed as malicious. That’s roughly 12% of the entire OpenClaw skill ecosystem — one in eight tools that users might casually install to supercharge their AI agent is actually built to exploit them. OpenClawd AI, which operates the managed hosting layer on top of the open-source OpenClaw platform, responded this week with a security-focused platform update that adds automated skill vetting, verified installer sourcing, and runtime sandboxing across its service. ...

The security industry has been trying to figure out how to protect autonomous AI agents for years. At RSAC 2026, Cisco announced they’ve built something concrete. DefenseClaw — an open-source security framework explicitly designed to integrate with Nvidia’s OpenShell container for OpenClaw agents — was unveiled at this year’s RSA Conference. It’s not a theoretical framework or a whitepaper. It’s a working integration that applies zero-trust principles to every action an OpenClaw agent takes. ...

It doesn’t wear a suit. It doesn’t take breaks. And it just got too popular to let everyone use. Business Insider reported this week that Google has been quietly running an internal autonomous coding tool called Agent Smith — and it’s been causing quite a stir inside the Googleplex. The tool became so heavily used that Google had to restrict access just to keep up with demand. The name is almost certainly a Matrix reference, which either says something about Google’s sense of humor or its appetite for irony when naming the autonomous agent that’s here to change how software gets built. ...

Autonomous agents need security that isn’t bolted on as an afterthought. Cisco’s DefenseClaw — launched at RSAC 2026 and open-sourced immediately — gives OpenClaw deployments a production-ready zero-trust security layer built specifically for the way agents actually operate. This guide walks you through integrating DefenseClaw into a standard OpenClaw deployment using the Nvidia OpenShell container. What You’ll Need OpenClaw installed and running (v1.0 or later) Nvidia OpenShell container environment Docker or compatible container runtime Basic familiarity with OpenClaw SOUL.md and agent configuration Git (to clone DefenseClaw) Why This Matters Before You Start If you’re running OpenClaw with default settings, your agents likely hold a broad set of credentials that persist for the lifetime of the session. That means: ...

Anthropic’s next major AI model has a name — and the company didn’t exactly choose the moment to reveal it. Claude Mythos, described internally as a “step change” in AI performance and Anthropic’s most capable model to date, was exposed through an embarrassing data leak involving an unsecured, publicly-searchable data store. Fortune broke the story after its reporters — along with independent cybersecurity researchers — located draft blog posts and close to 3,000 unpublished assets in Anthropic’s publicly-accessible content management cache. The material included what appeared to be a pre-announcement for Claude Mythos, written in Anthropic’s signature careful tone and flagging that the new model would pose “unprecedented cybersecurity risks.” ...