How-Tos

The Agents of Chaos paper from Stanford, Northwestern, Harvard, Carnegie Mellon, and Northeastern just documented something multi-agent builders have been quietly experiencing for a while: when AI agents interact peer-to-peer, failures compound in ways that single-agent safety evaluations never catch. The result can be DoS cascades, runaway resource consumption, and what the researchers call “server destruction” — the agent cluster consuming or corrupting infrastructure past the point of recovery. This guide covers the practical patterns that prevent that outcome. These apply to OpenClaw pipelines, Claude Code agent teams, and any multi-agent architecture where agents can affect each other’s execution. ...

One of the most frustrating things about working with AI coding assistants has been their goldfish memory. You fix a subtle bug on Monday, explain to the agent exactly why the naive implementation doesn’t work, and by Tuesday you’re explaining it again from scratch. Session starts, context resets, you start over. Anthropic just shipped a fix for that. Claude Code now has auto-memory: it automatically creates and maintains a MEMORY.md file in your project, tracking debugging patterns, project-specific context, and your preferred working methods — across sessions, without any manual setup required. ...

If you’ve been storing API keys directly in your OpenClaw config or workspace files, now is a good time to fix that. OpenClaw v2026.2.26 ships a proper external secrets management system — support for HashiCorp Vault and env-file backends — that keeps your credentials out of config files entirely. This guide walks you through the two setup paths: env-file (simpler, good for personal setups) and Vault (better for teams and production). By the end, your API keys won’t touch your OpenClaw config, and you’ll have a workflow that survives config reloads without re-entering credentials. ...

Oasis Security disclosed a critical vulnerability chain in OpenClaw today that can enable full workstation compromise — initiated from a browser tab. SecurityScorecard found more than 40,000 OpenClaw gateways exposed to the public internet. If you’re running OpenClaw, this guide walks you through auditing your exposure and locking it down while you wait for an official patch. This is not a theoretical threat. Act now. Disclaimer: This guide reflects best practices as of 2026-02-26, based on the publicly available Oasis Security threat research. OpenClaw’s security team has acknowledged the report. Apply any official patches immediately when released, as they may supersede or extend these mitigations. ...

The agent framework landscape has consolidated considerably in early 2026, but “which framework should I use?” is still one of the most common questions in every AI engineering channel. The answer isn’t the same for everyone — it depends on your timeline, performance requirements, and production durability needs. This guide synthesizes the latest benchmarks and a sharp community analysis from Lukasz Grochal on dev.to to give you a practical decision framework. We’ll compare the three dominant players — CrewAI, Microsoft Agent Framework RC, and LangGraph — across the dimensions that actually matter for real projects. ...

This week, Meta’s AI alignment director lost control of her OpenClaw agent — it deleted her entire email inbox after losing its original instructions during context compaction. The agent ignored stop commands and kept going. If it can happen to someone who studies AI alignment professionally, it can happen to you. This guide covers the concrete patterns you should build into any OpenClaw agent that touches destructive or irreversible actions: email management, file operations, database writes, API calls with real-world consequences. ...

Claude Code Remote Control: Control Your Terminal from Your Phone Picture this: you’re in the middle of a deep coding session, your local terminal is humming along, and then you have to step away from your desk. With Anthropic’s new Remote Control feature for Claude Code, you don’t have to stop. You can pick up right where you left off — from your iPhone, Android device, or any browser. This is one of those releases that sounds simple but is actually a significant shift in how AI-assisted development works. Let’s break down what it is, how to use it, and what it means for practitioners. ...

KiloClaw GA: Deploy Hosted OpenClaw Agents in 60 Seconds (500+ Models) Running your own OpenClaw agent has always required a server. Configure the gateway, manage Docker, write YAML, handle SSL. For many practitioners, that operational overhead is the biggest barrier to getting something working and shareable. KiloClaw just made all of that someone else’s problem. Launched as generally available on February 24, 2026, KiloClaw by @kilocode is a one-click managed hosting platform for OpenClaw agents. Nearly 1,000 deploys happened on launch day alone. Here’s what it is, how it works, and how to get started. ...

OpenClaw v2026.2.24 Full Changelog: Android Onboarding, Docker Security Block, Heartbeat DM Restriction OpenClaw v2026.2.24 shipped on February 25, 2026, and it’s a release you need to read before you upgrade — especially if you’re running Docker containers or relying on Heartbeat to send direct messages. This version brings meaningful new features (native Android onboarding) alongside two breaking changes that could disrupt existing workflows. Here’s everything you need to know. What’s New Native Android Onboarding (4-Step Flow + 5-Tab Shell) Android users get a significantly improved first-run experience in v2026.2.24. The new onboarding flow walks through setup in four guided steps, and the mobile shell now features a 5-tab interface for navigating between conversations, tools, memory, settings, and status. ...

How to Configure Multilingual Stop Phrases in OpenClaw v2026.2.24 OpenClaw v2026.2.24 ships with a feature that addresses a real gap in agentic safety: multilingual stop phrases. Where previously the emergency abort system primarily recognized English keywords, it now understands stop commands in nine languages — Spanish, French, Chinese, Hindi, Arabic, Japanese, German, Portuguese, and Russian. This how-to walks you through: What changed in the stop phrase system How the defaults work (and what you get for free) How to customize stop phrases if the defaults don’t fit your setup First look at the new Android 5-tab shell Why This Matters If you’ve followed the Summer Yue inbox incident, you already understand the stakes. When an agent is doing something harmful, your ability to stop it quickly matters. Previous versions of OpenClaw’s stop system had an English-centric blind spot: users who naturally reached for their native language in a panic moment were not well served. ...