How-Tos & Practical Guides

When people talk about multi-agent AI development teams, they usually mean two or three agents working together on a task. Peter Steinberger means something different. Steinberger — founder of OpenClaw and now an engineer at OpenAI — runs approximately 100 Codex instances in continuous operation. They write code, review pull requests, find bugs, deduplicate GitHub issues, monitor benchmarks, and even attend meetings to draft PRs for features discussed in conversation. In 30 days, his team’s OpenAI API bill hit $1.3 million for 603 billion tokens across 7.6 million requests. The top model powering it all: GPT-5.5. ...

If you’ve been running OpenClaw with OpenAI models and paying separately for API access, that just changed. OpenClaw now routes all OpenAI model requests through the native Codex runtime harness by default, and it’s powered by your existing ChatGPT Plus, Pro, or Team subscription. No separate API key. No double billing. Sign in via OAuth, and your ChatGPT plan funds your OpenClaw agents. What Changed OpenAI announced the Codex runtime integration in early May 2026. The key shift: instead of OpenClaw calling the OpenAI API directly with a developer API key, it now uses the Codex runtime harness — the same infrastructure powering Codex in the ChatGPT interface — accessed through your existing subscription credentials. ...

OpenClaw is running two release tracks simultaneously this week: v2026.5.12 is the latest stable release, and v2026.5.16-beta.1 is the current leading beta. Together they represent the most significant package of security and performance improvements OpenClaw has shipped since earlier this year. Here’s what’s in each track, why the changes matter for production agent deployments, and how to think about upgrading. v2026.5.12 Stable — What Changed Major Memory Leak Fix The most important change in v2026.5.12 is a fix for a memory leak that caused significant RSS (Resident Set Size) growth when processing large transcripts. ...

xAI’s Grok Build launched in early beta on May 14, 2026 — and if you’re a SuperGrok Heavy subscriber, you already have access to one of the most ambitious agentic coding CLIs in the field. This guide walks you through what you need to get started, what to expect from the parallel subagent architecture, and how to make the most of the Plan–Review–Approve workflow. Note: Grok Build is in early beta as of this writing. Some installation steps, specific commands, and configuration options may change as the product matures. Always refer to xAI’s official documentation at x.ai for the most current setup instructions. ...

If you’ve run long agentic sessions in Claude Code, you’ve probably hit this: the agent wraps up, reports success, and something is still broken. The model didn’t lie — it genuinely assessed its work as complete. But it was wrong. Claude Code v2.1.139 (shipped May 12, 2026) addresses this with the /goal command, a feature that separates the model doing the work from the model judging whether that work is done. This guide explains how it works and how to write goals that actually catch incomplete work. ...

CVE-2026-44338 is an authentication bypass in PraisonAI versions 2.5.6 through 4.6.33 that allows unauthenticated attackers to list your agent configurations and trigger arbitrary agent workflow execution. It was disclosed May 11, 2026 and was being actively exploited within 4 hours. This guide walks through: checking your installed version, patching, verifying the fix, auditing network exposure, and reviewing logs for indicators of compromise. Note: All commands in this guide are standard pip and system tools. For PraisonAI-specific configuration options and advanced deployment settings, always refer to the official PraisonAI documentation — don’t rely solely on this guide for edge-case deployment scenarios. ...

Freshworks announced Freddy AI Agent Studio at Refresh 2026 — a no-code platform for building custom AI agents on top of Freshservice, their IT service management (ITSM) platform. Alongside it: an MCP Gateway that connects Freddy agents to third-party tools including Notion, ClickUp, and Linear. This guide explains what Freddy AI Agent Studio is, what it can do, and how to approach building your first custom IT service desk agent using the platform. ...

TikTok launched its official Model Context Protocol (MCP) server at TikTok World 2026, giving AI agents the ability to plan, launch, optimize, and execute advertising campaigns through TikTok Ads Manager without human intervention. This guide walks through what you need to set up an MCP-compatible AI agent to start managing TikTok campaigns autonomously. ⚠️ Note on command accuracy: The TikTok MCP server was announced in May 2026 and full technical documentation is still rolling out. This guide provides a conceptual workflow based on standard MCP server patterns and confirmed capabilities. For exact API endpoints, authentication parameters, and configuration keys, refer to the official TikTok for Business developer documentation when it becomes available. ...

Most AI agents are reactive. You ask, they answer. You prompt, they respond. But according to Cat Wu — Anthropic’s head of product for Claude Code and Cowork — the next frontier for AI isn’t better responses to requests. It’s agents that anticipate your needs before you know what they are. Wu laid out her vision in a TechCrunch interview published today. This guide takes those principles and maps them to practical design patterns for building proactive agents with OpenClaw. ...

A new vulnerability affecting OpenClaw installations before version 2026.4.20 has been cataloged as CVE-2026-45001. If you’re running an older version of OpenClaw, this guide walks you through how to check your exposure, upgrade, and harden your deployment. Severity: This is a guard bypass vulnerability affecting the agent-facing gateway config.patch and config.apply endpoints. In vulnerable versions, these endpoints fail to properly protect against unauthorized configuration changes by agents or external clients. ...