OpenClaw v2026.5.28: Codex 0.134, Claude Opus 4.8, iOS Pro Refresh, and the $1.3M Question
The latest OpenClaw beta lands Claude Opus 4.8 support, Codex CLI 0.134.0, a full iOS Pro UI refresh, encrypted PDF extraction, and GitHub Copilot agent runtime. Meanwhile OpenClaw's creator publicly racks up $1.3M in AI API bills — and the ecosystem responds.
OpenClaw 2026.5.28: Claude Opus 4.8, Transcripts as Infrastructure, and $1.3M Token Bills
OpenClaw 2026.5.28 lands with Claude Opus 4.8 support, GitHub Copilot agent runtime, encrypted PDF extraction, and transcript capture as core infrastructure. Plus: Peter Steinberger's viral $1.3M OpenAI tab, ClawHub's new trust surfaces, and a deep look at what the beta 2 release train means for operators.
OpenClaw 2026.5.28: Security Boundaries Harden, Codex Gets More Reliable, Pixverse Video Lands, and the Gateway Gets Faster
OpenClaw's May 28 release is a serious security-and-reliability push: group prompt metadata is locked out of system prompts, Tailscale no-auth exposure is blocked, Codex app-server runs stabilize, DeepInfra gets a full model catalog, and Pixverse video generation ships as a first-class provider. Plus the latest on the $1.3M token story, ClawHub plugin metadata improvements, and what agentwashing means for your tool choices.
OpenClaw 2026.5.26-beta.2: Transcripts Go Core, Channels Harden, and the Gateway Gets a Speed Overhaul
OpenClaw's May 26 beta delivers transcript-backed meeting summaries, iMessage tapback approvals, a sweeping Gateway performance pass, named auth profiles, and a new Activity tab — while Red Hat brings the 'Lobster Trap' containerization story to AI Engineer Europe and ClawHub crosses 52.7K tools.
OpenClaw v2026.5.25 Lands iMessage Attachment Fixes, Alpine Linux Support, and MCP Hang Protection
OpenClaw's May 25 releases tackle iMessage attachment routing, deduplicate watcher startup, harden MCP tool materialization, restore Alpine Linux installs, and fix OpenRouter context limits — while the creator's $1.3M token bill keeps echoing through the ecosystem and multi-agent AI goes enterprise-grade.
OpenClaw v2026.5.22 Delivers 4,100× Gateway Speedup, Meeting Notes Plugin, and iMessage Tapback Approvals
OpenClaw v2026.5.22 is a landmark release: /models calls drop from 20 seconds to 5ms, the first external Meeting Notes plugin lands, iMessage thumbs-up now approves exec requests, and hundreds of fixes ship. We cover the security angle, a fresh skill pick, community signals, and what Peter Steinberger's $1.3M OpenAI bill means for the ecosystem.
OpenClaw 2026.5.22: Gateway Performance Overhaul, Meeting Notes Plugin, and the $1.3M AI Token Moment
OpenClaw 2026.5.22 lands a sweeping Gateway performance overhaul, a brand-new Meeting Notes plugin with Discord voice support, and tighter sub-agent context isolation. Meanwhile, Peter Steinberger's $1.3M OpenAI bill in 30 days is making the rounds — and the lesson isn't what you think.
OpenClaw 2026.5.20 Holds the Stable Line While 2026.5.22-beta.1 Cuts Latency, Tightens Delegation, and Keeps the Core Growing Up
OpenClaw 2026.5.20 remains the latest stable release, but today's 2026.5.22-beta.1 matters: smaller npm payloads, faster model listings, tighter subagent bootstrap defaults, and a steady stream of runtime fixes. We cover the operator implications, a practical security tip, a VirusTotal-verified ClawHub pick, community signals, and fresh agent-platform news from Dell, NVIDIA, Microsoft, and Kore.ai.
OpenClaw 2026.5.20 Turns Policy, Voice Context, and Safer Defaults Into the New Baseline
OpenClaw 2026.5.20 promotes policy-backed checks, safer skill loading, voice-session context controls, xAI device-code auth, and stronger secret hygiene into the operational baseline. We cover the real operator implications, a practical security tip, a VirusTotal-verified ClawHub skill, community signals, and fresh ecosystem news from Dell and NVIDIA’s local-agent push.
OpenClaw 2026.5.19 Becomes the Baseline While 2026.5.20-beta.1 Pushes Voice Context, Policy Checks, and Cron Repair Further
OpenClaw 2026.5.19 is now the operational baseline, while 2026.5.20-beta.1 extends voice context, policy-backed checks, xAI device-code auth, and cron recovery. We cover the real operator implications, a practical security tip, a VirusTotal-verified ClawHub skill, community signals, and fresh agent-framework ecosystem news.
OpenClaw 2026.5.18 Locks the Stable Branch While 2026.5.19 Pre-Releases Push Skills, QA, and Operator Hygiene Forward
OpenClaw 2026.5.18 is now the latest stable release, rolling up a volatile May branch into something operators can actually standardize on. We cover the new 2026.5.19 pre-releases, a practical shared-skill security tip, a VirusTotal-verified ClawHub pick, community signals, and why the broader agent framework race is shifting toward runtime discipline.
OpenClaw 2026.5.19-beta.1 Tightens Operator Authority, Modernizes Image Builds, and Makes the Plugin SDK a First-Class Citizen
OpenClaw's May 19 pre-release sharpens admin RPC controls, formalizes a typed plugin SDK with defineToolPlugin, ships realtime Android Talk Mode, redesigned Mac settings, and a long list of QA-Lab parity gates. We pair it with a supply-chain security tip, a VirusTotal-conscious ClawHub skill, community signals, and ecosystem news from Microsoft Agent Framework 1.0 and NVIDIA NemoClaw.
OpenClaw’s May 18 Pre-Release Shrinks the Core Again, Adds Safer Browser Dialog Control, and Turns Plugin Authoring Into a First-Class Workflow
OpenClaw’s May 18 pre-release focuses on safer browser dialog handling, cleaner plugin tooling, faster gateway startup paths, and a more polished Mac settings experience. We pair it with a supply-chain security tip, a VirusTotal-checked ClawHub skill, community signals, and the broader agent-framework race.
OpenClaw’s May 17 Pre-Release Hardens Security Audit Workflow, Adds Grok OAuth, and Doubles Down on Subagent Discipline
OpenClaw’s May 17 pre-release introduces audit-suppression hygiene, xAI Grok OAuth for SuperGrok users, parent-review subagent handoffs, and waitable cron runs. We pair it with a prompt-injection security tip, a carefully-scanned ClawHub skill, and ecosystem signals as the project keeps shrinking core complexity after April’s rough release week.
OpenClaw 2026.5.16 Bets on Faster Cron Control, Grok OAuth, and a Smaller Safer Core
OpenClaw’s May 16 beta train adds xAI Grok OAuth, waitable cron runs, warmer skill caching, and more restart resilience as the project keeps shrinking core complexity after a rough week. We cover the real operator implications, a practical security tip, ClawHub’s trust model, community signals, and why enterprise agent infrastructure keeps converging on governed orchestration.
Page 2 of 9