Blog - OpenClaw

OpenClaw improves user onboarding with a new installer on macOS, plus easier local model setup for Windows NVIDIA RTX PCs

A new installer and onboarding flow on macOS, plus streamlined local model setup on Windows NVIDIA RTX PCs, get you from download to a working agent faster.

Read more

OpenClaw 2.0, Accidentally

How a push for simpler setup and a first-class browser experience grew into OpenClaw 2.0.

Read more

On the Road to LTS: Extended-Stable Releases and the Maturity Scorecard

A new long-lived release channel and a public maturity scorecard make it easier to choose OpenClaw features for critical workloads.

Read more

Introducing the OpenClaw Foundation

The lobster grows up: OpenClaw is now a non-profit, with a full-time team, world-class partners, and a mission to bring personal AI to everyone.

Read more

Skill Workshop: Turn Agent Work Into Reusable Skills

Review, revise, and apply proposed skills before they change how OpenClaw agents work.

Read more

OpenClaw Collaborates with NVIDIA for Stronger Agent Skill Security

Every ClawHub skill now ships with a Skill Card showing what it does and where it came from, and SkillSpector scans it for hidden instructions and agentic risks.

Read more

Safer Than YOLO: Auto Mode for Exec Approvals

OpenClaw is adding opt-in auto mode for Enterprise-ready host exec guardrails: policy runs first, low-risk misses get reviewed, and humans stay in the loop.

Read more

OpenClaw Is Getting Faster, Smaller, and Easier to Trust

A release sweep across February through May shows faster agent turns, fewer dependencies, and a cleaner package shape.

Read more

Where OpenClaw Security Is Heading

The security roadmap for making OpenClaw a powerful personal assistant runtime users can understand, observe, and trust.

Read more

OpenAI Models in OpenClaw, Done Right

OpenClaw now runs OpenAI agent turns through the native Codex app-server harness by default, while bringing the lessons back to every model.

Read more

OpenClaw Had a Rough Week

What happened around the 2026.4.24 and 2026.4.29 releases, why the direction was right, and what we are changing now.

Read more

How OpenClaw Got Safer in Public

The work you do not see behind the world's most-watched open source personal AI agent.

Read more

OpenClaw Partners with VirusTotal for Skill Security

ClawHub skills are now scanned by VirusTotal's threat intelligence platform—bringing industry-leading security to the AI agent ecosystem.

Read more

Introducing OpenClaw

The journey from Clawd to Moltbot to OpenClaw—and why this name is here to stay.

Read more