Skip to content
All tool news

Tool desk · Updated daily

Tool news·OpenClaw·

OpenClaw Adds Extended-Stable Releases and Maturity Scorecard for Critical Workloads.

OpenClaw adds Extended-Stable Releases and a public Maturity Scorecard, giving teams clearer stability signals for critical workloads.

CW

Create With tool desk

1 source checked · 3 min read · 3 sections

ShareLinkedIn
OpenClaw Adds Extended-Stable Releases and Maturity Scorecard for Critical Workloads

OpenClaw is putting more structure around how businesses deploy its local AI agents. The company has introduced a long-lived software channel with backported fixes, alongside a public system for judging whether individual features are mature enough for critical workflows.

The announcement, published July 30, positions Extended-Stable Releases and Maturity Scorecard as steps toward eventual long-term support, or LTS. OpenClaw says its software has evolved from a side project into infrastructure used by individuals and Fortune 500 companies, raising the cost of unstable upgrades and unclear feature readiness.

OpenClaw's road toward long-term support releases
OpenClaw's road toward long-term support releases

A More Predictable Release Channel

Extended-stable releases will arrive monthly. Each release line starts with the version format YYYY.M.33, while subsequent security and reliability backports increase the patch number by one. A line remains supported until the following extended-stable release is issued, with a minimum support period of one month.

The first version is OpenClaw 2026.6.33. It is based on version 2026.6.11 and incorporates security and reliability fixes taken from later releases. That approach lets organizations stay on a known base while receiving selected fixes, rather than adopting every new feature and behavior immediately.

Users can install the selected extended-stable version with:

npm install -g openclaw@extended-stable

That command installs the release but does not retain extended-stable as the update channel. To make the channel persistent for a new or existing package installation, OpenClaw provides a second command:

openclaw update --channel extended-stable

The distinction matters for small businesses running agents continuously. A one-time installation may leave later updates following a different channel, while persisting the setting keeps the deployment aligned with the extended-stable track.

This release model builds on recent work around agent reliability and security. OpenClaw previously shipped version 2026.6.6 with tighter security and faster agent responses, as well as version 2026.6.5 with parallel web search and new security controls.

A Public View of Feature Maturity

The accompanying Maturity Scorecard provides an inventory of OpenClaw features and shows where each sits within the project’s maturity model. Features are grouped by broad product surface and then by category, making it possible to assess separate capabilities rather than treating the entire platform as equally production-ready.

OpenClaw currently calculates maturity using a combination of quality and completeness. Inputs include:

  • Outstanding GitHub issues
  • Comparisons with similar services
  • Maintainer judgment

Features classified as mature receive additional operational commitments. Issues filed against them will get a dedicated label and priority from maintainers, while the features themselves will have end-to-end tests that exercise them in production.

For builders, the scorecard could be as important as the new release channel. Extended-stable identifies which software build favors continuity, while the scorecard helps teams decide which capabilities to entrust with customer communication, internal automation, or other consequential work. Together, they provide two different signals: release-level stability and feature-level maturity.

OpenClaw is careful to describe extended-stable as a move toward official LTS, not LTS itself. The monthly support window remains relatively short compared with traditional enterprise support cycles, but it gives the project a controlled way to harden its release and backporting processes before making a longer-term commitment.

Frequently asked questions

What is OpenClaw Extended-Stable Releases and Maturity Scorecard?

It combines a monthly, longer-lived OpenClaw release channel with a public inventory that rates the maturity of individual features. The release channel receives backported security and reliability fixes, while the scorecard helps users evaluate feature quality and completeness.

How can users install an OpenClaw extended-stable release?

Users can run npm install -g openclaw@extended-stable to install the selected release. To retain extended-stable as the update channel, they must also run openclaw update --channel extended-stable.

Is extended-stable the same as an official OpenClaw LTS release?

No. OpenClaw describes extended-stable as a step toward official LTS releases. A monthly extended-stable line is supported until the next one is issued, for at least one month.

Sources

1 checked

How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.

Worth passing on?

ShareLinkedIn

Go deeper on OpenClaw

Related reading, watching and going.

Everything on OpenClaw →

The briefing

1 Sept 2026

GrokBot Tested: Two Conflicting Takes from Create With

Two Create With writers test GrokBot - an app giving each AI bot a cloud PC and letting bots message each other. We share opposing takes and pricing notes.

Read →

The briefing

28 Jul 2026

AI Loops Explained: Practical Guide Without the Hype

Understand AI 'loops'—how goal-driven agents replace manual prompts, when they help, and their real costs. A clear, no-hype primer for builders and teams.

Read →

The briefing

7 Jul 2026

Create With 2026: One Hot Day in Brighton — AI Agents

Recap of Create With 2026 in Brighton: 500+ creators, live AI-agent demos, Claude Cowork workshop, 50+ apps shipped, a 45-project hackathon and community magic.

Read →
36 min

Podcast

55. We're Back! Conference Recap, Running Events with AI & Self-Healing Apps

James and Kieran return to the Create With Podcast after their summer break to recap the 2026 Create With Conference in Brighton. They discuss how 550 attendees experienced workshops, a charity hackathon where functional apps were built in 30 minutes, and an innovative conference operating system built entirely with AI. The episode covers the latest developments in AI development tools including Anthropic's Fable model, scheduled tasks in Codex, and self-healing applications using PostHog.

Watch now ↗
56 min

Tutorial

OpenClaw + custom dashboard + subagents = mindblowing!

Benoit Devilliers demonstrates Visionary, a custom dashboard he built on top of OpenClaw that uses an orchestrator/sub-agent architecture. The system manages client projects, spawns specialized coding agents, and sends push notifications. In a live demo, he shapes a ticket, spawns an agent, and merges a PR in real-time. Benoit started AI coding in July 2024 and built this entire system himself, showcasing how accessible these tools have become.

Watch now ↗

Podcast

53. Why Your Vibe Code Needs Tests, Ditching SaaS & AI Agents That Work While You Sleep

James and Kieran discuss the practical realities of building AI-powered software, emphasizing the importance of testing in vibe-coded applications, exploring alternatives to traditional SaaS tools, and implementing autonomous AI agents for business operations. The episode covers technical topics like Convex databases, app store bottlenecks from AI-generated submissions, and using OpenClaw as a marketing automation agent.

Watch now ↗

Latest tool news

What else changed this week.

All tool news

The Create With Briefing

Don't watch forty changelogs. Read one email.

Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.