OpenClaw Releases 2026.9.5 With Atomic Updates, Plugin Hot Reload, Conversation Sharing, and Expanded GPT Live
OpenClaw is an open-source, MIT-licensed personal AI agent that you run on your own machines.Its Gateway connects models, tools, and chat channels such as Telegram, Slack, and Discord.The project has now shipped version 2026.9.5, announced on X.
The release bundles 4,179 pull requests and 64 direct commits, with credits to 502 contributing accounts.The main change is Atomic Updates, which targets a long-running complaint: updates that break a working agent.Is it deployable?Yes, Version 2026.9.5 is the current latest tag on npm.
It is self-hostable and needs Node 24.16+ or 26.1+.Why OpenClaw Updates Kept Breaking The OpenClaw team explained the problem in a blog post with maintainer Jason Sy.Before the fix, an update had 2 outcomes: incremental improvement or catastrophic failure.
In the failure case, the old version went down as well.That left no agent online to help with the repair.Two factors made this hard.First, OpenClaw has thousands of config options, so testing every permutation is near impossible.Second, maintainers rarely felt the pain themselves.
They are developers who ask Claude or Codex to update their claw.For many users, the claw is their only agent.The OpenClaw 2.0 launch in early September made the issue too large to ignore.How Atomic Updates Work According to the Claw team, the needed pieces already existed in the upgrade process.
They were in the wrong order.The new flow works like this: The existing Gateway keeps running while the update is prepared.The next version is checked against a private copy of your setup.OpenClaw switches over, then verifies the updated installation.
If the update fails, it rolls back to the last working configuration.OpenClaw always preserves a working agent, so it can help diagnose a failed upgrade.The team also added an issue reporting button for updates.The release notes list clear limits.Atomic Updates apply on supported update paths only.
Rolling back the application cannot undo database migrations.The private validation copy is not a backup, so keep a verified backup before upgrading.If an interactive update fails, AI repair starts only after you choose Yes.It uses your account and tokens, and a 30-second timeout skips it.
Interactive Explainer: OpenClaw 2026.9.5 (function(){var f=document.getElementById('mtp-oc95');window.addEventListener('message',function(e){if(e.source===f.contentWindow&&e.data&&e.data.mtpOc95){f.style.height=e.data.mtpOc95+'px';}});})(); What Else Ships in 2026.9.
5 Plugin hot reload: you can install or reload supported plugins without restarting the Gateway.It works from the CLI or an authorized chat command.The CLI also accepts several plugins in 1 command.
Conversation sharing: Session Share gives teammates on another paired installation read-only access to selected conversation groups.Recipients see conversation text and eligible forks.They do not see subagents, tool activity, or reasoning.Revocation cannot recall what was already received.
Expanded GPT Live: you can speak while GPT Live replies in supported Meet, Teams, and Zoom meetings.It can consult your OpenClaw agent during meetings or phone calls.Live is audio-only, so the notes point to gpt-realtime-2.1 for camera use.
Shared browser pages: a shared Browser dashboard lets you and your agent use the same page.It runs on a local OpenClaw-managed browser profile, not your laptop cookies.Conversation archiving: cold storage compresses older, inactive history.
It is off by default and archives after 30 days once enabled.Reopening a conversation restores it and makes it searchable again.Specialist-agent setup: guided setup can create a chief of staff, researcher, writer, and reviewer.You can also pick a single specialist.
Nothing is created before you approve the proposal.One upgrade warning applies to everyone.This release changes the conversation database even with archiving off.Going back requires the matching older build and a backup.
How To Install or Upgrade New installs can use the official script: Copy CodeCopiedUse a different Browsercurl -fsSL https://openclaw.ai/install.sh | bash If you already manage Node.
js, install the published package: Copy CodeCopiedUse a different Browsernpm install -g openclaw@latest --allow-scripts=openclaw openclaw onboard --install-daemon Existing users can run openclaw update.See the updating guide for manual paths.
The release also adds a FreeBSD CLI install route using system Node and npm.Key Takeaways OpenClaw 2026.9.5 ships 4,179 pull requests from 502 contributing accounts.Atomic Updates validate the next version while the current Gateway keeps running.
Failed updates roll back, and a working agent stays available to diagnose.Plugins now install or reload without a Gateway restart.Back up first: rollback cannot undo database migrations.The post OpenClaw Releases 2026.9.
5 With Atomic Updates, Plugin Hot Reload, Conversation Sharing, and Expanded GPT Live appeared first on MarkTechPost.
Related
相關文章
消息稱字節跳動大面積限制員工自費使用第三方AI工具
此次封禁的核心原因為防範數據洩露與資產安全風險,技術副總裁洪定坤在內網迴應時指出,L3及以上級別的核心內容一旦洩露後果極其嚴重,但同時也強調不應通過封禁其他選擇來強迫推廣內部產品。作為核心技術骨幹與管理者的分水嶺,L4級代碼庫沉澱了字節跳動全線業務的核心資產與底層架構,這也讓此次風控升級備受內部關注。
Anthropic產品團隊出現人事變動,Claude Code負責人離開
她近日在社交平臺X發文稱,週五是自己在Anthropic工作的最後一天,但未透露離職原因及下一步去向。Cat Wu曾負責Claude Code和Cowork兩款產品。加入Anthropic之前,她先後在Scale AI和Dagster擔任工程師,之後轉入風險投資機構Index Ventures工作。
國內首個三晉文化大模型“晉問AI”正式上線,數字人“晉豆”同步亮相
該項目由山西省委宣傳部指導、山西出版傳媒集團承建、山西春秋電子音像出版社具體實施,目前已被正式納入《山西省國民經濟和社會發展第十五個五年規劃綱要》。根植權威出版:構建“LLM+RAG+Agent”的技術護城河作為山西深厚歷史文化的數字化載體,“晉問AI”在技術架構上採用了先進的 LLM+RAG+Agent 方案。
搜索版圖被撕開一道口子:ChatGPT 搶下谷歌兩成流量
皮尤研究中心今年夏天的調查顯示,獲取信息已是美國成年人最普遍的 AI 用法——42% 的受訪者承認用 AI 搜過東西,在職人群裡更有 38% 拿它處理工作任務,娛樂、看新聞、問醫療建議則佔比小得多。而在所有聊天機器人中,ChatGPT 是那個"國民級"入口:44% 的美國成年人用過它,第二名 Gemini 僅 24%。
蘋果 AI 加速進入中國市場,Siri、視覺智能整合千問
蘋果中文官網公佈的功能包括寫作工具、實時翻譯、照片消除、智繪表情及通知摘要,標誌著蘋果 AI 功能開始向國行用戶開放。此次更新的一項重要變化是接入阿里千問。千問已整合至 Siri、視覺智能和寫作工具,用戶可以直接在系統內進行問答、文本生成及圖像處理。
2027 年起K- 12 學生賬戶AI與搜索服務將默認關閉,禁用AI將連帶失去傳統搜索
新規實施後,學校管理的 K-12學生賬戶中,Gemini、NotebookLM、Gemini in Classroom 以及 Google Search 等相關服務將全部調整為默認關閉狀態,只有在學校管理員主動授權後才能正常使用。賦予學校管理自主權,但“一刀切”綁定引發新討論谷歌表示,此次調整是在與學校、教師、研究人員及政策制定者進行充分溝通後決定的,核心目的在於讓學校能夠根據自身需求,自行決定人工智能工具在課堂教學中的具體使用方式。