Tag
OpenClaw
OpenClaw is a local-first multi-agent workflow framework for splitting research, writing, ops, and automation into coordinated agents. Its relevance lies in memory retrieval, tool integration, approval hooks, and the security tradeoffs of running local or cloud-connected models.
30 articles
Why AI-agent CLIs are the new supply-chain attack surface
AI-agent CLIs create a new supply-chain backdoor class that scanners do not catch.
Meta and Google join the AI agent race
OpenClaw’s viral rise pushed Meta and Google to build AI agents as Big Tech races to turn chatbots into task-doers.
OpenClaw vs Hermes: 五层架构对比
对比 OpenClaw 和 Hermes，帮助你判断该选轻量可控的代理框架还是自进化架构。
How to Run OpenClaw with Open-Source Models
Set up OpenClaw with open-source LLMs like Kimi-K2.5 through OpenRouter.
Red Hat’s Tank OS makes OpenClaw safer in enterprise
Red Hat engineer Sally O’Malley’s Tank OS wraps OpenClaw in rootless Podman containers, aiming to make enterprise agent fleets easier to control.
Build a Secure Local AI Agent with OpenClaw
NVIDIA’s NemoClaw pairs OpenClaw with OpenShell to run a Telegram-connected local AI agent on DGX Spark, with model weights kept on-device.
OpenClaw Memory: how its retrieval system works
OpenClaw’s memory system uses file watching, async debounced index updates, and optional API-backed search across local and cloud models.
Openclaw April 2026 Update Adds xAI, MiniMax
Openclaw’s April 2026 release adds xAI and MiniMax support, new approval hooks, safer exec defaults, and cleaner onboarding.
OpenClaw: How to build your own AI agent
OpenClaw is an open-source AI agent you can run locally, message from Telegram, and train to handle email, calendars, code, and more.
OpenClaw Is Testing China’s AI Ambitions
OpenClaw is spreading fast in China, but data leaks, deleted files, and plugin risks are forcing regulators to react.
OpenClaw’s 60-Day Surge Changes AI Agents
OpenClaw hit React-level GitHub stars in 60 days, showing how fast open-source agents are moving from chat to actual work.
OpenClaw v2026.3.24: Reset Guide and Integrations
OpenClaw v2026.3.24 is still beta, but its reset flow, Ark Coding Plan support, and Feishu channels hint at a practical agent setup.
OpenClaw’s 1,299 Repos: What the Data Shows
OpenClaw hit 1,299 repos in eight weeks. The repo mix shows fast adoption, Chinese tooling, and a clear build order.
OpenClaw Bug Lets Websites Hijack AI Agents
Oasis found a flaw in OpenClaw that lets any website take over a local agent. Update to version 2026.2.25 or later now.
OpenClaw Update Guide: Safe Upgrades in 2026
OpenClaw updates can break tools, plugins, and config. Here’s the safest upgrade flow, with backup, rollback, and version checks.
Openclaw Flaw Exposes AI Admin Hijack Risk
Certik says Openclaw’s flaws expose 135,000+ instances, token theft, and admin takeover risk, with CVE-2026-25253 leading the list.
OpenClaw and the New Solo Builder Stack
One builder runs 8 orchestrators and 35 personas on a homelab, using OpenClaw to ship writing, research, and ops in parallel.
OpenClaw 3.24 Fixes “needs setup” Skills Install
OpenClaw 3.24 rewrites the Skills install flow with guided setup, a cleaner console, and fixes a file-access security hole. The update also improves Teams support.
OpenClaw安全风险与防护清单
OpenClaw已曝出1184个恶意技能包，23万+实例暴露公网。本文拆解风险、漏洞与防护清单。
OpenClaw 多智能体上云，运维更轻了
OpenClaw 现在可跑在 DigitalOcean App Platform，上云后支持多智能体、私有网络和更可预测的成本。
OpenClaw: the AI worker with privacy costs
OpenClaw hit 300K GitHub stars fast, but its always-on agent model raises hard questions about privacy, consent, and security.
OpenClaw走红：13家大厂为何都在跟进
OpenClaw把AI从“会说话”推到“会操作”，腾讯、字节、华为云等13家厂商跟进，争的是办公与设备控制入口。
OpenClaw 3.28 brings approval gates
OpenClaw 3.28 adds Grok search, MiniMax image tools, and approval popups after a 4-day sprint with 100+ fixes.
OpenClaw命令指南：从Web UI切到终端
OpenClaw用户多停在Web UI。本文整理常用命令、性能差异和终端工作流，帮你更快上手。
OpenClaw and the AI agent boom, explained
OpenClaw turned local AI agents into a fast-moving trend, but its access to files, email, and chats brings real security tradeoffs.
OpenClaw Agents Can Be Manipulated Into Failure
Northeastern researchers found OpenClaw agents can be guilted, looped, and tricked into breaking their own tools inside a sandbox.
20 GitHub AI Projects to Watch in 2026
OpenClaw may top GitHub, but 2026’s AI list shows a bigger shift toward agents, workflow systems, RAG, and multimodal tools.
OpenClaw's Rise Raises Concerns of AI Model Commoditization
OpenClaw's rapid success highlights a potential shift in AI models, sparking discussions on their commoditization within the tech industry.
Anthropic's Claude AI Agent: A New Era of Task Automation
Anthropic's Claude AI can now autonomously complete tasks on personal computers, marking a significant step in AI agent capabilities.
NVIDIA GTC 2026: Key Highlights and Innovations
Explore the latest AI advancements from NVIDIA's GTC 2026, including new platforms, partnerships, and innovative AI applications.