[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-247k-github-stars-openclaw-local-ai-assistant-en":3,"article-related-247k-github-stars-openclaw-local-ai-assistant-en":31,"series-tools-3622b611-53b4-47a6-bc79-ea9c33988e6c":77},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":23,"views":27,"created_at":28,"published_at":29,"topic_cluster_id":30},"3622b611-53b4-47a6-bc79-ea9c33988e6c","247k-github-stars-openclaw-local-ai-assistant-en","247k GitHub Stars: OpenClaw Local AI Assistant","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002Fopenclaw\">OpenClaw\u003C\u002Fa> is a local-first AI assistant that runs on your machine and replies through \u003Ca href=\"\u002Fnews\u002Fopenclaw-persistent-ai-assistant-chat-apps-en\">chat apps\u003C\u002Fa>.\u003C\u002Fp>\u003Cp>OpenClaw, the open-source personal AI assistant from \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpsteinberger\u002Fopenclaw\" target=\"_blank\" rel=\"noopener\">OpenClaw\u003C\u002Fa> creator Peter Steinberger, reached 247,000 \u003Ca href=\"\u002Ftag\u002Fgithub\">GitHub\u003C\u002Fa> stars and 47,700 forks by March 2026 after launching as a side project in November 2025. The project now runs as a local gateway for chat-based assistants, with messages arriving through \u003Ca href=\"https:\u002F\u002Ftelegram.org\" target=\"_blank\" rel=\"noopener\">Telegram\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fsignal.org\" target=\"_blank\" rel=\"noopener\">Signal\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fwww.whatsapp.com\" target=\"_blank\" rel=\"noopener\">WhatsApp\u003C\u002Fa>, and other channels while the model and tools stay under the user’s control.\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>項目\u003C\u002Fth>\u003Cth>數值\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>GitHub stars\u003C\u002Ftd>\u003Ctd>247,000\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>GitHub forks\u003C\u002Ftd>\u003Ctd>47,700\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Launch month\u003C\u002Ftd>\u003Ctd>November 2025\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Guide date\u003C\u002Ftd>\u003Ctd>June 24, 2026\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>ClawHub skills\u003C\u002Ftd>\u003Ctd>2,857+\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Security incident\u003C\u002Ftd>\u003Ctd>341 malicious skills\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>What changed\u003C\u002Fh2>\u003Cp>OpenClaw packages three parts into one workflow: a local gateway, messaging channels, and installable skills called claws. The gateway runs as a Node.js process on the user’s machine, routes each message to the right session, manages memory, and sends responses back through the same chat app.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782560865314-wwov.png\" alt=\"247k GitHub Stars: OpenClaw Local AI Assistant\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>The assistant is model-agnostic. Users can connect \u003Ca href=\"\u002Ftag\u002Fclaude\">Claude\u003C\u002Fa>, GPT-5.5, DeepSeek, Gemini, Ollama, or any \u003Ca href=\"\u002Ftag\u002Fopenai\">OpenAI\u003C\u002Fa>-compatible endpoint, then switch models per agent or workspace. OpenClaw handles routing and tool execution; the chosen model handles \u003Ca href=\"\u002Ftag\u002Finference\">inference\u003C\u002Fa>.\u003C\u002Fp>\u003Cul>\u003Cli>Channels include Telegram, Signal, WhatsApp, Discord, Slack, iMessage, and 20+ others.\u003C\u002Fli>\u003Cli>Claws are markdown-based skill packs with YAML frontmatter and instructions.\u003C\u002Fli>\u003Cli>Core tools include read, write, exec, web_search, web_fetch, browser, and memory.\u003C\u002Fli>\u003Cli>ClawHub is the official skill registry, with install and search commands built into the CLI.\u003C\u002Fli>\u003C\u002Ful>\u003Cp>Setup is short on paper: install the CLI, run onboarding, choose a model provider, connect a channel, and add claws as needed. The guide says Telegram is the fastest first setup, while Signal and WhatsApp require extra transport configuration.\u003C\u002Fp>\u003Ch2>Why it matters\u003C\u002Fh2>\u003Cp>OpenClaw solves two pain points that keep showing up in AI tooling: users do not want another app, and they do not want their chat history copied to a vendor server. By keeping the assistant local and letting people talk to it inside the messaging apps they already use, OpenClaw lowers the friction for daily use.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782560861981-iosk.png\" alt=\"247k GitHub Stars: OpenClaw Local AI Assistant\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>For developers, the bigger draw is control. Skills can be scoped to a workspace or installed globally, each skill declares its tool access up front, and the local memory layer stores facts in SQLite instead of a hosted database. That makes OpenClaw easier to audit than many hosted agent stacks, especially for workflows that touch files, shells, or APIs.\u003C\u002Fp>\u003Cp>The security angle is now part of the product story too. After researchers flagged ClawHavoc, ClawHub removed suspicious skills and added VirusTotal scanning. Anyone installing community claws still has to check publisher identity and tool permissions before turning on write access.\u003C\u002Fp>\u003Cp>OpenClaw’s rise is a signal that local-first agents are moving from niche hobby to serious developer tooling; the open question is how much trust users will place in third-party skills as the ecosystem grows.\u003C\u002Fp>","OpenClaw hit 247,000 GitHub stars as a local-first AI assistant that runs on your machine and replies in chat apps you already use.","www.explainx.ai","https:\u002F\u002Fwww.explainx.ai\u002Fblog\u002Fwhat-is-openclaw-personal-ai-assistant-guide-2026",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782560865314-wwov.png","tools","en","04331bf8-5731-406b-9242-778d5ce5d1e9",[17,18,19,20,21,22],"OpenClaw","local AI assistant","open source","chat apps","skills","developer tools",[24,25,26],"OpenClaw hit 247k GitHub stars after launching in late 2025.","It runs locally, but replies through Telegram, Signal, WhatsApp, and other chat apps.","Skills, called claws, extend the assistant with auditable tool access.",0,"2026-06-27T11:47:17.186498+00:00","2026-06-27T11:47:17.174+00:00","3d5be689-f455-4a79-b777-ce657fb1525f",{"tags":32,"relatedLang":36,"relatedPosts":40},[33,35],{"name":17,"slug":34},"openclaw",{"name":21,"slug":21},{"id":15,"slug":37,"title":38,"language":39},"247k-github-stars-openclaw-local-ai-assistant-zh","24.7 萬星：OpenClaw 本地 AI 助手","zh",[41,47,53,59,65,71],{"id":42,"slug":43,"title":44,"cover_image":45,"image_url":45,"created_at":46,"category":13},"0a5f2eb9-7c4b-4382-b0e0-501f1bc3e70f","midjourney-review-2026-v8-worth-it-en","Midjourney Review 2026: Is V8 Still Worth It?","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782576174182-vc3v.png","2026-06-27T16:02:30.622473+00:00",{"id":48,"slug":49,"title":50,"cover_image":51,"image_url":51,"created_at":52,"category":13},"3a9390c3-0160-4d2a-bb42-25f6437aecb4","midjourney-v81-faster-renders-pricing-video-en","Midjourney V8.1 lands with 4-5x faster renders","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782573467328-ybtn.png","2026-06-27T15:17:23.634784+00:00",{"id":54,"slug":55,"title":56,"cover_image":57,"image_url":57,"created_at":58,"category":13},"9e1a94d8-5e53-4bca-b32d-83c73cef1639","mlops-roadmap-2026-turns-learning-into-delivery-en","MLOps Roadmap 2026 Turns Learning Into Delivery","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782567216077-5x25.png","2026-06-27T13:33:07.454419+00:00",{"id":60,"slug":61,"title":62,"cover_image":63,"image_url":63,"created_at":64,"category":13},"37e775a7-6538-4f24-aca4-38823422a8ec","best-prompt-evaluation-tools-2026-compared-en","Best Prompt Evaluation Tools in 2026, Compared","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782549172915-z0gb.png","2026-06-27T08:32:27.03361+00:00",{"id":66,"slug":67,"title":68,"cover_image":69,"image_url":69,"created_at":70,"category":13},"12b5a886-cace-428d-9df4-5e9b4b2eae64","devzero-kubernetes-optimization-tool-2026-en","DevZero is the Kubernetes optimization tool that matters in 2026","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782541063086-l0cx.png","2026-06-27T06:17:20.966532+00:00",{"id":72,"slug":73,"title":74,"cover_image":75,"image_url":75,"created_at":76,"category":13},"79194d55-f22c-465f-90b8-8050b2c278fb","gentoo-kernel-config-menuconfig-workflow-en","Gentoo kernel config turns menuconfig into a workflow","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782523097255-cir6.png","2026-06-27T01:17:52.032704+00:00",[78,83,88,93,98,103,108,113,118,123],{"id":79,"slug":80,"title":81,"created_at":82},"8008f1a9-7a00-4bad-88c9-3eedc9c6b4b1","surepath-ai-mcp-policy-controls-en","SurePath AI's New MCP Policy Controls Enhance AI Security","2026-03-26T01:26:52.222015+00:00",{"id":84,"slug":85,"title":86,"created_at":87},"27e39a8f-b65d-4f7b-a875-859e2b210156","mcp-standard-ai-tools-2026-en","MCP Standard in 2026: Integrating AI Tools","2026-03-26T01:27:43.127519+00:00",{"id":89,"slug":90,"title":91,"created_at":92},"165f9a19-c92d-46ba-b3f0-7125f662921d","rag-2026-transforming-enterprise-ai-en","How RAG in 2026 is Transforming Enterprise AI","2026-03-26T01:28:11.485236+00:00",{"id":94,"slug":95,"title":96,"created_at":97},"6a2a8e6e-b956-49d8-be12-cc47bdc132b2","mastering-ai-prompts-2026-guide-en","Mastering AI Prompts: A 2026 Guide for Developers","2026-03-26T01:29:07.835148+00:00",{"id":99,"slug":100,"title":101,"created_at":102},"3ab2c67e-4664-4c67-a013-687a2f605814","garry-tan-open-sources-claude-code-toolkit-en","Garry Tan Open-Sources a Claude Code Toolkit","2026-03-26T08:26:20.245934+00:00",{"id":104,"slug":105,"title":106,"created_at":107},"66a7cbf8-7e76-41d4-9bbf-eaca9761bf69","github-ai-projects-to-watch-in-2026-en","20 GitHub AI Projects to Watch in 2026","2026-03-26T08:28:09.752027+00:00",{"id":109,"slug":110,"title":111,"created_at":112},"9f332fda-eace-448a-a292-2283951eee71","practical-github-guide-learning-ml-2026-en","A Practical GitHub Guide to Learning ML in 2026","2026-03-27T01:16:50.125678+00:00",{"id":114,"slug":115,"title":116,"created_at":117},"1b1f637d-0f4d-42bd-974b-07b53829144d","aiml-2026-student-ai-ml-lab-repo-review-en","AIML-2026 Is a Bare-Bones Student Lab Repo","2026-03-27T01:21:51.661231+00:00",{"id":119,"slug":120,"title":121,"created_at":122},"6d1bf3f6-e191-4d30-b55b-8a0722fa6afe","ai-trending-github-repos-and-research-feeds-en","AI Trending Tracks Repos and Research Feeds","2026-03-27T01:31:35.709532+00:00",{"id":124,"slug":125,"title":126,"created_at":127},"010539a1-4c3a-4bd3-937a-26616422ee0d","awesome-ai-for-science-research-tools-map-en","Awesome AI for Science Is Becoming a Real Research Map","2026-03-27T01:46:50.89513+00:00"]