[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-kimi-k26-live-300-agent-workflows-en":3,"article-related-kimi-k26-live-300-agent-workflows-en":30,"series-ai-agent-5b873eea-a5c8-4e78-9509-e2d904934303":83},{"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":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":29},"5b873eea-a5c8-4e78-9509-e2d904934303","kimi-k26-live-300-agent-workflows-en","Kimi K2.6 goes live with 300-agent workflows","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002Fmoonshot-ai\">Moonshot AI\u003C\u002Fa>’s Kimi app now adds 300-\u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> workflows, one-prompt site building, and multi-claw group chat.\u003C\u002Fp>\u003Cp>\u003Ca href=\"https:\u002F\u002Fapps.apple.com\u002Fus\u002Fapp\u002Fkimi-kimi-k2-6-is-live\u002Fid6474233312\" target=\"_blank\" rel=\"noopener\">Kimi\u003C\u002Fa> has pushed its K2.6 update live on the App Store, pitching the iPhone, iPad, Mac, Vision, and Watch app as a productivity tool for research, coding, slides, and office work. The listing says the app is free with in-app purchases, carries a 4.8 rating from 4.5K reviews, and is built by \u003Ca href=\"https:\u002F\u002Fmoonshot.ai\" target=\"_blank\" rel=\"noopener\">Moonshot AI\u003C\u002Fa>.\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>項目\u003C\u002Fth>\u003Cth>數值\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>App version\u003C\u002Ftd>\u003Ctd>K2.6\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Rating\u003C\u002Ftd>\u003Ctd>4.8\u002F5\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Reviews\u003C\u002Ftd>\u003Ctd>4.5K\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>File size\u003C\u002Ftd>\u003Ctd>135.6 MB\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Age rating\u003C\u002Ftd>\u003Ctd>4+\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Agent swarm size\u003C\u002Ftd>\u003Ctd>Up to 300 sub-agents\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Workflow steps\u003C\u002Ftd>\u003Ctd>Up to 4,000 steps\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>File batch limit\u003C\u002Ftd>\u003Ctd>Up to 50 files\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>What changed\u003C\u002Fh2>\u003Cp>K2.6 centers on agentic work rather than chat alone. The update adds Multi-Claw Group Chat, where users can pull multiple agents into a shared thread and invite human collaborators, plus a new “Claw Group” pitch for parallel work on complex tasks.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780430570173-x78p.png\" alt=\"Kimi K2.6 goes live with 300-agent workflows\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>The biggest upgrade is Kimi’s “\u003Ca href=\"\u002Ftag\u002Fvibe-coding\">vibe coding\u003C\u002Fa>” and visual coding flow. According to the App Store text, a single prompt can generate a production-ready website with databases, auth, admin panels, and animated visuals, while uploaded designs, mockups, sketches, or screen recordings can be turned into a matching site.\u003C\u002Fp>\u003Cul>\u003Cli>Agent Swarm can deploy up to 300 sub-agents.\u003C\u002Fli>\u003Cli>The app claims support for 4,000 execution steps.\u003C\u002Fli>\u003Cli>Users can analyze up to 50 files at once.\u003C\u002Fli>\u003Cli>Web search spans 100+ websites, per the listing.\u003C\u002Fli>\u003Cli>Visual Agentic Slides turns references into editable presentations.\u003C\u002Fli>\u003Cli>Office Agent handles PPT, Word, Excel, and PDF workflows.\u003C\u002Fli>\u003C\u002Ful>\u003Cp>Other listed features include Kimi K2.6 Thinking for math, physics, logic, writing, and code; persistent memory and scheduled tasks through Kimi Claw; and “one-click” reuse of outputs as custom \u003Ca href=\"\u002Ftag\u002Fskills\">Skills\u003C\u002Fa>. The App Store version history also shows a steady stream of recent bug-fix releases, with version 2.7.3 listed as updated 4 days ago.\u003C\u002Fp>\u003Ch2>Why it matters\u003C\u002Fh2>\u003Cp>Kimi is moving from a research assistant into a broader workbench for builders. For developers, the draw is clear: fewer handoffs between ideation, research, prototyping, and presentation, especially when the app claims to handle databases, auth, charting, and document conversion in one place.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780430575259-9s2g.png\" alt=\"Kimi K2.6 goes live with 300-agent workflows\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>The market angle is just as direct. Kimi is positioning itself against premium AI assistants by bundling multi-agent execution, office automation, and web app generation into a single mobile product, while the App Store reviews show both strong praise and pushback on pricing and design.\u003C\u002Fp>\u003Cp>The key question is whether users want another chat app, or a phone-sized agent stack that can actually ship work. Kimi’s K2.6 bet is that the latter will win.\u003C\u002Fp>","Moonshot AI’s Kimi app adds 300-agent swarms, one-prompt site building, and multi-claw group chat in its K2.6 update.","apps.apple.com","https:\u002F\u002Fapps.apple.com\u002Fus\u002Fapp\u002Fkimi-kimi-k2-6-is-live\u002Fid6474233312",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780430570173-x78p.png","ai-agent","en","841eac88-b0f0-4a4c-9e1e-efc3b5c16281",[17,18,19,20,21],"Kimi","Moonshot AI","agent swarm","vibe coding","App Store",[23,24,25],"K2.6 adds 300-agent workflows and 4,000-step execution claims.","The app now targets site building, slides, office files, and research.","Pricing and UI comments suggest users want clearer value, not just more features.",2,"2026-06-02T20:02:25.552333+00:00","2026-06-02T20:02:25.545+00:00","a9bee732-b07c-4e5b-a0e6-3048577e32a7",{"tags":31,"relatedLang":42,"relatedPosts":46},[32,34,36,38,40],{"name":21,"slug":33},"app-store",{"name":20,"slug":35},"vibe-coding",{"name":18,"slug":37},"moonshot-ai",{"name":19,"slug":39},"agent-swarm",{"name":17,"slug":41},"kimi",{"id":15,"slug":43,"title":44,"language":45},"kimi-k26-live-300-agent-workflows-zh","Kimi K2.6 上線：300 代理工作流","zh",[47,53,59,65,71,77],{"id":48,"slug":49,"title":50,"cover_image":51,"image_url":51,"created_at":52,"category":13},"5efa67dd-b9f7-4a2f-8c68-3a4bc6a6b7d9","claude-code-dynamic-workflow-ai-harness-en","Claude Code 动态工作流：AI 自写 Harness","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781035372495-9czj.png","2026-06-09T20:02:22.33375+00:00",{"id":54,"slug":55,"title":56,"cover_image":57,"image_url":57,"created_at":58,"category":13},"2bd28e0e-0f4b-4987-a961-28763c1e1926","agent-orchestration-enterprise-ai-layer-en","Agent orchestration is the missing layer for enterprise AI","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780984981174-08mj.png","2026-06-09T06:02:31.384174+00:00",{"id":60,"slug":61,"title":62,"cover_image":63,"image_url":63,"created_at":64,"category":13},"95684312-23dc-4a78-a917-df14d132c5fa","ai-agents-use-blockchain-trust-layer-en","AI agents use blockchain as a trust layer","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780980506080-ki4s.png","2026-06-09T04:48:01.710214+00:00",{"id":66,"slug":67,"title":68,"cover_image":69,"image_url":69,"created_at":70,"category":13},"0208e47f-7d4c-4473-a0f9-4cd193b5c139","8-rag-patterns-demos-into-prod-en","8 RAG patterns that turn demos into prod","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780971552707-qpl7.png","2026-06-09T02:18:36.760049+00:00",{"id":72,"slug":73,"title":74,"cover_image":75,"image_url":75,"created_at":76,"category":13},"b413d484-6786-4c32-abdc-77f010ac7eba","fine-tuning-beats-rag-style-not-facts-en","Fine-tuning beats RAG when the goal is style, not facts","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780924681800-5xji.png","2026-06-08T13:17:25.701649+00:00",{"id":78,"slug":79,"title":80,"cover_image":81,"image_url":81,"created_at":82,"category":13},"57beb8b4-c233-400f-b95b-a97be1cf9d02","openclaw-small-business-ai-staff-en","OpenClaw shows how small businesses use AI staff","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780904882032-yp13.png","2026-06-08T07:47:27.730921+00:00",[84,89,94,99,104,109,114,119,124,129],{"id":85,"slug":86,"title":87,"created_at":88},"03db8de8-8dc2-4ac1-9cf7-898782efbb1f","anthropic-claude-ai-agent-task-automation-en","Anthropic's Claude AI Agent: A New Era of Task Automation","2026-03-25T16:25:06.513026+00:00",{"id":90,"slug":91,"title":92,"created_at":93},"045d1abc-190d-4594-8c95-91e2a26f0c5a","googles-2026-ai-agent-report-decoded-en","Google’s 2026 AI Agent Report, Decoded","2026-03-26T11:15:23.046616+00:00",{"id":95,"slug":96,"title":97,"created_at":98},"e64aba21-254b-4f93-aa21-837484bb52ec","kimi-k25-review-stronger-still-not-legend-en","Kimi K2.5 review: stronger, still not a legend","2026-03-27T07:15:55.385951+00:00",{"id":100,"slug":101,"title":102,"created_at":103},"30dfb781-a1b2-4add-aebe-b3df40247c37","claude-code-controls-mac-desktop-en","Claude Code now controls your Mac desktop","2026-03-28T03:01:59.384091+00:00",{"id":105,"slug":106,"title":107,"created_at":108},"254405b6-7833-4800-8e13-f5196deefbe6","cloudflare-100x-faster-ai-agent-sandbox-en","Cloudflare’s 100x Faster AI Agent Sandbox","2026-03-28T03:09:44.356437+00:00",{"id":110,"slug":111,"title":112,"created_at":113},"04f29b7f-9b91-4306-89a7-97d725e6e1ba","openai-backs-isara-agent-swarm-bet-en","OpenAI backs Isara’s agent-swarm bet","2026-03-28T03:15:27.849766+00:00",{"id":115,"slug":116,"title":117,"created_at":118},"3b0bf479-e4ae-4703-9666-721a7e0cdb91","openai-plan-automated-ai-researcher-en","OpenAI’s plan for an automated AI researcher","2026-03-28T03:17:42.312819+00:00",{"id":120,"slug":121,"title":122,"created_at":123},"fe91bce0-b85d-4efa-a207-24ae9939c29f","harness-engineering-ai-agent-reliability-2026","Harness Engineering: From Bridle to Operating System, The Missing Link in AI Agent Reliability","2026-03-31T06:36:55.648751+00:00",{"id":125,"slug":126,"title":127,"created_at":128},"7a09007d-820f-43b3-8607-8ad1bfcb94c8","mcp-explained-from-prompts-to-production-en","MCP Explained: From Prompts to Production","2026-04-01T09:24:40.089177+00:00",{"id":130,"slug":131,"title":132,"created_at":133},"116d5ee9-a4f1-4b5a-aac5-5d035dd22bbe","amazon-bedrock-agents-multi-agent-workflows-en","Amazon Bedrock Agents Gets Multi-Agent Workflows","2026-04-01T09:30:30.197685+00:00"]