[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-autogpt":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"3b08f091-5234-4f2e-b14b-f2629fd8942d","AutoGPT","autogpt",3,"AutoGPT 代表早期 AI agent 自動化的實驗路線：讓模型自己拆解任務、呼叫工具、迭代執行，常見於研究原型、CLI 工具與工作流自動化。它的重要性在於把「對話」推向「可執行流程」，也暴露了可靠性、成本與狀態管理的核心問題。","AutoGPT sits in the early wave of AI agents that try to break tasks into steps, call tools, and iterate with little human input. It matters because it shifts AI from chat to executable workflows, while exposing the hard parts: reliability, cost, memory, and state handling.",[12,21],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"2d99f1d9-86b5-4c8b-a1ea-4b212fd363f2","superpowers-121k-stars-agents-get-structured-zh","Superpowers 破 12.1 萬星的原因","Superpowers 在 5 個月內拿下 12.1 萬 GitHub stars。它靠的是把 AI agent 綁進技能、測試先行與固定流程，讓程式碼更乾淨、回頭修 bug 的成本更低。","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775093181136-ss2q.png","zh","2026-04-02T01:24:39.069101+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"042a73a2-18a2-433d-9e8f-9802b9559aac","github-ai-projects-to-watch-in-2026-zh","2026 必看 20 個 GitHub AI 專案","OpenClaw 衝到約 30.2 萬 GitHub stars 很吸睛，但 2026 年更大的變化其實是另一件事：開源 AI 焦點正從聊天介面，轉向 agents、工作流程、RAG 與多模態工具。這份名單反映的，是 AI 正在變成可部署的軟體基礎層。","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774519972047-6tx9.png","2026-03-26T08:28:09.619964+00:00"]