[{"data":1,"prerenderedAt":636},["ShallowReactive",2],{"$fwuenr1OZcDw8TjcC-BzsU1lhSGBFolBhwdGCSmwMXKw":3,"$fbekRXJxOJg1aYjlp5hVi8f0m50IXMafdqeIIrubmu_0":232,"$fVqO0k1BAadQrWkzSdzKIzB9FEw46o3cTAskVE807S0o":563,"mdc-kf808m-key":603},[4,18,35,47,58,68,78,93,101,111,120,130,143,152,161,171,181,189,199,208,220],{"id":5,"level":6,"link":7,"publish":8,"reward_type":9,"reward_data":10,"name":11,"intro":14,"image":16,"track":17},"臺北市資訊局","thanks","https:\u002F\u002Fdoit.gov.taipei",true,"連續贊助",2,{"zh":12,"en":13},"臺北市政府資訊局","Department of Information Technology, Taipei City Government",{"zh":15,"en":15},"臺北市政府資訊局（Department of Information Technology）為臺北市政府資訊業務主管機關，致力於推動市政創新與科技應用，將先進數位科技融入城市治理、公共服務及基礎設施建設，透過各項資訊平台運用，提升民眾良好的市政服務體驗，積極打造更智慧、便捷的臺北城市環境","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1iVTTBCvVuA95ntyn389Gj-nra-dmSRjc",null,{"id":19,"level":20,"link":21,"publish":8,"reward_type":9,"reward_data":22,"name":23,"intro":26,"image":29,"track":30},"andes","friend","https:\u002F\u002Fwww.andestech.com\u002Fen\u002F",3,{"zh":24,"en":25},"晶心科技股份有限公司","Andes Technology Corporation",{"zh":27,"en":28},"晶心科技股份有限公司于2005年成立於新竹科學園區，2017年於臺灣證交所上市 ([TWSE: 6533](https:\u002F\u002Ffinance.yahoo.com\u002Fquote\u002F6533.TW?p=6533.TW&ncid=stockrec); [SIN: US03420C2089](https:\u002F\u002Fwww.bourse.lu\u002Fsecurity\u002FUS03420C2089\u002F342557); [ISIN: US03420C1099](https:\u002F\u002Fwww.bourse.lu\u002Fsecurity\u002FUS03420C2089\u002F342557))。晶心是RISC-V國際協會的創始首席會員，也是第一家推出商用RISC-V向量處理器的主流CPU供應商。為滿足當今電子設備的嚴格要求，晶心提供可配置性高的32\u002F64位元高效能CPU核心，包含DSP、FPU、Vector、超純量  (Superscalar)、亂序執行  (Out-of-Order)、多核心及車用系列，可應用於各式ＳｏＣ與應用場景。晶心並提供功能齊全的整合開發環境和全面的軟\u002F硬體解決方案，可幫助客戶在短時間內創新其SoC設計。截至2025年底，Andes-Embedded™ SoC累計出貨量已超過200億顆。欲瞭解更多資訊，請訪問  [https:\u002F\u002Fwww.andestech.com](https:\u002F\u002Fwww.andestech.com\u002F)。請立即透過[LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002F13688177\u002F)、[Facebook](https:\u002F\u002Fwww.facebook.com\u002FAndesTechTW?locale=zh_TW)、[X(原 Twitter)](https:\u002F\u002Ftwitter.com\u002FAndes_Tech)、[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fc\u002FAndesTechnology\u002F) 以及[Bilibili](https:\u002F\u002Fspace.bilibili.com\u002F335295020)追蹤晶心最新消息。","As a Founding Premier member of RISC-V International and a leader in commercial CPU IP, Andes Technology ([TWSE: 6533](https:\u002F\u002Ffinance.yahoo.com\u002Fquote\u002F6533.TW?p=6533.TW&ncid=stockrec); [SIN: US03420C2089](https:\u002F\u002Fwww.bourse.lu\u002Fsecurity\u002FUS03420C2089\u002F342557); [ISIN: US03420C1099](https:\u002F\u002Fwww.bourse.lu\u002Fsecurity\u002FUS03420C2089\u002F342557)) is driving the global adoption of RISC-V. Andes’ extensive RISC-V Processor IP portfolio spans from ultra-efficient 32-bit CPUs to high-performance 64-bit Out-of-Order multiprocessor coherent clusters. With advanced vector processing, DSP capabilities, the powerful Andes Automated Custom Extension (ACE) framework, end-to-end AI hardware\u002Fsoftware stack, ISO 26262 certification with full compliance, and a robust software ecosystem, Andes unlocks the full potential of RISC-V, empowering customers to accelerate innovation across AI, automotive, communications, consumer electronics, data centers, and mobile devices. Over 20 billion Andes-powered SoCs are driving innovations globally. Discover more at [www.andestech.com](http:\u002F\u002Fwww.andestech.com\u002F) and connect with Andes on [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002F13688177\u002Fadmin\u002Fdashboard\u002F), [X (formerly Twitter)](https:\u002F\u002Fx.com\u002FAndes_Tech) , [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fc\u002FAndesTechnology) and [Bilibili](https:\u002F\u002Fspace.bilibili.com\u002F335295020).","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1SXvUlmHuSXDchd6HoejXMvHiDebVoVgL",{"id":31,"name":32},517,{"en":33,"zh-hant":34},"Open Source Inspired Hardware","",{"id":36,"level":6,"link":37,"publish":8,"reward_type":38,"reward_data":39,"name":40,"intro":43,"image":46,"track":17},"sifive","https:\u002F\u002Fwww.sifive.com","Null",0,{"zh":41,"en":42},"美商賽發馥股份有限公司臺灣分公司","SiFive",{"zh":44,"en":45},"身為 RISC-V 的發明者與領導廠商，SiFive 正在改變未來運算的典範，將 RISC-V 的無限潛力引領至世上最高效能與資料密集應用中。SiFive 所建構無與倫比的運算平台能夠在晶片設計的每個細分市場成功協助全世界眾多科技領導廠商，從創新發明、優化至完美、並推出最先進的晶片設計解決方案，涵蓋人工智慧、機器學習、車用電子、資料中心、行動運算與消費性電子等應用領域。SiFive 與您同行，創造 RISC-V 的無限未來。欲知更詳細信息，請洽 www.sifive.com","As the pioneers who introduced RISC-V to the world, SiFive is transforming the future of computing by bringing the power and flexibility of RISC-V to the world. SiFive’s market-leading IP provides the blueprint for high-performance, customizable, and energy-efficient processor cores across the entire computing spectrum, from the intelligent edge to the most advanced AI data centers. For more information, visit www.sifive.com","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=17TquX8coFopolRFi2W9ZbDUzgkT5YF0X",{"id":48,"level":49,"link":50,"publish":8,"reward_type":9,"reward_data":10,"name":51,"intro":54,"image":57,"track":17},"IMA","gold","https:\u002F\u002Fwww.ima.org.tw\u002F",{"zh":52,"en":53},"中華民國資訊經理人協會","Information Management Association",{"zh":55,"en":56},"IMA資訊經理人協會自1982年成立至今已逾四十年，是台灣歷史最悠久的IT專業團體之一。自2022年由台灣大哥大資訊長蔡祈岩接任理事長後，致力於串聯IT產業、產業IT、政府、學術及開源社群資源，推動台灣成為全球最能發揮IT與AI專業實力的國家。\n\n近年協會重點推動工作如下：\n一、IT Matters Awards—打造IT雇主品牌獎：由數位發展部指導、IMA主辦的 IT Matters Awards，是全台首創以IT人才、技術與應用為核心的年度獎項，表揚重視IT人才、推動數位轉型並對社會產生正向影響的企業與個人。2026年將持續擴大辦理並與《天下雜誌》共同舉辦，透過評選標竿企業、人才與創新專案，分享最佳實務經驗，促進企業與人才交流，推動台灣IT人才質與量的雙向成長。\n二、執行政府數位發展相關計畫：整合活動推廣、產業交流、Demo Day與多元行銷策略，今年度更協助軟體開源推廣機制，包含開源上架指引優化等，擴大產業參與及政策影響力。\n三、Taiwan Tongues台灣通用語料集計畫：建構台灣通用語料共享計畫，致力建立涵蓋台灣華語、台語、客語與原住民族語的開放語料庫，讓全球語言模型能理解台灣的語言與文化。\n四、台灣開源連線計畫：舉辦專家座談、開源專案展示與國際交流，攜手台灣開源社群推動技術交流與創新合作，打造「台灣開源隊」，提升我國在全球開源生態系中的角色。\n\nIMA將持續以專業行動，深化產業鏈結與生態系建構，從單一活動推動提升為跨產業協作平台，為台灣在全球數位與AI浪潮中爭取更關鍵的位置。","Information Management Association (IMA), Taiwan\nFounded in 1982, IMA is one of Taiwan's longest-established IT professional organizations, dedicated to strengthening Taiwan's digital competitiveness.\n\nSince 2022, the association has been chaired by Rock Tsai, CIO of Taiwan Mobile.\nOur members:\n．Industrial Enterprises: AMD, Phison, Taiwan Mobile, Fubon Bank, etc.\n．IT Solution Providers: Top 10 SI companies such as Systex Group, WITS, Syscom Group\n\nIn 2026, IMA focuses on four key initiatives:\n\n1. IT Matters Awards: Recognizing outstanding IT employers, technology talent, digital transformation achievements, and innovative projects, co-organized with CommonWealth Magazine to share best practices and foster collaboration.  \n2. Government Digital Development Programs: Supporting policy implementation through industry events, networking activities, Demo Days, and multi-channel communications.\n3. Taiwan Tongues: Building an open corpus covering Taiwanese Mandarin, Taiwanese Hokkien, Hakka, and Indigenous languages to help global language models better understand Taiwan.\n4. Taiwan Open Source Initiative:  Promoting technical collaboration, open-source project showcases, and international exchange; building “Team Taiwan” in the global open-source ecosystem.  \n\n\nIMA remains committed to advancing IT value, fostering cross-sector collaboration, and positioning Taiwan at the forefront of the global digital and AI landscape.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1USFHc7t-l4bctCkZUXQ_f21Fng1ZO1lR",{"id":59,"level":60,"link":61,"publish":8,"reward_type":38,"reward_data":39,"name":62,"intro":64,"image":67,"track":17},"KKTIX","bronze","https:\u002F\u002Fkktix.com\u002F",{"zh":63,"en":59},"華娛網路娛樂股份有限公司",{"zh":65,"en":66},"KKTIX作為台港兩地領先的活動售票、報名與線上直播平台，致力於透過穩定\n可靠的技術服務，協助主辦單位打造更好的活動體驗。從技術研討會、開源社\n群聚會、教育課程到大型論壇、展演活動與線上直播，KKTIX支援各種規模的\n活動需求。\n自2010年成立以來，KKTIX已累積超過700萬名會員，每年服務超過75,000場\n活動。平台提供報名管理、售票、金流、會員經營、數據分析等全方位方案，\n讓主辦單位能專注於內容與社群經營！\nKKTIX長期支持技術與開源社群發展，陪伴許多開發者社群、使用者社群及非\n營利組織舉辦活動。我們相信，每一場活動都是知識交流與社群連結的起點，\n而好的工具能讓更多人專注於分享、學習與創造價值。","As Taiwan and Hong Kong’s leading platform for event ticketing, registration,\nand live streaming, KKTIX is dedicated to empowering organizers with reliable\ntechnology and seamless event experiences. From technical conferences,\nopen-source community meetups, and educational programs to large-scale\nforums, live performances, and online events, KKTIX supports events of all\nsizes and formats.\n\nSince its founding in 2010, KKTIX has amassed more than 7 million registered\nmembers and proudly supports over 75,000 events annually. The platform\nprovides comprehensive solutions—including event registration, ticketing,\npayment processing, membership management, and data analytics—enabling\norganizers to focus on curating impactful content and fostering vibrant\ncommunities.\n\nKKTIX has a long-standing commitment to driving the growth of technology\nand open-source communities, partnering with developer ecosystems, user\ngroups, and non-profit organizations to bring people together. We believe that\nevery event serves as a catalyst for knowledge sharing and community\n\nbuilding, and that the right tools empower people to focus on learning,\ncollaboration, and creating lasting value.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1rWagmNMioYe6vRW0144D939XqHD-ZhI-",{"id":69,"level":60,"link":70,"publish":8,"reward_type":38,"reward_data":39,"name":71,"intro":74,"image":77,"track":17},"國網中心","https:\u002F\u002Fwww.nchc.org.tw",{"zh":72,"en":73},"財團法人國家實驗研究院國家高速網路與計算中心","National Center for High-performance Computing",{"zh":75,"en":76},"財團法人國家實驗研究院國家高速網路與計算中心（簡稱國網中心），於1991年成立，致力扎根國內高速計算技術，提供世界級的高速計算與學研網路設施，為台灣的科技能量奠基。我們秉持著「驅動轉型，為更美好的未來而努力」的信念，積極推動高速計算的技術與應用發展，引領數位轉型並促進智慧生活的改變。","National Center for High-performance Computing (NCHC), founded in 1991,is committed to strengthening national high-performance computing (HPC)technology, providing world-class supercomputing and academic researchnetwork infrastructure, and laying foundation for the development oftechnology in Taiwan. NCHC, in the spirit of \"driving transformation fora better future with HPC\", is dedicated to promoting HPC technology andapplications development, leading digital transformation in industriesand smart living.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1zegCBM3yK8M049xewjkc0IRtE2UqIUdU",{"id":79,"level":49,"link":80,"publish":8,"reward_type":9,"reward_data":10,"name":81,"intro":84,"image":87,"track":88},"國泰金控","https:\u002F\u002Fwww.cathayholdings.com\u002Fholdings\u002Fbrand\u002Ffintech",{"zh":82,"en":83},"國泰金融控股公司","Cathay Financial Holdings",{"zh":85,"en":86},"國泰金控致力成為「以金融為核心的科技公司」，透過數位、數據與技術，積極研發並導入國際前瞻技術，打造創新平台與產品服務。\n整合集團資源、強化一站式數位金融體驗，國泰金控發揮持續創新與技術領先優勢，樹立技術與開發環境典範。同時，積極佈局海外並接軌國際，深耕大中華與東南亞市場，注入數據驅動文化，以高效協作的矩陣式組織，持續朝「亞太地區最佳金融機構」願景邁進，共創更好的未來金融。","Cathay Financial Holdings (FHC) is committed to being a technology company with finance at its core. We actively develop and adopt international innovations to build cutting-edge platforms and services through digitalization, data, and technology.\nBy integrating group-level resources, Cathay FHC leverages its strengths in continuous innovation, intelligent applications, and technological leadership to set a benchmark for development environments. At the same time, we continue expanding across the Asia-Pacific, aligning with global trends to become the leading financial institution in the region. Driven by a data-driven culture and a highly collaborative matrix organization, Cathay FHC is dedicated to shaping the future of finance.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1JN_uNRjQ6-9I7z_azEjhahMtTQqDk3SC",{"id":89,"name":90},526,{"en":91,"zh-hant":92},"Open Source Policy","開源政策",{"id":94,"level":60,"link":95,"publish":8,"reward_type":38,"reward_data":39,"name":96,"intro":97,"image":100,"track":17},"ONLYOFFICE","https:\u002F\u002Fwww.onlyoffice.com",{"zh":94,"en":94},{"zh":98,"en":99},"ONLYOFFICE 是一個國際性的開源專案，由領先的 IT 公司 Ascensio System SIA 開發。目前在中國、新加坡、英國等 7 個國家設有分公司，為全球企業與個人使用者提供高效率的文件處理與協作解決方案，深受網易、百威中國、中信集團、南京大學、中國知網等眾多企業與教育機構的青睞。\n\nONLYOFFICE Docs 是一套功能完整的線上辦公套件，整合了文件編輯、試算表、簡報、可填寫表單以及 PDF 編輯器，並與 Microsoft Office 格式具備高度相容性。此外，還提供數百種格式與樣式設定工具，以及多元的協作功能。","ONLYOFFICE, an open-source office software project, focuses on advanced and secure office solutions. With over 15 million users worldwide, it is recognized for its innovation in the online office domain. The ONLYOFFICE ecosystem includes collaborative applications such as online editors for text documents, spreadsheets, presentations, forms, and PDFs, along with a room-based collaborative platform. \nAs an international company, ONLYOFFICE has employees and contributors across the globe, with offices located in Singapore, Dallas, Shanghai, Riga, London, Belgrade, Yerevan, and Tashkent.\n","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1uilDLdToDeqOJYEGoljpbw2l9YOYDKvs",{"id":102,"level":60,"link":103,"publish":8,"reward_type":38,"reward_data":39,"name":104,"intro":107,"image":110,"track":17},"QNAP","https:\u002F\u002Fwww.qnap.com\u002Fzh-tw",{"zh":105,"en":106},"QNAP Systems, Inc. 威聯通科技","QNAP Systems, Inc.",{"zh":108,"en":109}," QNAP 命名源自於高品質網路設備製造商（Quality Network Appliance Provider），我們致力研發軟體應用，匠心優化硬體設計，並設立自有生產線，以提供全面而先進的科技解決方案。QNAP 專注於儲存、網通及智慧視訊產品創新，並持續拓展人工智慧應用，推動 Edge AI 邊緣優先、雲端協作的整合模式，協助客戶在不同場域中即時分析、決策與協同運作，充分發揮數據價值。\n\nQNAP 亦是一個全面性的資安品牌，我們將資料保護、防勒索、不可變儲存與多層資安機制融入解決方案中，確保企業營運不中斷並維持長期資料完整性。在 QNAP 的企業藍圖中，NAS 早已突破儲存裝置的框架，更是驅動人工智慧、邊緣運算與資安防護的重要平台，為全球用戶創造更大優勢與價值。","QNAP (Quality Network Appliance Provider) is a global leader in software development, hardware design, and in-house manufacturing, delivering solutions that help businesses and individuals securely store, connect, and innovate. We drive breakthroughs in storage, networking, and smart video, and advance an Edge AI strategy that integrates edge-first deployment with cloud collaboration—enabling real-time data analysis, decision-making, and collaboration across diverse environments.\n\nQNAP is also a comprehensive cybersecurity brand, embedding data protection, anti-ransomware resilience, immutable storage, and multi-layered security into our solutions. For us, NAS has evolved beyond storage—turning NAS into the platform that drives AI, edge intelligence, and trusted data protection worldwide.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1ZBMNO4GxVf6McP1VBEbkL7qs2xdLHBSm",{"id":112,"level":20,"link":113,"publish":8,"reward_type":38,"reward_data":39,"name":114,"intro":116,"image":119,"track":17},"Appier","https:\u002F\u002Fwww.appier.com\u002Fzh-tw\u002F",{"zh":115,"en":112},"沛星互動科技股份有限公司",{"zh":117,"en":118},"Appier 是一家 AI 原生的 Agentic AI 即服務（AaaS）公司，透過最先進的廣告科技（AdTech）與行銷科技（MarTech）解決方案，協助企業制定更明確的商業決策。創立於 2012 年，Appier 秉持 Making AI Easy by Making Software Intelligent 的願景，致力透過旗下由 Agentic AI 驅動的的廣告雲（Ad Cloud）、個人化雲（Personalization Cloud) 及數據雲（Data Cloud）解決方案，賦予企業自主、自適應、即時決策的能力，將 AI 轉化為可衡量的投資報酬（ROI）。Appier 目前在亞太、美國與 EMEA 地區設有 17 個據點，並於東京證券交易所 Prime 板上市。欲了解更多資訊請參閱 Appier | Empowering Businesses to Turn AI into ROI 。","Appier (TSE: 4180) is an AI-native Agentic AI as a Service (AaaS) company that empowers businesses to create value through cutting-edge AdTech and MarTech solutions. Founded in 2012 with the vision of “Making AI Easy by Making Software Intelligent,” Appier helps businesses turn AI into ROI through its Ad Cloud, Personalization Cloud, and Data Cloud—each powered by Agentic AI that enables autonomous, adaptive, and real-time decision-making. Today, Appier operates 17 offices across APAC, the US, and EMEA, and is listed on the Tokyo Stock Exchange. Learn more at Appier | Empowering Businesses to Turn AI into ROI .","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1HXbbA7QkJWwkXeHPE0nTfYRJcfKI0E4z",{"id":121,"level":49,"link":122,"publish":8,"reward_type":9,"reward_data":123,"name":124,"intro":126,"image":129,"track":17},"玉山銀行","https:\u002F\u002Fwww.esunbank.com\u002Fzh-tw\u002Fpersonal",5,{"zh":121,"en":125},"E.SUN Bank",{"zh":127,"en":128},"玉山銀行成立於1992年，取名自台灣最高的山，以顧客體驗為核心的理念，致 力於構建科技與綠色雙軸轉型的的金融發展策略。作為數位金融的領導品牌， 玉山銀行擁有超過1300位科技人才，負責整體的數位發展、智能應用、資訊研 發以及資安管理。為臺灣首家銀行將人工智慧深入應用於各項業務，也是首家 銀行以開放的雲端原生技術、微服務架構自建核心系統。近年來玉山銀行展現 卓越的綜合績效，榮獲第十二屆菁業獎共8項大獎，累計歷屆獲奬總數持續領先 金融同業。從台灣到亞洲，玉山以靈活的策略和高效的執行力穩健發展，為顧 客創造持續的價值，邁向永續經營的未來。","E.SUN Bank, established in 1992 and named after Taiwan’s highest mountain, is dedicated to customer-centric values and committed to developing financial strategies centered around technology and ESG. With more than 1,300 technology professionals forming a technology team responsible for overall digital development, AI applications, IT research, and information security management, we are the first bank in Taiwan to deeply integrate AI into various businesses and the first bank to build our core system using cloud-native technology and a microservices architecture. In recent years, E.SUN Bank has demonstrated outstanding comprehensive performance, winning a total of 8 major awards at the 12th Elite Awards for Taiwan Banking Excellence, which maintain our industry-leading record in total awards received. From Taiwan to Asia, E.SUN Bank steadily grows with flexible strategies and efficient execution, creating sustained value for our customers and moving toward a future of sustainability.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1Wu648Tl50fARXtXGK2qkgPfXWhc4-hiT",{"id":131,"level":132,"link":133,"publish":8,"reward_type":134,"reward_data":135,"name":136,"intro":139,"image":142,"track":17},"慧邦科技","silver","https:\u002F\u002Fwww.gamesofa.com","累計贊助",16,{"zh":137,"en":138},"慧邦科技股份有限公司  Gamesofa Inc.","Gamesofa Inc.",{"zh":140,"en":141},"慧邦科技Gamesofa成立於2005年，透過優異的網路核心技術，自製研發並行銷營運30餘款web, iOS, Android多人遊戲，是台灣首屈一指的遊戲開發公司。\n\nGamesofa以「5分鐘．想樂最輕鬆」為核心理念，成功打造台灣第一大網路麻將遊戲【神來也麻將】並在印尼、越南、星馬、美加推出德州撲克與當地牌類\n及模擬休閒遊戲【貓咪造咖】，全球累積註冊用戶數超過7,500萬，每日活躍用戶超過200萬人。Gamesofa除了在遊戲開發力求創新，更擅長以資料分析\n驅動營運決策，讓產品開發、營運、行銷團隊皆能透過數據分析工具與預測模型，快速掌握遊戲狀況，擬定策略，是一間充滿熱情與效率的企業。","Founded in 2005, Gamesofa is a leading Taiwanese game developer powered by top-tier core web technologies. We’ve self-developed and operated over 30 multiplayer games across web, iOS, and Android platforms.\n\nLiving by our motto, \"Fun in Five Minutes,\" we successfully launched Taiwan’s #1 online Mahjong game, GodGame Mahjong. We're also capturing hearts across Indonesia, Singapore, Malaysia, and North America with Texas Hold’em, local card games, and our casual simulation hit, Catfe World. With over 75 million registered users worldwide and 2 million+ daily active users, our community keeps growing!\n\nWe don't just innovate; we run on data. By leveraging advanced data analytics and predictive models, our development, operations, and marketing teams can instantly read the game environment and pivot strategies. At Gamesofa, we combine passion with high-efficiency execution.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1Tw5jqRB3RNLQ6ey9dklsM0fuAWzVXW8o",{"id":144,"level":60,"link":145,"publish":8,"reward_type":9,"reward_data":135,"name":146,"intro":148,"image":151,"track":17},"祐生研究基金會","https:\u002F\u002Fwww.archilife.org\u002F",{"zh":144,"en":147},"The Archilife Research Foundation",{"zh":149,"en":150},"祐生研究基金會自 1987 年推動建築與環境永續發展之研究開始，推動長期的知識累積與人才培養。除了過去建築、環境、生態、健康與資訊社會與文化等面向之碩士論文獎助主題外，本會目前定期舉辦的聯誼會及讀書會，強化祐生成員的知識密度。 其後，於 2011 年起，本會持續針對國內開源活動進行贊助，也針對國內獨立遊戲開發者，推動知識與資訊分享聚會，期能幫助國內相關社群之發展。","Since 1987, the Archilife Research Foundation started long-term researches in architecture, sustainability, and go on to other areas of knowledge integration. Efforts including previously giving scholarships in aforementioned areas, and currently holding reading group meetings and communion events for knowledge keepers to better our understandings of the world. Starting from 2011, we also have been sponsoring various open source related events, holding meetups and game jams for local game developers’ groups, in the hope of supporting the growth of relevant communities in these fields.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1Jhy0M0l7kqfA-auPZwPHmrwxtuiBsrjB",{"id":153,"level":154,"link":155,"publish":8,"reward_type":38,"reward_data":39,"name":156,"intro":158,"image":160,"track":17},"Canonical","diamond","https:\u002F\u002Fcanonical.com\u002F",{"zh":153,"en":157},"Canonical ",{"zh":159,"en":159},"Helping innovators build the future since 2004.\nCanonical’s story is closely linked to the communities that shape us, including the global community of open source contributors and enthusiasts who are part of our team.\n\nSince 2004, we have nurtured a community around Ubuntu, a Linux distribution that leveled the playing field by making software accessible to everyone - whether you are a developer in Calcutta, an end user in Cape Town or a sysadmin in California. Today, we continue to build and grow communities around us, as we help make open source more secure, reliable and manageable at scale.\n\nTogether, we enable organizations and end users everywhere to innovate with confidence on the largest supported collection of open source software.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=100QqFUM1e5FQoSqOnYtwmfAFBU4uJGNF",{"id":162,"level":49,"link":163,"publish":8,"reward_type":134,"reward_data":164,"name":165,"intro":167,"image":170,"track":17},"Oracle（MySQL）","https:\u002F\u002Fwww.mysql.com\u002F",12,{"zh":166,"en":166},"MySQL",{"zh":168,"en":169},"MySQL 是世界上最受歡迎的開源資料庫。 它為 Facebook、Booking、Uber 和 Tesla 等最具創新性的公司都用它當主要的資料庫。 它可以在本地使用，也可以作為 Oracle 雲端上的 MySQL 資料庫服務使用。 對於開發人員來說，它是一個易於使用、可靠且高效能的資料庫，支援 NoSQL 和 SQL。許多 SaaS、電子商務、金融、電信和Fortune 1000 強公司都依靠 MySQL 企業版的高級安全功能來保護資訊隱私、防止資料外洩，並協助滿足 GDPR、PCI、HIPAA 等監管要求。 MySQL 高可用性具有內建的 HA能力，完全整合到 MySQL 伺服器中，可實現 99.99% 的正常運作時間\n","MySQL is the World’s Most Popular Open Source Database. It powers the most innovative companies including Facebook, Booking, Uber, and Tesla. It is available on-premises and as the MySQL Database Service on Oracle Cloud. For developers, it’s an easy to use, reliable and high-performance database with NoSQL and SQL support. SaaS, ecommerce, financial, telecom, and Fortune 1000 companies rely on the MySQL Enterprise edition advanced security features to protect the privacy of information, prevent data breaches and help meet regulatory requirements such as GDPR, PCI, HIPAA. MySQL High Availability has native HA, fully integrated into the MySQL Server for 99.99% uptime. ","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1gK-ZMKBj5g59qekvVWutwAq7s2v3MmGT",{"id":172,"level":49,"link":173,"publish":8,"reward_type":134,"reward_data":174,"name":175,"intro":177,"image":180,"track":17},"Berry AI","https:\u002F\u002Fberry-ai.com",6,{"zh":176,"en":172},"華捷智能股份有限公司",{"zh":178,"en":179},"Berry AI 運用電腦視覺與 AI 技術，協助美國速食（QSR）業者分析得來速服務流程、改善營運效率。我們的產品在全美門市即時運作，從攝影機影像中偵測車輛動線、計時服務流程，並產出營運洞察，工程團隊每天面對的是真實世界、大規模的 Vision AI 挑戰。\nBerry AI 的客戶包含多間全球前十大連鎖速食品牌。繼 2025 年與 Zaxby's 簽署近千家門市的全品牌導入合約後，2026 年我們再與美國知名品牌 Culver's 展開全品牌部署，業務持續快速成長。Berry 亦獲得台灣上市公司飛捷科技的投資（全球前三大 POS 製造商之一），擁有穩定的資源與客戶基礎。\n我們的團隊位於台灣，成員來自海內外知名學府與大型科技公司，工程師能直接參與美國市場產品的核心開發。隨著業務成長，我們也在持續徵才，歡迎造訪 berry-ai.com 了解更多。","Berry AI leverages computer vision and AI to help U.S. quick-service restaurant (QSR) operators analyze drive-thru workflows and improve operational efficiency. Our products run in real time at restaurants across the U.S.—detecting vehicle journeys from camera feeds, timing service stages, and generating operational insights. For our engineers, that means working on real-world, large-scale Vision AI challenges every day.\nBerry AI serves several of the world's top ten fast-food chains. Following our 2025 full-brand agreement with Zaxby's covering nearly 1,000 locations, we kicked off another full-brand deployment with Culver's in 2026, and our business continues to grow rapidly. We are backed by Flytech Technology, a publicly listed Taiwanese company and one of the world's top three POS manufacturers.\nOur team is based in Taiwan, with members from top universities and major tech companies worldwide—engineers here directly contribute to the core of products deployed in the U.S. market. As we grow, we're also hiring; visit berry-ai.com to learn more.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=19MMkcQMO3m6qMBD8KvHSEVIeFdY44WHU",{"id":182,"level":49,"link":183,"publish":8,"reward_type":38,"reward_data":39,"name":184,"intro":185,"image":188,"track":17},"Nitra","https:\u002F\u002Fnitra.com\u002Fcareers",{"zh":182,"en":182},{"zh":186,"en":187}," \"The financial home for independent medicine.\" Nitra 是專為美國醫療院所打造的 AI-native 財務平台，讓每間獨立診所都能少花時間處理繁瑣行政、多花時間照顧病患。\n\n\nNitra 整合財務管理、醫療採購與病患行政系統，建立能自動化支付、採購、庫存管理、預約排程、保險資格驗證與病患溝通等核心流程。成立至今，Nitra 已完成 1.87 億美元（約新台幣 59.8 億元）募資，年化交易額突破 10 億美元，是美國醫療科技領域成長最快的新創之一。\n\n\nNitra 從創立初期便將產品研發重心設於台灣，目前 Nitra Taiwan 主導公司絕大部分的產品開發工作，團隊規模在過去半年成長超過一倍，成員涵蓋軟體工程師、設計師與產品經理，並持續快速擴編中。","\"The financial home for independent medicine.\" Nitra is the AI-native financial platform built for U.S. healthcare specialty practices — helping every independent practice spend less time on paperwork and more time on patients.\n\n\nThe platform brings together financial management, a medical supplies marketplace, and patient administration — automating payments, procurement, inventory management, scheduling, insurance eligibility verification, and patient communication. Nitra has raised $187M in funding and surpassed $1B in processing volume, making it one of the fastest-growing healthcare fintech startups in the U.S.\n\n\nFrom its earliest days, Nitra chose to build its core R&D team in Taiwan. Today, Nitra Taiwan leads the majority of the company's product development, with the local team more than doubling in size over the past six months — spanning software engineers, designers, and product managers — and continuing to expand.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1SPHLtEBEX9ap_snb8Rm2SwjIVGlR52gq",{"id":190,"level":60,"link":191,"publish":8,"reward_type":38,"reward_data":39,"name":192,"intro":195,"image":198,"track":17},"源鋼技術顧問有限公司","https:\u002F\u002Fsunsquare.tech\u002F",{"zh":193,"en":194},"源鋼技術顧問有限公司 SUN SQUARE Co., Ltd","SUN SQUARE Co., Ltd",{"zh":196,"en":197},"源鋼技術顧問有限公司 Sun Square Co., Ltd. 專注於資安、技術顧問與產業標準導入服務，協助企業強化產品安全、系統安全、軟體供應鏈安全與合規實作能力。\n\n我們長期關注開源治理、SBOM、開源供應鏈安全、工控系統資安與產業標準實作，也持續參與並貢獻開源社群與相關技術實務。我們相信開放技術與工程實務是建立可信賴數位環境的重要基礎。\n\n源鋼歡迎對開源軟體、安全工程、SBOM、供應鏈安全與工控資安有興趣的開發者、研究者與技術夥伴，一起交流與合作。","Sun Square Co., Ltd. provides cybersecurity, technical consulting, and industry standard implementation services to help organizations strengthen product security, system security, software supply chain security, and practical compliance capabilities.\n\nWe have long followed open source governance, SBOM, open source supply chain security, industrial cybersecurity, and practical implementation of industry standards. We also continue to participate in and contribute to open source communities and related engineering practices. We believe open technologies and engineering practices are important foundations for building a trustworthy digital environment.\n\nSun Square welcomes developers, researchers, and technology partners interested in open source, security engineering, SBOM, supply chain security, and industrial cybersecurity to connect, exchange ideas, and collaborate with us.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1ozuvt4cNMXQCQqD5VY4EyMdQSbwVuDAL",{"id":200,"level":6,"link":201,"publish":8,"reward_type":38,"reward_data":39,"name":202,"intro":204,"image":207,"track":17},"Rozeta","https:\u002F\u002Frozeta.app",{"zh":203,"en":203},"Rozeta AI",{"zh":205,"en":206},"Rozeta AI 是專為全球化溝通打造的即時翻譯平台，提供精準的語音轉文字、雙向翻譯與即時字幕，協助不同語言的參與者同步理解會議內容，並使用自己最熟悉的語言自在交流。\n不同於一般逐字翻譯工具，Rozeta AI 能根據會議主題、產業背景及企業自訂詞彙掌握溝通情境，提升專業術語、產品名稱與特定用語的翻譯準確度。無論是跨國團隊協作、客戶會議、教育訓練、線上研討會、國際論壇或大型活動，都能提供流暢且一致的多語溝通體驗。\n使用者透過電腦、平板或手機瀏覽器即可加入，無需下載或安裝 App，便能即時查看共享逐字稿與翻譯內容。平台亦支援簡報浮動字幕、講者辨識、會議逐字稿與 AI 摘要，協助團隊從即時溝通延伸至有系統的會後整理與追蹤。\nRozeta AI 提供 40 種語言的低延遲即時翻譯，協助企業跨越語言隔閡，提升國際協作效率，讓每位參與者都能充分理解、清楚表達並真正投入對話。","Rozeta AI is a real-time translation platform designed for global communication. It delivers accurate speech-to-text transcription, bidirectional translation, and live captions, enabling participants who speak different languages to follow meetings in real time and communicate confidently in the language they know best.\n\nUnlike conventional word-for-word translation tools, Rozeta AI understands the context of each conversation by incorporating meeting topics, industry knowledge, and organization-specific terminology. This improves the accuracy of technical terms, product names, and specialized language. Whether used for global team collaboration, client meetings, training sessions, webinars, international forums, or large-scale events, Rozeta AI provides a seamless and consistent multilingual communication experience.\n\nParticipants can join through a web browser on a computer, tablet, or mobile device without downloading or installing an app. They can instantly access shared live transcripts and translations, while additional features such as floating captions for presentations, speaker identification, meeting transcripts, and AI-generated summaries support structured post-meeting review and follow-up.\n\nWith low-latency, real-time translation across 40 languages, Rozeta AI helps organizations overcome language barriers, improve global collaboration, and empower every participant to understand fully, communicate clearly, and engage meaningfully in every conversation.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1EgrBD5uRahGcIBjIl7CC0off_2uWcxhq",{"id":209,"level":210,"link":211,"publish":8,"reward_type":212,"reward_data":164,"name":213,"intro":216,"image":219,"track":17},"ocf","co-organizer","https:\u002F\u002Focf.tw\u002F","累計合作",{"zh":214,"en":215},"開放文化基金會","Open Culture Foundation",{"zh":217,"en":218},"開放文化基金會（Open Culture Foundation，簡稱 OCF）是一個非營利性的組織。透過推廣開放科技和跨界合作，在台灣持續的銜繫科技社群與其他公／私領域，來促成開放共創保障數位人權、支持透明涵融的數位公民社會。\n\n自 2014 年創立以來，我們以法人做為組織形式，支持台灣 30 多個開放科技社群，在過程中，不僅是持續性的推廣開放科技概念，我們也開始參與政策倡議，為眾人的數位人權發聲，進而創建了一個在台灣發展開放科技的基地。這些成果並非由開放文化基金會獨立實現，而是透過科技社群和公民夥伴一起促使台灣的數位\u002F網路環境變得更加公開、透明和公眾參與 — 不論這樣的參與是以個人、社群或是組織為名義。","(The) Open Culture Foundation is a non-profit organization. Through promoting open technology and cross-field collaboration, we continue to connect tech communities and other public and private entities in Taiwan. By doing so, we work to promote open co-creation and protect digital rights, and thereby support a more transparent and inclusive digital civil society.\nSince 2014, we have functioned as a legal entity and supported over 30 open technology communities in Taiwan. Throughout this process, we have not only continued to promote the idea of open technology, we have also become involved in policy advocacy and spoken up for the public's digital rights. Through this process, we have created a base for the development of open technology in Taiwan. None of these successes are the result of OCF alone. Rather, they are the result of several open tech communities, individuals and organizations working together to make Taiwan's internet and digital environment more open, transparent, and participation.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1hWBw5glA7cS53GFdRsCDU5YMdvAtfKar",{"id":221,"level":222,"link":223,"publish":8,"reward_type":212,"reward_data":224,"name":225,"intro":228,"image":231,"track":17},"ntust","co-host","https:\u002F\u002Fece.ntust.edu.tw\u002F",9,{"zh":226,"en":227},"臺灣科技大學 電子工程系","NTUST - Department of Electronic and Computer Engineering ",{"zh":229,"en":230},"本校定位為「國際化應用研究型大學」，配合學校發展主軸，本系發展目標為培育優秀高科技人才，扮演銜接基礎科學與產業應用的橋樑。本系配合國家科技政策的長遠發展與國際化趨勢，重視實務能力，培育理論與實務兼具，專業與倫理並重，具國際視野及創新能力的電子科技人才，使其具備AI 資訊、電力電子與半導體、通訊及光電元件與系統之其一或斜槓專業 。使學生從事製作、維護及測試能力。並以專題研究及產學合作計畫，培養學生實務能力，協助企業發展。與國內教研單位及國際知名學研機構密切合作，提升研發能量，發展科技大學特色，提昇我國產業的全球競爭力。","Our university is recognized as an application-oriented research-type international university. In line with this university axis, our department's development goal is to educate high-tech personnel and supply delicate application technology. With this, our department will play a role of connecting basic technology and industrial application. As part of our government's technology policy and the internationalization of education, we will continue to emphasize practical application in our department. With a “combination of theory and application” and “balance on IQ and EQ,” electronic specialists with “international view and creation capability” will be trained in our department. These engineers will be able to design, manufacture, maintain, and test the systems and elements in electronics, information communication, and photo-electronics. With the “professional topics for undergraduate students,” “cooperation projects from the industry,” and “the enforcement of the manufacturing ability of students,” our professors will help the industry to develop their required technologies. We will be able to boost the energy of our research ability, develop our specialization, and lift our industry's global competitiveness through cooperation with neighboring educational and research institutions.","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1v9FGN3h1BJyBhxeqKlOcpYafQsw8QKNv",{"id":233,"name":234,"description":237,"sessions":240,"colors":559,"sponsors":562},543,{"en":235,"zh-hant":236},"Open LLM End User: Downstream Applications","Open LLM End User: 開源模型應用",{"en":238,"zh-hant":239},"This track focuses on application scenarios and system integration after obtaining generated content from open-source models. We welcome sharing practical experiences on transforming AI capabilities into actual tools to solve real-world problems. Topics include, but are not limited to:\r\n\r\n1. RAG & System Integration\r\nShare implementations of RAG (Retrieval-Augmented Generation) architectures, applications of vector databases, and how to integrate LLMs into existing software workflows.\r\n2. AI Agents & Automation Workflows\r\nExplore building AI Agents with task planning and execution capabilities using open-source models, and automation practices within various industry scenarios.\r\n3. Application Evaluation & Security\r\nDiscuss evaluating the quality of generated content (e.g., hallucination detection), optimization of prompt engineering, and privacy protection mechanisms at the application level.","本軌聚焦於開源模型在取得生成內容後的應用場景與系統整合。我們歡迎分享如何將 AI 能力轉化為實際工具，解決真實世界問題的實戰經驗。主題包括但不限於：\r\n\r\n1. 檢索增強生成與系統整合\r\n分享 RAG（Retrieval-Augmented Generation）架構的實作、向量資料庫的應用，以及如何將 LLM 整合進現有的軟體工作流。\r\n2. AI 代理人與自動化流程\r\n探討如何利用開源模型構建具備任務規劃與執行能力的 AI Agents，以及在不同產業場景中的自動化實踐。\r\n3. 應用層的評估與安全\r\n討論如何評估生成內容的品質（如 Hallucination 檢測）、提示詞工程（Prompt Engineering）的優化，以及應用端的隱私保護機制。",{"2026-08-09":241,"2026-08-08":535},[242,274,297,325,345,365,387,409,432,453,474,493,515],{"id":243,"room":244,"start":246,"end":247,"language":248,"track":249,"speakers":251,"zh":264,"en":268,"tags":271,"uri":273},"97QGUT",{"en":245,"zh-hant":34},"AU","2026-08-09T15:10:00+08:00","2026-08-09T15:25:00+08:00","Mandarin",{"id":233,"name":250},{"en":235,"zh-hant":236},[252,259],{"id":253,"avatar":254,"zh":255,"en":258},"JEVXQA","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FJEVXQA_Gnt6P4q.webp",{"name":256,"bio":257},"廖庭暘","來自蘭陽平原的小小工程師，目前任職於永豐金，對前後端開發都有些經驗，喜歡腦動大開做一些看起來很沒用，實際上也沒什麼用，但很有趣的事情",{"name":256,"bio":257},{"id":260,"avatar":17,"zh":261,"en":263},"UE9HJ3",{"name":262,"bio":34},"張琪鈺",{"name":262,"bio":34},{"title":265,"describe":266,"type":267},"異議喵！你的冷知識來源不足：用 AI Agent 打造冷知識審判與卡牌對戰系統","曾幾何時，你有沒有想過「畫大餅」的由來可追溯到三國時期？魏國盧毓曾以「名如畫地作餅，不可啖也」比喻空有名聲、不能實用。原來一句職場吐槽，也藏著意想不到的冷知識。\r\n\r\n在資訊爆炸的時代，碎片化知識往往轉身即忘。為了讓學習與記憶變得更有趣，我們開發了開源趣味專案——逆轉喵判：一款結合 AI Agent、冷知識審判、卡牌對戰與桌面虛擬萌寵的智慧互動系統。\r\n\r\n使用者在日常與 Agent 互動時，系統會根據對話補上一則相關冷知識，並延伸小問題；答對後可獲得貓飼料，用來餵養桌面貓，提升牠的飽食度與好感度。隨著好感度變化，貓貓會解鎖不同外觀、動作與互動反應，讓碎片知識透過養成回饋被重新記住。\r\n\r\n為避免冷知識淪為隨機產生的有趣廢話，逆轉喵判以工程化方法建立評分流程，透過來源查證、語意比對與另一個 LLM 裁判，從冷度、可信度、關聯度、驚奇度、趣味度與可傳播度建立六邊形評分，將冷知識轉化為可收藏、可出戰的「知識喵牌」。\r\n\r\n玩家可帶著日常獲得的知識喵牌，透過另一套對戰系統，與未知挑戰者展開冷知識決鬥；桌面貓也會成為戰鬥夥伴，牠的飽食度、好感度與心情將影響對戰中的分數權重、技能觸發率與情境加成。本場分享將拆解 Prompt Engineering、Skill 設計、幻覺降低、LLM 裁判與遊戲化對戰機制。","Talk",{"title":269,"describe":270,"type":267},"Meowjection! — An AI-powered trivia court where cats judge, cards battle, and facts fight back.","Have you ever wondered where the phrase “drawing a big pie” comes from? Its origin can be traced back to the Three Kingdoms period, when Lu Yu of the Wei state used the phrase “a name is like drawing a cake on the ground — it cannot be eaten” to describe something that sounds impressive but has no practical value. In other words, even a casual workplace complaint may hide an unexpected piece of trivia.\r\n\r\nIn an age of information overload, fragmented knowledge is often forgotten almost instantly. To make learning and memory more engaging, we created an open-source playful project: Meowjection! — an intelligent interactive system that combines AI Agents, trivia judgment, card battles, and a desktop virtual pet.\r\n\r\nDuring everyday interactions with the Agent, the system provides not only the original response, but also a contextually relevant trivia fact and a follow-up question. When users answer correctly, they earn cat food to feed their desktop cat, improving its fullness and affection levels. As affection increases, the cat unlocks different appearances, animations, and interactive reactions, turning fragmented knowledge into a memorable pet-raising experience.\r\n\r\nTo prevent trivia from becoming random “interesting nonsense,” Meowjection! introduces an engineering-driven evaluation pipeline. Through source verification, semantic comparison, and a separate LLM judge, each trivia fact is scored across six dimensions: Novelty, Factuality, Relevance, Surprise, Interestingness, and Shareability. The result is a hexagonal rating system that transforms trivia into collectible and playable Knowledge Meow Cards.\r\n\r\nPlayers can bring the Knowledge Meow Cards they earn from daily interactions into trivia battles against unknown challengers. The desktop cat also becomes a battle companion: its fullness, affection, and mood influence scoring weights, skill trigger rates, and contextual bonuses during battles. In this talk, we will break down the implementation behind Prompt Engineering, Skill design, hallucination reduction, LLM judging, and gamified battle mechanics.",[272,248],"Elementary","https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002F97QGUT",{"id":275,"room":276,"start":247,"end":277,"language":248,"track":278,"speakers":280,"zh":288,"en":291,"tags":294,"uri":296},"A7LL8G",{"en":245,"zh-hant":34},"2026-08-09T15:40:00+08:00",{"id":233,"name":279},{"en":235,"zh-hant":236},[281],{"id":282,"avatar":283,"zh":284,"en":287},"TAY83U","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FTAY83U_76mLza9.webp",{"name":285,"bio":286},"Mohuhu開發團隊","我們是一群來自金融、法律、零售、科技工程的開發者，因共同進修 AI 數據學習而集結。\r\n這份跨領域的交會，催生了我們打造「企業資訊模糊搜尋系統」的共同理念。我們致力於將複雜的 RAG 技術與多策略檢索架構整合，解決台灣在地化搜尋中常見的名稱錯置與語意斷層。對我們而言，開源不只是技術分享，更是一種實踐「資訊易得性」的方式。我們希望能消弭專業領域的資訊門檻，讓高資安要求的企業與一般使用者，都能透過這套系統，在安全的前提下實現精準、直覺的情報檢索。",{"name":285,"bio":286},{"title":289,"describe":290,"type":267},"RAG 落地實踐：用開源 LLM 打造高資安、零門檻的台灣公司情報搜尋系統","RAG（檢索增強生成）在真實生產環境的落地，常受限於企業資安紅線與硬體資源。本分享以 Mohuhu 平台為例，探討如何利用開源 LLM 與系統整合技術，解決台灣上市公司資料中複雜的語意關聯與搜尋容錯問題。\r\n\r\n我們將解析如何將 AI 能力拆解並注入系統環節：\r\n\r\n- LLM 驅動索引強化：利用 Google Gemini 作為知識 Agent，在入庫階段自動產出非結構化別名（如「護國神山」、「2330」），從根本解決向量搜尋在特定領域的語意缺失。\r\n\r\n- 四策略融合檢索（Hybrid RAG）：本系統核心為「加權評分引擎」，將檢索拆解為四個維度並合計信心分數：\r\n1. 精準比對：確保代號與統編之絕對準確。\r\n2. 中文模糊搜尋：處理名稱錯置與冗餘詞。\r\n3. 注音\u002F拼音容錯：解決輸入法未切換（如 vm6vm42j\u002F）之痛點。\r\n4. RAG 向量語意：整合本地 Ollama (bge-m3) 與 pgvector 處理深層語意。\r\n\r\n- 高資安環境部署取捨：針對離線地端場景，提出「AI 預處理、地端輕量化檢索」架構。透過 PyInstaller 封裝，讓企業在完全離線下仍能享受 LLM 強化後的體驗。\r\n\r\n- 自動化工作流：利用 OpenClaw 與 Telegram Bot 監控從爬蟲到 Embedding 的 ETL 管線，並實作失敗自動回補機制。\r\n\r\n聽眾獲益\r\n1. 混合搜尋實作：四路並行加權架構與權重調校細節。\r\n2. RAG 實戰策略：利用 LLM 預處理提升特定領域檢索召回率（Recall）。\r\n3. 工程設計模式：在資安、硬體限制與 AI 效能間取得平衡的落地經驗。",{"title":292,"describe":293,"type":267},"Secure RAG: Bridging LLMs and Local Deployment for Corporate Intelligence Search","Below is the English abstract for your submission, refined to reflect your technical depth and strategic engineering choices:\r\n\r\nAbstract\r\nThe real-world deployment of RAG (Retrieval-Augmented Generation) often faces challenges from corporate security policies and hardware constraints. This session uses the Mohuhu platform as a case study to explore how open-source LLMs and system integration techniques solve complex semantic relationships and search fault-tolerance issues for Taiwan’s listed company data.\r\n\r\nWe will deconstruct how AI capabilities are injected into different system layers:\r\n\r\nLLM-Driven Index Enrichment: Using Google Gemini as a knowledge agent to automatically generate unstructured aliases (e.g., \"護國神山,\" \"2330\") during the indexing stage, fundamentally addressing semantic gaps in vector search for domain-specific data.\r\n\r\nFour-Strategy Hybrid RAG: The system’s core is a weighted scoring engine that aggregates confidence scores across four dimensions:\r\n\r\nExact Match: Ensuring absolute accuracy for stock codes and tax IDs.\r\n\r\nChinese Fuzzy Search: Handling character misplacements and redundant terms.\r\n\r\nPhonetic\u002FBopomofo Fault-Tolerance: Solving search pain points caused by incorrect input methods (e.g., typing vm6vm42j\u002F).\r\n\r\nSemantic Vector Search: Integrating local Ollama (bge-m3) and pgvector to process deep semantic connections.\r\n\r\nDeployment Trade-offs for High-Security Environments: Proposing an \"AI Pre-processing + Lightweight Local Retrieval\" architecture for offline scenarios. Using PyInstaller for encapsulation, allowing enterprises to enjoy LLM-enhanced experiences in completely offline environments.\r\n\r\nAutomated LLM Workflows: Utilizing OpenClaw and Telegram Bots to monitor the ETL pipeline—from crawling to embedding—and implementing automated retry mechanisms for failures.\r\n\r\nKey Takeaways\r\nHybrid Search Implementation: Detailed design of a four-way parallel weighted architecture and weight-tuning strategies.\r\n\r\nRAG Practical Strategies: Improving retrieval recall in specific domains using LLM-based data pre-processing.\r\n\r\nEngineering Design Patterns: Practical experience in balancing data security, hardware limitations, and AI performance during deployment.",[295,248],"Intermediate","https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FA7LL8G",{"id":298,"room":299,"start":300,"end":301,"language":248,"track":302,"speakers":304,"zh":317,"en":320,"tags":323,"uri":324},"BJ78VU",{"en":245,"zh-hant":34},"2026-08-09T14:00:00+08:00","2026-08-09T14:30:00+08:00",{"id":233,"name":303},{"en":235,"zh-hant":236},[305,312],{"id":306,"avatar":307,"zh":308,"en":311},"YYXZZY","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FYYXZZY_fRNHwoy.jpg",{"name":309,"bio":310},"Samson","現任國泰金控助理架構師，擁有 9 年以上系統架構與後端開發經驗，橫跨金融、政府、醫療與車用等多個產業領域。目前職責著重於企業 AI 賦能與架構治理，推動內部 AI 導入策略與工程實踐。\r\n\r\n長期關注開源技術在垂直領域的落地應用，熟悉雲端部署與分散式系統設計。\r\n\r\n本次議程以自行實作的 AlphaCouncil 開源專案為主軸，分享在金融場景中導入 Google ADK 與開源 LLM（Gemma 4）構建多代理人系統的工程實踐。\r\n\r\n---\r\nAssistant Architect at Cathay Financial Holdings with 9+ years of system architecture and backend development experience across financial services, government, healthcare, and automotive domains. Currently focused on enterprise AI adoption and architecture governance.\r\n\r\nA practitioner interested in applying open-source technology to real-world vertical domains, with background in cloud deployment and distributed systems design.\r\n\r\nThis talk is grounded in hands-on experience building AlphaCouncil: an open-source multi-agent Taiwan stock analysis framework integrating Google ADK with locally-deployed open-source LLMs (Gemma 4).",{"name":309,"bio":310},{"id":313,"avatar":17,"zh":314,"en":316},"SG8HJL",{"name":315,"bio":34},"陳庭宇",{"name":315,"bio":34},{"title":318,"describe":319,"type":267},"AlphaCouncil：用 Google ADK ＋ 開源模型打造多代理人辯論式台股分析系統——資料在地化 × 模型在地化","GitHub 上的 ai-hedge-fund（⭐ 52k）與 TradingAgents（⭐ 50k）讓「用 LLM 分析股票」的概念引爆開源社群——但兩者的資料源與語境都以美股為主，難以直接套用於台灣市場。\r\n\r\n本議程以 AlphaCouncil 為例，分享如何以 Google ADK（Agent Development Kit）的 SequentialAgent、ParallelAgent、LoopAgent 三種原生編排原語，融合上述兩個開源框架的設計精髓，打造一套以台灣股市為第一公民的在地化多代理人分析系統。在地化發生在兩個層次：\r\n\r\n資料層：新聞改接台灣繁體中文財經媒體（Yahoo 財經、鉅亨網、經濟日報等）；籌碼面整合 TWSE OpenAPI 的融資融券與三大法人資料（外資、投信、自營商），完全免費、無需 API 金鑰；基本面納入殖利率、月營收、本淨比等台股特有指標。\r\n\r\n模型層：透過 Ollama 在本機執行開源模型（Gemma 4、Llama 3、Qwen 等），讓台股分析資料無須離開本機，符合金融場景的資料隱私需求，同時消除商業 API 費用。Gemma 4 與 Google ADK 同屬 Google 生態系，在繁體中文指令遵循與多步驟推理上表現亮眼，是本系統首選開源底座；商業 API（Gemini、Claude、GPT）則作為可選替換方案。\r\n\r\n系統架構五個階段：四位分析師並行蒐集資料、13 位投資大師（Buffett、Graham、Munger 等）以台股視角評述、看多\u002F看空研究員 LoopAgent 辯論、交易員整合提案，最後由三方風險辯論後投資組合管理人裁決。\r\n\r\n本議程聚焦三項工程重點：Gemma 4 + ADK 的整合方式、TWSE OpenAPI 免費資料的接入實作，以及如何讓開源模型以繁體中文輸出具台股語境的人格分析報告。無論你是想用開源模型打造垂直領域 Agent，還是想把熱門英文開源專案在地化為繁體中文版本，本議程將提供一個可拆解、可復用的參考實作。",{"title":321,"describe":322,"type":267},"AlphaCouncil: Multi-Agent Debate-Driven Taiwan Stock Analysis with Google ADK + Open-Source LLMs — Localizing Both Data and Models","Open-source projects like ai-hedge-fund (⭐ 52k stars) and TradingAgents (⭐ 50k stars) have proven the community's appetite for LLM-powered financial analysis. But both projects are US-centric—their data sources, news feeds, and financial metrics are built around American markets and don't transfer cleanly to Taiwan.\r\n\r\nThis talk introduces AlphaCouncil, a Taiwan-first multi-agent stock analysis framework built natively on Google ADK, combining investor persona agents (inspired by ai-hedge-fund) with debate-driven decision-making (inspired by TradingAgents). Localization happens at two levels:\r\n\r\nData layer — replacing US-centric sources with Taiwan equivalents:\r\n\r\nNews: Traditional Chinese financial media (Yahoo Finance TW, 鉅亨網, 經濟日報, etc.)\r\nInstitutional flows: TWSE OpenAPI for 三大法人 (foreign investors, investment trusts, dealers) and margin trading (融資融券)—free, no API key required\r\nFundamental metrics: yield (殖利率), monthly revenue (月營收), P\u002FB ratio—Taiwan-specific KPIs absent from US-oriented feeds\r\nModel layer — running open-source LLMs locally via Ollama (Gemma 4, Llama 3, Qwen, etc.):\r\n\r\nAll 13 investor persona reports generated in Traditional Chinese with Taiwan market context\r\nFinancial data never leaves the local machine—addressing privacy requirements in financial use cases\r\nGemma 4 pairs naturally with Google ADK (same ecosystem), delivering strong Traditional Chinese instruction-following and multi-step reasoning out of the box\r\nNo commercial API costs; commercial APIs (Gemini, Claude, GPT) remain an optional swap-in\r\nThe pipeline runs in five stages—analyst team, masters panel, research debate, trader, and risk debate—orchestrated with SequentialAgent, ParallelAgent, and LoopAgent primitives to ensure a deterministic flow without LLM dynamic routing.\r\n\r\nKey engineering takeaways:\r\n\r\nIntegrating Gemma 4 via Ollama into a Google ADK multi-agent pipeline\r\nIntegrating TWSE's free OpenAPI into an ADK tool layer\r\nPrompt engineering for Traditional Chinese persona-constrained output with Taiwan market context",[295,248],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FBJ78VU",{"id":326,"room":327,"start":277,"end":328,"language":248,"track":329,"speakers":331,"zh":339,"en":342,"tags":343,"uri":344},"H3VJLX",{"en":245,"zh-hant":34},"2026-08-09T15:55:00+08:00",{"id":233,"name":330},{"en":235,"zh-hant":236},[332],{"id":333,"avatar":334,"zh":335,"en":338},"BMWNNY","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FBMWNNY_xVbNEKG.webp",{"name":336,"bio":337},"Jarvis Chen","曾任軟體開發工程師，目前擔任 DevOps 工程師，專注於系統現代化與自動化部署相關工作。身為一位熱衷研究新技術的工程師，我目前的重心在於 CNCF 生態系中的雲原生技術實務落地，以及 AI Agent 的開發與創新應用。\r\n\r\n我非常享受深入研究最新技術趨勢，並將這些經驗轉化為內部技術分享，協助團隊建立更成熟的 DevOps 文化。我也期待在快速變化的技術環境中，持續迎接新的挑戰與成長。",{"name":336,"bio":337},{"title":340,"describe":341,"type":267},"打開就能工作的 AI Agent：Aileron 的 Workspace 設計實踐","AI Agent 已經不只是一個會寫程式的工具。從 Claude Code、Codex、Gemini 到OpenCode，不同 Agent 能力正在快速演進；但對企業來說，真正困難的往往不是模型夠不夠強，而是如何讓 Agent 在符合內部規範、權限治理與基礎設施要求的前提下，被團隊穩定採用。\r\n\r\n實際導入時，使用者常常還是得自己處理 system prompt、MCP、skills、slash commands、工具安裝、SDK、CLI、專案起始檔案與執行環境。這些設定散落在個人經驗、團隊文件與本機環境裡，讓 AI Agent 很難從工程師個人工具，變成企業可管理、可複製、可擴展的工作方式。\r\n\r\n本次將介紹 Aileron 開源平台, Aileron 的目標不是只讓 AI 更會寫 code，而是讓組織可以用標準化的方式提供 Agent 工作區，讓使用者打開 workspace 就能開始工作。\r\n\r\n  為了讓這件事成立，Aileron 聚焦在三個關鍵設計：\r\n\r\n  1. 讓 Agent 更容易被企業採用\r\n     透過集中式 Marketplace、模板、權限與標準化能力，將 system prompt、MCP、skills、slash commands、起始檔案與工具需求包裝成可分發、可選擇、可治理的工作區能力。企業不需要依賴每個人手動拼裝 Agent 設定，而是可以用平台化方式管理不同場景的 Agent 使用方式。\r\n\r\n  2. 讓使用者更容易開始工作\r\n     Aileron 將 Chat、檔案管理、Git、Web Terminal、OpenSpec 與常用 CLI \u002F SDK 整合在同一個 workspace 中，並透過 base image 預先準備執行環境。使用者不需要先安裝一堆工具、處理權限或設定本機環境，就能直接進入可工作的Agent workspace。\r\n\r\n  3. 與 Kubernetes 結合，支撐正式環境部署\r\n     Aileron 透過容器化 runtime 與 workspace-operator，將每個 Agent workspace 轉換成 Kubernetes 中可動態佈建、隔離、重現與管理的執行環境。這讓 Agent 不只是換 prompt，而是真的進入對應任務的工作場景，也讓企業能用既有的 K8s來承載 Agent 工作負載。\r\n\r\n  本次分享重點包括：\r\n  1. 導入 AI Agent 時，從個人工具走向平台化工作區會遇到哪些門檻\r\n  2. Aileron 如何用 Marketplace \u002F 模板系統，讓 Agent 能力變成可分發與重用的 workspace capability\r\n  3. base image、容器化與預裝工具，如何降低使用者開始工作的成本\r\n  4. workspace-operator 如何結合 Kubernetes，動態建立可隔離、可重現、可管理的 Agent workspace\r\n  5. 使用 OpenSpec 開發 Aileron 的歷程與實務經驗",{"title":340,"describe":341,"type":267},[295,248],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FH3VJLX",{"id":346,"room":347,"start":348,"end":246,"language":248,"track":349,"speakers":351,"zh":359,"en":362,"tags":363,"uri":364},"M9AKQY",{"en":245,"zh-hant":34},"2026-08-09T14:55:00+08:00",{"id":233,"name":350},{"en":235,"zh-hant":236},[352],{"id":353,"avatar":354,"zh":355,"en":358},"QMJRYB","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FQMJRYB_Y4ngkKF.webp",{"name":356,"bio":357},"Justin Lee （阿修）","UX 和 iOS 背景的開發者，致力於透過對人的觀察和技術實踐提供最佳的使用體驗。近兩年的重心，在研究如何透過 AI 提升軟體團隊開發效率。",{"name":356,"bio":357},{"title":360,"describe":361,"type":267},"自己的 AI agent dashboard 自己刻——ccxray 實作筆記","你每天用 Claude Code 寫程式，但真的知道每輪 turn 燒了多少 token、context window 還剩幾趴、cache 有命中嗎？辛苦寫的 skill 到底被呼叫了多少次？\r\nccxray 是一支透明 HTTP proxy + 即時 web dashboard，夾在 Agent 與 API 之間。把所有的 request 和 response 都 log 下來，並提供清楚的視覺化。\r\n本場演講將揭露本專案的開發過程。\r\nhttps:\u002F\u002Fgithub.com\u002Flis186\u002Fccxray",{"title":360,"describe":361,"type":267},[295,248],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FM9AKQY",{"id":366,"room":367,"start":368,"end":369,"language":370,"track":371,"speakers":373,"zh":381,"en":384,"tags":385,"uri":386},"NJSSSE",{"en":245,"zh-hant":34},"2026-08-09T11:45:00+08:00","2026-08-09T12:15:00+08:00","English",{"id":233,"name":372},{"en":235,"zh-hant":236},[374],{"id":375,"avatar":376,"zh":377,"en":380},"38ZMFE","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002F38ZMFE_sXGvYc6.png",{"name":378,"bio":379},"Sasha Denisov","Sasha is CTO at Brainform.ai with over 20 years of experience architecting scalable enterprise systems. With a strong engineering background, his expertise spans frontend, backend, cloud infrastructure, mobile development, and AI — from cloud-based generative AI to on-device solutions. He specializes in building robust, production-ready products using a variety of technologies and frameworks. Sasha has delivered solutions across fintech, digital media, and entertainment. He is a Google Developer Expert for Cloud, AI, Firebase, Flutter, and Dart, co-organizes the Flutter Berlin Community, and is a recognized international speaker and writer, having presented at 30+ conferences worldwide.",{"name":378,"bio":379},{"title":382,"describe":383,"type":267},"Hybrid AI: The Next Pattern for AI-Powered Apps","Most applications treat AI as a cloud-only feature — send a request, wait for a response, pay per token. Open models like Gemma, Llama, DeepSeek, and Phi freed developers from proprietary APIs, but not from costs: you still need to host them somewhere — GPU servers, infrastructure, per-request pricing. You can run models directly on the user's device — zero inference costs, offline access, full data privacy. But there's a trade-off: models small enough to run on a phone or in a browser can't handle every task.\r\nHybrid AI is the answer to this dilemma. Combine cloud and on-device models in a single application: simple and privacy-sensitive tasks run on-device, complex reasoning and multimodal workloads go to the cloud. The problem is that you end up maintaining two completely different inference stacks: different runtimes (TFLite, LiteRT-LM, llama.cpp), different model formats (TFLite flatbuffers vs GGUF), different quantization strategies, and different streaming APIs — all within one app.\r\nIn this talk, I'll show how to solve this problem with Genkit — an open-source AI framework from Google with an open plugin system. Each plugin adapts a specific runtime or model format to a unified pipeline: genkit_flutter_gemma for TFLite\u002FLiteRT models, genkit_llamadart for GGUF. Engine-specific details are hidden behind a single API for flows, structured output, tool calling, and agentic workflows. Need a new runtime? Write a plugin. New model format? Same story. On-device inference runs across Android, iOS, macOS, Windows, Linux, and Web — switching between cloud and local execution is a one-line model reference change.\r\nWe'll explore hybrid patterns in practice: how to route between on-device and cloud based on model capabilities, connectivity, and task complexity. We'll cover the real trade-offs — quantization impact on output quality, memory constraints across platforms, cold start latency, and when hybrid actually makes sense versus pure cloud or pure edge.\r\nOpen-source models made on-device AI possible. Open-source tooling makes hybrid AI extensible.",{"title":382,"describe":383,"type":267},[295,370],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FNJSSSE",{"id":388,"room":389,"start":390,"end":300,"language":248,"track":391,"speakers":393,"zh":401,"en":404,"tags":407,"uri":408},"NLCRV9",{"en":245,"zh-hant":34},"2026-08-09T13:30:00+08:00",{"id":233,"name":392},{"en":235,"zh-hant":236},[394],{"id":395,"avatar":396,"zh":397,"en":400},"RFCLRX","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FRFCLRX_ZHBCOjH.jpg",{"name":398,"bio":399},"徐方繹 Fngi Shiu","Fngi 專注於 AI 安全治理與 LLM 紅隊測試。曾任多家台灣機構 CISO，同時擔任 GDG Taipei Organizer 及台灣金融研訓院 AI 安全講師。擁有超過十年資安與全端工程經驗。",{"name":398,"bio":399},{"title":402,"describe":403,"type":267},"你的 LLM App 上線第一天就該做的三件事（但你可能一件都沒做）","你花了一個週末串好 RAG、接上 MCP、部署了一個會自動回 Issue 的 LLM Agent——然後你就直接上線了。沒有 input validation、沒有權限控制、System Prompt 裸奔。別擔心，大家都這樣，而且不需要資安背景也能跟上。今天我們直接開 terminal，打給你看。\r\n這場議程會告訴你上線前該做好的三件事：一、管好你的 System Prompt——我們會現場用 Prompt Injection 把它整段偷出來，然後示範怎麼用 NemoClaw Guardrail 擋住。二、清洗你的 RAG 資料來源——我們會在知識庫文件裡埋 Indirect Prompt Injection，讓你的 Agent 做出它不該做的事，然後示範 content sanitization 怎麼實作。三、限制你的 Agent 權限——我們會讓一個有過多權限的 Agent 自己刪掉自己的資料，然後用 least privilege 原則加上 tool call 權限控制修好它。\r\n每一件事都是「現場用 OpenClaw 打給你看，再用 NemoClaw 修給你看」，全部開源，git clone 就能跑。你會帶走一份可以直接丟進 repo 的安全 checklist。",{"title":405,"describe":406,"type":267},"Three Things Your LLM App Should Have Done on Day One (But Probably Didn't)","You spent a weekend wiring up RAG, connecting MCP, and deploying an LLM Agent that auto-replies to GitHub Issues — then shipped it straight to production. No input validation, no permission controls, system prompt wide open. Don't worry, everyone does it. No security background needed to follow along — we'll open a terminal and show you live.\r\nThis talk covers three things you should do before going live: First, protect your system prompt — we'll steal it with prompt injection, then block the attack with NemoClaw Guardrail. Second, sanitize your RAG data sources — we'll plant an indirect prompt injection in a knowledge base document and make your Agent do things it shouldn't, then show how content sanitization works. Third, limit your Agent's permissions — we'll let an over-privileged Agent delete its own data, then fix it with least-privilege principles and tool call permission controls.\r\nEvery attack uses OpenClaw, every fix uses NemoClaw — all open source, git clone and go. You'll leave with a security checklist ready to drop into your repo.",[295,248],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FNLCRV9",{"id":410,"room":411,"start":412,"end":413,"language":248,"track":414,"speakers":416,"zh":424,"en":427,"tags":430,"uri":431},"NUPSVF",{"en":245,"zh-hant":34},"2026-08-09T10:05:00+08:00","2026-08-09T10:35:00+08:00",{"id":233,"name":415},{"en":235,"zh-hant":236},[417],{"id":418,"avatar":419,"zh":420,"en":423},"SUVVXB","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FSUVVXB_O9vuwAP.webp",{"name":421,"bio":422},"Kent Huang","Software Engineer @ Recce 與 AI 搏鬥中，嘗試不要被淹沒在 AI 洪流的工程師一枚",{"name":421,"bio":422},{"title":425,"describe":426,"type":267},"AI 也要期中考？ The Story Behind Building a Benchmark for Agent Workflow Development","要考期中考？AI 沒過也會有這天。開發 Agent Workflow 時要怎麼分辨。表現變好是 Model 的功勞，還是好的 Workflow 帶來的功勞？這時就需要一套好的驗證方法：期中考！但是道高一尺，魔高一丈。你想得到的，AI 也想得到。上網作弊、偷看答案，只有你想不到，沒有 AI 做不到。本節的故事背景，是我們在開發開源 Agent Workflow 時，設計內部 benchmark 所碰到的各種大小事。\r\n\r\nHow do you evaluate the performance of an agent workflow? When things get better, is it the model doing the work, or the workflow itself? A good benchmark is like a midterm exam. It tells you who actually studied.\r\nBut AI is smarter than you expect. It will cheat by searching the web, peek at other answers, and find every loophole you forgot to close. AI always finds a way to surprise you.\r\nIn this session, we'll share the story behind building a benchmark for an open-source agent workflow. Every twist, every workaround, and every time the AI quietly outsmarted our test design.",{"title":428,"describe":429,"type":267},"The Story Behind Building a Benchmark for Agent Workflow Development","How do you evaluate the performance of an agent workflow? When things get better, is it the model doing the work, or the workflow itself? A good benchmark is like a midterm exam. It tells you who actually studied.\r\nBut AI is smarter than you expect. It will cheat by searching the web, peek at other answers, and find every loophole you forgot to close. AI always finds a way to surprise you.\r\nIn this session, we'll share the story behind building a benchmark for an open-source agent workflow. Every twist, every workaround, and every time the AI quietly outsmarted our test design.",[272,248],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FNUPSVF",{"id":433,"room":434,"start":435,"end":436,"language":370,"track":437,"speakers":439,"zh":447,"en":450,"tags":451,"uri":452},"QALAL8",{"en":245,"zh-hant":34},"2026-08-09T10:45:00+08:00","2026-08-09T11:15:00+08:00",{"id":233,"name":438},{"en":235,"zh-hant":236},[440],{"id":441,"avatar":442,"zh":443,"en":446},"JUMDFL","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FJUMDFL_9j50avB.webp",{"name":444,"bio":445},"Teo Richie","Richie is a Lead Experience Engineer based in Kuala Lumpur, Malaysia, with five years of experience building software products. He works at the intersection of backend systems and user-facing product, with a focus on making complex infrastructure feel simple to use. His recent work includes Alfred, a multi-agent orchestration platform. This project pushed him deep into the practical challenges of running AI systems in production, which is what this talk is about.",{"name":444,"bio":445},{"title":448,"describe":449,"type":267},"Wiring AI Agents to the Real World: The Integration Layer Nobody Talks About","Everyone talks about prompts, models, and RAG. Nobody talks about the 80% of work that actually gets AI agents running in production. \r\n\r\nThis talk is about the integration layer. The OAuth flows, channel routing, credential management, scheduling infrastructure, and observability tooling that separates a working demo from a system your users can rely on every day. \r\n\r\nI'll draw from a system I've participated in building: Alfred, a multi-agent orchestration platform. We'll start with integrations. An agent is only as useful as what it can reach. Connecting to Gmail, Slack, Google Calendar, Microsoft 365, or Telegram sounds straightforward until you're dealing with token expiry, scope changes, and multiple users with different credentials. We'll look at how to build a credential layer that handles all of this cleanly, so agents can act on behalf of users without the whole thing falling apart when a token rotates. \r\n\r\nFrom there we'll talk about routing. In a real deployment, messages come in from multiple channels simultaneously. Telegram, Slack, and web chat all have different UX contracts and different audiences. The answer isn't to write channel-aware agent code. It's to build a routing layer that maps channels to agents declaratively, so you can change behavior without touching your agent logic. \r\n\r\nWe'll also cover scheduling. Agents are far more powerful when they run on a schedule rather than waiting to be asked. We'll look at how to treat cron jobs as first-class agent invocations, with full run history and cost tracking so you know exactly what every scheduled run is doing and what it's spending. \r\n\r\nFinally we'll talk about observability. If you can't see what your agent is doing in real time, and you can't track what it's costing you, you can't trust it in production. We'll look at patterns for tracking subagent spawns, monitoring delegation health, and surfacing live activity so problems surface before your users notice them. \r\n\r\nBy the end of this talk you'll have a clear mental model of the integration layer and a set of concrete, framework-agnostic patterns you can take back to whatever stack you're building on.",{"title":448,"describe":449,"type":267},[295,370],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FQALAL8",{"id":454,"room":455,"start":456,"end":412,"language":248,"track":457,"speakers":459,"zh":467,"en":470,"tags":472,"uri":473},"SSN9Y7",{"en":245,"zh-hant":34},"2026-08-09T09:35:00+08:00",{"id":233,"name":458},{"en":235,"zh-hant":236},[460],{"id":461,"avatar":462,"zh":463,"en":466},"H9PJPV","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002Foie_ZBmmBLx7r7zm_QNFhfvF.jpg",{"name":464,"bio":465},"Che Chia Chang","Che-Chia Chang 是一名專注於後端開發、開發維運、容器化應用及 Kubernetes 開發與管理的技術專家，同時也是 Microsoft 最有價值專業人士（MVP）。\r\n\r\n活躍於台灣技術社群，經常在 CNTUG、DevOps Taipei、GDG Taipei、Golang Taipei Meetup 等社群分享 DevOps、SRE、Kubernetes 及雲端運算相關技術。致力於推動開發與維運的最佳實踐，並熱衷於研究與應用最新的雲端與 AI 技術。\r\n\r\n個人部落格：https:\u002F\u002Fchechia.net\r\n\r\nChe-Chia Chang is a technology expert specializing in backend development, DevOps, site reliability engineering (SRE), containerized applications, and Kubernetes development and management. He is also recognized as a Microsoft Most Valuable Professional (MVP).\r\n\r\nActively engaged in the Taiwanese tech community, he frequently shares insights on DevOps, SRE, Kubernetes, and cloud computing at CNTUG, DevOps Taipei, GDG Taipei, and Golang Taipei Meetup. Passionate about promoting best practices in development and operations, he continuously explores and applies the latest advancements in cloud and AI technologies.\r\n\r\nhttps:\u002F\u002Fchechia.net",{"name":464,"bio":465},{"title":468,"describe":469,"type":267},"Observe and evaluate LLM Coding Agents","在導入 LLM Coding Agent 到日常開發後，很多團隊會遇到問題：品質不穩、風險難估、模型升級缺少客觀依據。本分享會從實務流程出發，介紹如何觀測 Agent 行為、把評估流程自動化，並建立可持續迭代的 decision system。\r\n\r\n1. 為什麼 LLM Coding Agent 需要 O11y 與 Evaluation\r\n1. 從 trace 開始：觀測 agent 任務、工具調用與失敗模式\r\n1. Observability != Decision System：看得到不代表能決策\r\n1. LLM-as-a-judge 在 coding 任務中的價值與限制\r\n1. 從 daily coding logs 抽取 dataset\r\n1. 建立 regression evaluation pipeline 與 quality gate\r\n1. 用量化結果比較不同模型與 agent framework\r\n1. 把模型升級與框架切換變成可驗證工程流程",{"title":468,"describe":471,"type":267},"LLM coding agents are changing software delivery, but most teams still lack a reliable way to measure quality and risk before deployment. This talk shows how to move from raw observability to practical decision-making by combining tracing, dataset extraction, LLM-as-a-judge, and regression evaluation, so model and framework upgrades become testable engineering decisions instead of guesswork.",[295,248],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FSSN9Y7",{"id":475,"room":476,"start":436,"end":368,"language":370,"track":477,"speakers":479,"zh":487,"en":490,"tags":491,"uri":492},"W9PG8F",{"en":245,"zh-hant":34},{"id":233,"name":478},{"en":235,"zh-hant":236},[480],{"id":481,"avatar":482,"zh":483,"en":486},"8KG7ST","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002F8KG7ST_lBZJAd6.webp",{"name":484,"bio":485},"Bruce Momjian","Bruce Momjian is co-founder and core team member of the PostgreSQL Global Development Group, and has worked on PostgreSQL since 1996. He has been employed by EDB since 2006. He has spoken at many international open-source conferences and is the author of PostgreSQL: Introduction and Concepts, published by Addison-Wesley. Prior to his involvement with PostgreSQL, Bruce worked as a consultant, developing custom database applications for some of the world's largest law firms. As an academic, Bruce holds a Masters in Education, an honorary doctorate, was a high school computer science teacher, and lectures internationally.",{"name":484,"bio":485},{"title":488,"describe":489,"type":267},"Building an MCP Server Using Postgres","Large language models are good at generating text, but can't easily report discrete, dynamic, and always-accurate results. They also can't take external actions. The model context protocol (MCP) has become the standard way for generative AI models to access external data and take external actions. This talk explains the purpose of MCPs, how they are used, and shows examples of database and non-database MCP servers.",{"title":488,"describe":489,"type":267},[295,370],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FW9PG8F",{"id":494,"room":495,"start":496,"end":348,"language":370,"track":497,"speakers":499,"zh":507,"en":510,"tags":513,"uri":514},"WAKGQH",{"en":245,"zh-hant":34},"2026-08-09T14:40:00+08:00",{"id":233,"name":498},{"en":235,"zh-hant":236},[500],{"id":501,"avatar":502,"zh":503,"en":506},"YFWTUW","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FPXL_20210320_023758096.MP_ZOINVEy.jpg",{"name":504,"bio":505},"Amanda Lam","作為 Women Techmakers Hong Kong 大使及 ProductTank Hong Kong 活動召集人，過去 16 年 Amanda 每週也會共同主持其中一個最受歡迎的廣東話科技播客節目 - HKPUG Podcast《派樂派對》。日常方面，她以管理香港迪士尼樂園的數碼產品及平台來維持生計。 \r\n\r\nAs a Women Techmakers Hong Kong Ambassador and ProductTank Hong Kong Organizer, Amanda also co-hosts one of the most popular Cantonese tech podcasts, HKPUG Podcast for around 16 years. She manages digital products and platforms in Hong Kong Disneyland as her day job.",{"name":504,"bio":505},{"title":508,"describe":509,"type":267},"給 OpenClaw（龍蝦）控制你的 Home Assistant 智能家居，會發生甚麼事？","究竟讓 OpenClaw（龍蝦）利用 本地開放模型透過 Home Assistant 控制智能家居，會發生甚麼事？Amanda 會分享她的發現：究竟有甚麼更智能的自動化機會可以實踐？有甚麼方面不太可行？又發現了甚麼風險？\r\n\r\n這是 Amanda 在過往 Women Techmakers Hong Kong 國際婦女節活動、香港開源年會、OpenTechConf 及 COSCUP 開源人年會所做的 Home Assistant 系列分享的續篇。\r\n\r\n關鍵詞：#OpenClaw #LocalLLM #Gemma #Qwen #HomeAssistant #SmartHome #AgenticAI #AIagents #MCP",{"title":511,"describe":512,"type":267},"What happens when OpenClaw takes control to your Home Assistant smart home?","Amanda will discuss her discoveries to allow OpenClaw to control a Smart Home through Home Assistant via a local open LLM - what intelligent automation opportunities did it unlock, what didn't work well, and what risks were observed.\r\n\r\nThis is a sequel of the Home Assistant sharing series that Amanda previously shared at Women Techmakers Hong Kong IWD event, Hong Kong Open Source Conference, OpenTechConf and COSCUP Taipei.\r\n\r\nTags: #OpenClaw #LocalLLM #Gemma #Qwen #HomeAssistant #SmartHome #AgenticAI #AIagents #MCP",[295,370],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FWAKGQH",{"id":516,"room":517,"start":518,"end":390,"language":248,"track":519,"speakers":521,"zh":529,"en":532,"tags":533,"uri":534},"ZESBXN",{"en":245,"zh-hant":34},"2026-08-09T13:00:00+08:00",{"id":233,"name":520},{"en":235,"zh-hant":236},[522],{"id":523,"avatar":524,"zh":525,"en":528},"XTRQDX","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002Fme_linkedin_rwldHF1.jpeg",{"name":526,"bio":527},"Gavin Guo","Gavin Guo is a Linux kernel engineer at Igalia working on the scheduler subsystem (sched_ext \u002F LAVD) and AI-assisted kernel debugging tooling. Outside the kernel, he builds COCA Dashboard, an open-source MCP-native vocabulary-learning platform combining the Corpus of Contemporary American English with the FSRS-4.5 spaced-repetition algorithm. He has spoken at Linux Plumbers Conference 2025 and Open Source Summit Japan 2025, and previously presented kernel work at LPC and OSPM.",{"name":526,"bio":527},{"title":530,"describe":531,"type":267},"COCA MCP: Learning English While Chatting with an LLM","People who try to learn English as a second language usually quit their flashcard app within two weeks. The hard part isn't memorising definitions. It's that a new word only sticks after a dozen real-world encounters, and a flashcard never gives you that. We introduce the concept \"Ambient Learning\" — learning from natural conversation.\r\n\r\nCOCA MCP is an useful tool to suggest the vocabularies chat to an LLM. The server sits behind the Corpus of Contemporary American English — 60,000 words ranked by frequency — and exposes a small set of MCP tools. When a client like Claude is talking to a learner, it asks the server which words are due, and gets back a short list scheduled by FSRS-4.5. The model uses those words in its reply. It then tells the server which ones it actually used; the server records the exposure and reschedules.\r\n\r\nThe session walks through a modern English learning methodology on the running site at coca.gavinguo.cc — how to use MCP technology to improve the English ability.",{"title":530,"describe":531,"type":267},[272,248],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FZESBXN",[536],{"id":537,"room":538,"start":540,"end":541,"language":248,"track":542,"speakers":544,"zh":552,"en":556,"tags":557,"uri":558},"X7P83A",{"en":539,"zh-hant":34},"TR212","2026-08-08T14:30:00+08:00","2026-08-08T16:30:00+08:00",{"id":233,"name":543},{"en":235,"zh-hant":236},[545],{"id":546,"avatar":547,"zh":548,"en":551},"WJJQHU","https:\u002F\u002Fpretalx.coscup.org\u002Fmedia\u002Favatars\u002FWJJQHU_cwnzFj1.webp",{"name":549,"bio":550},"Tan Lean Sheng","Analog player in the digital world. Technologist and AI evangelist for greater good. Open source community contributor and maintainer for almost a decade.",{"name":549,"bio":550},{"title":553,"describe":554,"type":555},"迷你 AI 黑客松 (Mini AI Hackathon)：打造一個能做一件實事的 Agent","大部分 AI agent 的 demo 在台上很厲害，一碰到真實任務就沒用了。這場 2 小時的迷你 hackathon 要做的正好相反：一起做一個小小的、但真的能動的東西。\r\n我們會給一個明確的題目和一份起始素材（starter kit），讓你不用從零開始——現場跟著一起打造一個能從頭到尾完成任務的 AI agent。範圍抓小、把它做出來、現場 demo。\r\n不需要事前準備、也不需要 agent 經驗，帶著筆電和好奇心來就好。歡迎使用開源權重模型與開源工具。可以單人做，也可以現場組隊，會有 mentor 在場協助。\r\n流程上，我們會先說明題目與規則，大部分時間拿來動手做，最後以簡短的現場 demo 收尾。來做一個東西、認識其他開發者，看看一整個房間的人在兩小時內能生出什麼。\r\n關於題目細節、建議工具與 starter kit，我們會在活動前另行公布。","workshop\u002Fpanel",{"title":553,"describe":554,"type":555},[272,248],"https:\u002F\u002Fcoscup.org\u002F2026\u002Fsession\u002FX7P83A",{"2026-08-09":560,"2026-08-08":561},"#457b9d","#a8dadc",[],[564,569,573,577,580,583,586,590,594,599],{"id":565,"imageVertical":566,"imageHorizontal":567,"link":568,"weight":10},"QNAP-news","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1-HQ9oQMOngtqM3yL-1DBHRhzWbuyxgfE&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1aVhw014dwVLuxbNadE314lnl992FcjS_&&sz=w4000","https:\u002F\u002Fwww.qnap.com\u002Fgo\u002Fsolution\u002Fvirtualization",{"id":570,"imageVertical":571,"imageHorizontal":572,"link":80,"weight":174},"Cathay-news","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=10ndsUHILq9m_boaoilHTERyTXCsCBlSX&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=11_VlhFrCYcNOHML4z0jm6AmyL7MxNTfl&&sz=w4000",{"id":574,"imageVertical":575,"imageHorizontal":576,"link":122,"weight":174},"esunbank-news","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1aNURMNN83oIZHAtBzm2rUZODKVBO29dt&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=17OA0eu-N510ePhhDuiSuBV_4mdlU5gfi&&sz=w4000",{"id":34,"imageVertical":578,"imageHorizontal":579,"link":163,"weight":174},"https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1_NsnJt2O238fO_dLl19RR4SNbyRErIJY&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1Q989E0GWazdVSPcGvZLMYzsNSh4cV2-g&&sz=w4000",{"id":34,"imageVertical":581,"imageHorizontal":582,"link":173,"weight":174},"https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1d4-1ZBMs6GqYcYytlYrSVZhs8Jgye5l3&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1Ea4CNZ-14siicP3xYm78l3AF41iAb9Om&&sz=w4000",{"id":34,"imageVertical":584,"imageHorizontal":585,"link":183,"weight":174},"https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1A9Q35aOO4LDtI1-MVbIlLoGBmWn2VwZg&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=13Oz8Eq6MXXspGEqwi5QGbwYyDNeU1idK&&sz=w4000",{"id":587,"imageVertical":588,"imageHorizontal":589,"link":61,"weight":10},"kktix-news","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=11md6cNzKBG-OF_e_9G5ZCLujoyck96as&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1ec5tuBMqbKDfPakOPWZF93Q55JI7DOOl&&sz=w4000",{"id":591,"imageVertical":592,"imageHorizontal":593,"link":133,"weight":22},"gamesofa-news","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1HkRfiNOhKrH2zTaOHjTkDnAmoDPqV5_c&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1IVAroDzzryU5AIY4qMMVztg4hu-FXaIM&&sz=w4000",{"id":595,"imageVertical":596,"imageHorizontal":597,"link":598,"weight":10},"onlyoffice-news","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1H7dguSsKUH9aS9vxK-RhI519LEQjaak-&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1IchePy7nwLT4TXnLYLf8o6HS4TKOOjFd&&sz=w4000","https:\u002F\u002Fwww.onlyoffice.com\u002F",{"id":600,"imageVertical":601,"imageHorizontal":602,"link":191,"weight":10},"SUN-SQUARE-news","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=19TU_W9JBLzrRYVSQPG4cbbckhWLy0JaS&&sz=w4000","https:\u002F\u002Fdrive.google.com\u002Fthumbnail?id=1-2rlsJngO4Qiu0SElyXhMYmsjmGokHu_&&sz=w4000",{"data":604,"body":605},{},{"type":606,"children":607},"root",[608,616],{"type":609,"tag":610,"props":611,"children":612},"element","p",{},[613],{"type":614,"value":615},"text","This track focuses on application scenarios and system integration after obtaining generated content from open-source models. We welcome sharing practical experiences on transforming AI capabilities into actual tools to solve real-world problems. Topics include, but are not limited to:",{"type":609,"tag":617,"props":618,"children":619},"ol",{},[620,626,631],{"type":609,"tag":621,"props":622,"children":623},"li",{},[624],{"type":614,"value":625},"RAG & System Integration\nShare implementations of RAG (Retrieval-Augmented Generation) architectures, applications of vector databases, and how to integrate LLMs into existing software workflows.",{"type":609,"tag":621,"props":627,"children":628},{},[629],{"type":614,"value":630},"AI Agents & Automation Workflows\nExplore building AI Agents with task planning and execution capabilities using open-source models, and automation practices within various industry scenarios.",{"type":609,"tag":621,"props":632,"children":633},{},[634],{"type":614,"value":635},"Application Evaluation & Security\nDiscuss evaluating the quality of generated content (e.g., hallucination detection), optimization of prompt engineering, and privacy protection mechanisms at the application level.",1785691052222]