{"profile":{"name":"Hu Qi","alternateName":"胡琦","handle":"@hu-qi","location":"Canton","motto":"Finding myself. Building useful things with AI.","role":"AI-native builder · Front-End engineer · Cloud & AIoT explorer","summary":"I build practical AI applications, developer tools, technical tutorials, and cloud-native demos. Recently focused on AI Agent, RAG, full-stack engineering, ROS2, and CloudDev.","email":"huqi1024@gmail.com","github":"https://github.com/hu-qi","blog":"https://hu-qi.github.io","twitter":"https://twitter.com/huqii","huaweiCloud":"https://bbs.huaweicloud.com/community/usersnew/id_1567662212449451","avatar":"https://github.com/hu-qi.png"},"signals":[{"label":"GitHub repos","value":"145","note":"GitHub API"},{"label":"Stars","value":"31","note":"latest public repos page"},{"label":"Followers","value":"127","note":"GitHub API"},{"label":"Following","value":"684","note":"GitHub API"}],"projects":[{"name":"BiddingAudit-knowledge","org":"hu-qi","tag":"Front-End","desc":"招投标文件稽核对齐与合规校验知识库（OKF v0.1）。通过 QwebBridge 浏览器探索行业竞品、深度地图绘制、沉淀行业术语、构建对标信息。","link":"https://github.com/hu-qi/BiddingAudit-knowledge"},{"name":"OpenKnowledgeFormat-Skill","org":"hu-qi","tag":"AI","desc":"Open Knowledge Format Skill.","link":"https://github.com/hu-qi/OpenKnowledgeFormat-Skill"},{"name":"frontend-project-map-skill","org":"hu-qi","tag":"Front-End","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/frontend-project-map-skill"},{"name":"ohpm-awesome","org":"hu-qi","tag":"Open Source","desc":"https://hu-qi.github.io/ohpm-awesome/","link":"https://github.com/hu-qi/ohpm-awesome"},{"name":"arcprize-leaderboard-zh","org":"hu-qi","tag":"Open Source","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/arcprize-leaderboard-zh"},{"name":"hu-qi","org":"hu-qi","tag":"Open Source","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/hu-qi"},{"name":"huawei-case-writer","org":"hu-qi","tag":"Cloud AI","desc":"Huawei Cloud Case Writer","link":"https://github.com/hu-qi/huawei-case-writer"},{"name":"macos-dev-machine-rebuild-skill","org":"hu-qi","tag":"Open Source","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/macos-dev-machine-rebuild-skill"},{"name":"QWebBridge","org":"hu-qi","tag":"AI","desc":"Browser bridge for AI agents — control Chrome via accessibility tree, navigate, click, fill, screenshot, and more","link":"https://github.com/hu-qi/QWebBridge"},{"name":"chatgpt-auto-driver","org":"hu-qi","tag":"Open Source","desc":"🤖 Auto-driver for ChatGPT macOS app: auto-click Allow buttons and keep conversations going","link":"https://github.com/hu-qi/chatgpt-auto-driver"},{"name":"ai-app-dev-handbook","org":"hu-qi","tag":"AI","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/ai-app-dev-handbook"},{"name":"globaldev-agent","org":"hu-qi","tag":"AI","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/globaldev-agent"},{"name":"globaldev-agent-skill","org":"hu-qi","tag":"AI","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/globaldev-agent-skill"},{"name":"jiuwenswarm-ebook-site","org":"hu-qi","tag":"Open Source","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/jiuwenswarm-ebook-site"},{"name":"Tidewise","org":"hu-qi","tag":"AI","desc":"Tidewise - AI-powered tide prediction and coastal monitoring platform","link":"https://github.com/hu-qi/Tidewise"},{"name":"TuskMind","org":"hu-qi","tag":"AI","desc":"TuskMind - Sui blockchain project planning and execution platform","link":"https://github.com/hu-qi/TuskMind"},{"name":"MemLens","org":"hu-qi","tag":"AI","desc":"MemLens - Memory monitoring and analytics platform with Walrus storage","link":"https://github.com/hu-qi/MemLens"},{"name":"seo-skills","org":"hu-qi","tag":"Open Source","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/seo-skills"},{"name":"mural-flashlight","org":"hu-qi","tag":"Open Source","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/mural-flashlight"},{"name":"x-cli-rs","org":"hu-qi","tag":"Open Source","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/x-cli-rs"},{"name":"ocr-wasm","org":"hu-qi","tag":"Open Source","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/ocr-wasm"},{"name":"panan","org":"hu-qi","tag":"Open Source","desc":"磐安县开咖啡馆可行性数据报告 - 人口/消费/旅游/竞品分析 + Python量化分析脚本","link":"https://github.com/hu-qi/panan"},{"name":"clearmatte-studio","org":"hu-qi","tag":"Open Source","desc":"Browser-based client-side background removal studio","link":"https://github.com/hu-qi/clearmatte-studio"},{"name":"picgo-plugin-huaweicloud-obs","org":"hu-qi","tag":"Cloud AI","desc":"Open-source project from Hu Qi GitHub activity.","link":"https://github.com/hu-qi/picgo-plugin-huaweicloud-obs"}],"documents":[{"label":"GitHub profile README","url":"https://github.com/hu-qi/hu-qi","content":"\n\n
\n\n# Hi, I'm Hu Qi 👋\n\n## AI-native builder · Front-End engineer · Cloud & AIoT explorer\n\n

\n \"GitHub\n \"X\n \"Email\"\n \"Blog\"\n

\n\n

\n I build practical AI applications, developer tools, technical tutorials, and cloud-native demos.\n
\n Recently focused on AI Agent, RAG, Full-stack engineering, ROS2, and CloudDev.\n

\n\n
\n\n---\n\n## 🚀 What I am building\n\n\n\n\n\n\n
\n\n### 🤖 AI / Agent / RAG\n\n- [wow-agent](https://github.com/datawhalechina/wow-agent) — learning and building agent workflows\n- [wow-rag](https://github.com/datawhalechina/wow-rag) — retrieval-augmented generation practice\n- AI coding, prompt engineering, knowledge-base applications\n\n\n\n### 🧩 Full-stack / Cloud / AIoT\n\n- [wow-fullstack](https://github.com/datawhalechina/wow-fullstack) — full-stack project practice\n- Front-End engineering, interactive docs, developer experience\n- ROS2, IoT scenarios, cloud-native hands-on cases\n\n
\n\n```mermaid\nmindmap\n root((Hu Qi))\n AI Native\n Agent\n RAG\n Coding Assistant\n Engineering\n Front-End\n Full-stack\n Developer Experience\n Cloud & AIoT\n CloudDev\n ROS2\n IoT Scenarios\n Content\n Tutorials\n Open Source Notes\n WeChat / Blog\n```\n\n---\n\n## 🕸️ GitHub developer graph\n\n
\n\n\"Hu\n\n
\n\n
\nHow this graph is generated\n\n
\n\nThis graph is generated from GitHub data and updated by GitHub Actions.\n\n| Signal | Meaning |\n| --- | --- |\n| Repositories | Own repos ranked by stars, forks, and recent activity |\n| Communities / Orgs | External repositories and organizations touched by authored issues, PRs, or public events |\n| Languages | Language distribution from public repositories |\n| Activity Types | Recent public GitHub event types |\n\nThe generator lives in `.github/scripts/generate-developer-graph.py`, and the workflow lives in `.github/workflows/update-developer-graph.yml`.\n\n
\n\n---\n\n## 🧭 Explore my profile\n\n
\n🌟 Current focus\n\n
\n\n| Direction | What I care about | Output style |\n| --- | --- | --- |\n| AI Agent | from toy demos to useful workflows | repos, tutorials, cases |\n| RAG | retrieval quality, knowledge engineering, evaluation | notes, examples, templates |\n| Front-End | interaction, visual polish, DX | components, pages, docs |\n| CloudDev | practical cloud scenarios | hands-on guides, case studies |\n| AIoT / ROS2 | bridging software and devices | experiments, demos |\n\n
\n\n
\n🛠️ Tech stack and tools\n\n
\n\n

\n \"Tech\n

\n\n```txt\nLanguages TypeScript / JavaScript / Python / Markdown\nFront-End React / Vue / Vite / Interactive Docs\nAI Agent / RAG / Prompt Engineering / AI Coding\nCloud & IoT CloudDev / Linux / Docker / ROS2 / AIoT\nWorkflow GitHub / VS Code / Technical Writing / Open Source\n```\n\n
\n\n
\n📚 Writing and communities\n\n
\n\n| Platform | Link |\n| --- | --- |\n| Blog | [hu-qi.github.io](https://hu-qi.github.io) |\n| X / Twitter | [@huqii](https://twitter.com/huqii) |\n| 知乎 | [fashaoge](https://www.zhihu.com/people/fashaoge) |\n| 华为云社区 | [Hu Qi on Huawei Cloud](https://bbs.huaweicloud.com/community/usersnew/id_1567662212449451) |\n\n
\n\n
\n💬 Contact / WeChat\n\n
\n\n\n\n\n\n\n
\n\n- Email: [huqi1024@gmail.com](mailto:huqi1024@gmail.com)\n- GitHub: [@hu-qi](https://github.com/hu-qi)\n- Open to collaboration on AI applications, Front-End, CloudDev, AIoT, tutorials, and open-source learning projects.\n\n\n\n\"WeChat\n\n
\n\n
\n\n---\n\n## 📊 GitHub signal\n\n
\n\n\n \n \n \"Hu\n\n\n\n \n \n \"Hu\n\n\n
\n\n
\n🏆 More GitHub widgets\n\n
\n\n
\n\n\"GitHub\n\n

\n\n\"3D\n\n
\n\n
\n\n---\n\n## 🧪 README design notes\n\nThis profile README intentionally uses mostly native GitHub-flavored Markdown features:\n\n- `details / summary` for clickable sections\n- `picture` for light/dark adaptive GitHub stats\n- `mermaid` for an interactive-looking knowledge map without custom JavaScript\n- generated SVG developer relationship graph from GitHub data\n- fewer fragile external widgets; removed abandoned-style counters and skill-chart dependencies\n\n
\n\n### Thanks for visiting. Let's build useful things with AI. ✨\n\n
"},{"label":"Huawei Cloud recent blog listing","url":"https://bbs.huaweicloud.com/community/usersnew/id_1567662212449451","content":"This snapshot is fetched from Hu Qi's Huawei Cloud community profile and includes recent blog titles, categories, dates, and visible metrics.\n\n胡琦的博客_云社区-华为云 Lv.6 胡琦 更多个人资料 2755 成长值 92 关注 60 粉丝 + 关注 私信 个人介绍 同名公众号，WeChat：Hugi66 感兴趣或擅长的领域 人工智能、IoT、软件开发、鸿蒙、开发语言 个人勋章 云上体验官 活跃之星 成长雷达 1650 825 50 210 20 个人资料 个人介绍 同名公众号，WeChat：Hugi66 感兴趣或擅长的领域 人工智能、IoT、软件开发、鸿蒙、开发语言 达成规则 以上满足 项可达成此勋章 博客 关注 粉丝 论坛 全部时间 全部时间 最近三天 最近一周 最近一月 全部 码道实战营 All-in-RAG 开发者空间 上云正当时 用码道来写 subAgent，轻松搞定项目周报 码道新特性支持 subAgent，快速构建 subAgent 群智能体解决业务问题。 人工智能 华为云码道（CodeArts）代码智能体 胡琦 2026-05-18 01:08:41 395 2 0 2026-05-18 01:08:41 395 2 0 【案例共创】在开发者空间使用 MateChat 和MaaS快速开发智能对话界面 开发者空间快速验证 MateChat ！ AI开发平台ModelArts 开发者空间 前端 Vue 胡琦 2025-01-15 02:23:27 23558 2 2 2025-01-15 02:23:27 999+ 2 2 Claude Code 作者亲自揭秘：我是如何使用Claude Code？（13条全配置解析） Claude Code 发布后迅速成为开发者的新宠。作为工具的创造者，Boris Cherny (@bcherny) 自己究竟是如何使用它的？最近，他毫无保留地公开了自己的 13 条核心配置（Setup）。这不仅是一份工具指南，更是一套 AI 原生时代的开发哲学。 人工智能 胡琦 2026-01-04 23:30:18 1888 0 0 2026-01-04 23:30:18 999+ 0 0 【手摸手学 RAG】RAG性能再突破！当知识图谱遇上LLM，打造你的终极问答机器人 RAG性能再突破！当知识图谱遇上LLM，打造你的终极问答机器人 智能问答机器人 机器人 知识图谱 胡琦 2025-10-05 11:02:57 5152 0 0 2025-10-05 11:02:57 999+ 0 0 【手摸手学 RAG】从零开始，和我一起搭建一个RAG知识库问答机器人 从零开始，和我一起搭建一个RAG知识库问答机器人 AI开发平台ModelArts Python 开发者空间 智能问答机器人 机器人 胡琦 2025-10-05 10:43:08 18676 0 0 2025-10-05 10:43:08 999+ 0 0 【手摸手学 RAG】我的RAG机器人咋总答不对？三步升级你的检索系统 我的RAG机器人咋总答不对？三步升级你的检索系统 AI开发平台ModelArts Python 开发者空间 胡琦 2025-10-05 10:00:51 3013 2 2 2025-10-05 10:00:51 999+ 2 2 【手摸手学RAG】05-从向量嵌入到Milvus索引优化，一文打通核心技术脉络 作为当前大模型落地应用的关键一环，RAG的效果很大程度上取决于其检索的准确性和效率。而这背后，**向量嵌入（Vector Embedding）**、**向量数据库（Vector Database）** 以及 **索引优化（Index Optimization）** 等技术扮演着至关重要的角色。 AI开发平台ModelArts Python 开发者空间 胡琦 2025-09-25 21:38:25 5569 0 0 2025-09-25 21:38:25 999+ 0 0 【手摸手学RAG】03数据准备——从加载到分块，构建高效知识库 在RAG中外部知识库是关键要素之一，本文将从最基础的数据加载和文本分块开始，和大家学习交流如何构建一个高效的知识库。 AI开发平台ModelArts 开发者空间 胡琦 2025-09-19 23:26:33 2364 1 0 2025-09-19 23:26:33 999+ 1 0 【手摸手学RAG】00-零基础也能玩转检索增强生成，AI开发So Easy！ 先导篇：零基础也能玩转检索增强生成，AI开发So Easy！ AI开发平台ModelArts 开发者空间 胡琦 2025-09-17 20:22:06 2103 0 0 2025-09-17 20:22:06 999+ 0 0 【案例共创】ESC基于RAGFlow和DeepSeek构建本地问答知识库 Dify、maxkb玩腻了？试试RAGFlow！ Docker 容器 弹性云服务器 ECS 胡琦 2025-03-09 05:40:10 6901 0 0 2025-03-09 05:40:10 999+ 0 0 总条数：72 10 10 20 50 100 1 2 3 4 5 6 7 8 上滑加载中 https://www.baidu.com/s?ie=utf-8&f=3&rsv_bp=0&rsv_idx=1&tn=baidu&wd=sed%20%E6%9B%BF%E6%8D%A2%E5%AD%97%E7%AC%A6%E4%B8%B2&rsv_pq=c7db61a600035dc5&rsv_t=5e19yEsbV9N5fIvdlGRU 快速交付 + 关注 --> -->"},{"label":"Satellite site: ClearMatte Studio","url":"https://clearmatte.huqi.host/","content":"ClearMatte Studio ClearMatte Studio Ready Reset Export PNG Grid White Dark Color Compare Drop Image PNG, JPEG, WebP Choose Image Remove Background Waiting for an image 0% Matte Apply Cutoff 42 Softness 14 Clean 8 Output Max Edge 2048 px 3072 px 4096 px Transparent PNG Model BiRefNet lite 512 License MIT Runtime Auto"},{"label":"Satellite site: QWebBridge","url":"https://qweb-bridge.huqi.host/","content":"QWebBridge — Open-Source Browser Bridge for AI Agents QWebBridge Features Protocols Install FAQ Chrome Store GitHub Open source · MIT Let AI agents drive your browser QWebBridge gives AI agents full control over your real Chrome browser — navigate, click, fill forms, screenshot, and extract data using your own login sessions. Get started Add Chrome Extension View on GitHub 16 Tools 4 Protocols 1 Command to install Architecture How it works A local service, Chrome extension, and agent skill connect your AI agent to your real browser through Chrome DevTools Protocol. 🤖 AI Agent Claude Code, Kimi Code, Cursor ... → 📦 Agent Skill tool usage guide → 🌉 QWebBridge Daemon localhost:10086 → 🔌 Chrome Extension CDP via chrome.debugger → 🌐 Your Browser Real tabs, real sessions Features 16 browser automation tools Everything an AI agent needs to browse the web, interact with pages, and extract information. 🧭 navigate Navigate to any URL. Opens new tabs with session-based grouping and auto-load waiting. 📋 snapshot Get the full accessibility tree with @eN refs for reliable element targeting. 📸 screenshot Capture screenshots in PNG, JPEG, or WebP. Supports full-page and element capture. 👆 click Click elements by CSS selector or accessibility ref. Auto-scrolls into view. ✏️ fill Fill forms, textareas, and rich editors (ProseMirror, Lexical, Slate, Quill). ⚡ evaluate Run arbitrary JavaScript in the page. Supports async/await. 🖱️ mouse_click Real mouse event dispatch at element coordinates. ⌨️ key_type Type text character by character via CDP. 🔑 send_keys Keyboard shortcuts with modifier keys — Control, Alt, Shift, Meta. 📎 upload Upload files to inputs. Supports multiple files. 🌐 network Monitor network requests — start, stop, list, inspect. 🔍 find_tab Find an open tab by URL. Target active tab or first match. 📑 list_tabs List all open tabs with URL, title, and session group. ❌ close_tab Close the current tab or a specific tab by ID. 🧹 close_session Close all tabs in an AI session — one command cleanup. 📄 save_as_pdf Render page to PDF with configurable format and scale. Use Cases What you can build From automated testing to AI-powered research — if you can do it in a browser, your AI agent can too. 🔍 Web research at scale Have your agent search, read, and compile information from hundreds of pages automatically. 📊 Data extraction Pull structured data from SaaS dashboards, CRM systems, and internal tools — APIs not required. 🧪 Automated testing Run end-to-end tests through real browser sessions with full network monitoring. 🔄 Workflow automation Automate repetitive browser tasks: form filling, file uploads, multi-step approvals. 👀 Monitoring & alerts Track prices, job listings, product changes, and competitor moves as they happen. 🎯 Form & CAPTCHA handling Let your agent handle login forms, job applications, and vendor portals. Integration Works with any AI agent Connect your preferred coding agent through the protocol that fits your workflow. WebSocket WebSocket API Kimi WebBridge compatible protocol. Connect any agent that speaks WebSocket. ws://localhost:10086/selector/command MCP Model Context Protocol Standard MCP server for Claude Desktop, Cursor, Windsurf, and any MCP client. qweb-bridge mcp REST HTTP API Simple HTTP POST interface for custom scripts and integrations. POST /api/tool/ CLI Command Line Direct terminal access for quick browser automation from your shell. qweb-bridge Install Get started in 1 minute QWebBridge needs three parts: the local daemon, the Chrome extension, and the AI agent skill. Prerequisites: Chrome browser and Node.js ≥ 18 . 1 Chrome extension is now available on Chrome Web Store Install the browser-side component from Chrome Web Store , then start the local daemon and install the agent skill below. curl npm pnpm Manual # One-command install (macOS / Linux) curl -fsSL https://github.com/hu-qi/QWebBridge/raw/main/install.sh | bash # Not yet published to npm — use curl or manual build # Stay tuned: npm package coming soon # Install dependencies pnpm install # Build all packages pnpm build $ git clone https://github.com/hu-qi/QWebBridge.git $ cd QWebBridge $ pnpm install $ pnpm build $ node packages/daemon/dist/cli.js run Setup steps 1 Start the daemon Run qweb-bridge start or node packages/daemon/dist/cli.js run . The daemon listens on localhost:10086 . 2 Install the Chrome extension Install from Chrome Web Store . For local development, you can still use chrome://extensions and load packages/extension/dist . 3 Install the AI agent skill Run qweb-bridge install-skill . The skill tells your AI agent how to use QWebBridge tools, sessions, screenshots, and troubleshooting commands. 4 Connect your AI agent Point your agent to ws://localhost:10086/selector/command (WebSocket) or run qweb-bridge mcp (MCP). Run qweb-bridge status to verify extensions_connected: true . ✓ Chrome browser ✓ Node.js ≥ 18 ✓ AI agent skill FAQ Frequently asked questions How\n\n[Document truncated for context length]"},{"label":"Satellite site: Mural Flashlight","url":"https://flashlight.huqi.host/","content":"Mural Flashlight"}],"refreshedAt":"2026-06-16T14:27:26.775Z","sources":[{"label":"GitHub API","url":"https://api.github.com/users/hu-qi"},{"label":"GitHub Profile","url":"https://github.com/hu-qi"},{"label":"Huawei Cloud Community","url":"https://bbs.huaweicloud.com/community/usersnew/id_1567662212449451"},{"label":"ClearMatte Studio","url":"https://clearmatte.huqi.host/"},{"label":"QWebBridge","url":"https://qweb-bridge.huqi.host/"},{"label":"Mural Flashlight","url":"https://flashlight.huqi.host/"}]}