AI设计工坊 的周报精粹。

apache/ossie

Apache Ossie, industry wide specification effort to standardize how we exchange semantic metadata across analytics, AI and BI platforms, providing a vendor neutral, single source of truth for semantic data Apache Ossie (incubating) Apache Ossie is a collaborative, open-source effort dedicated to standardizing and streamlining semantic model exchange and utilization across the diverse array of tools and platforms within the data analytics, AI, and BI ecosystem. Our shared vision is to establish a common, vendor-agnostic semantic model specification, promoting unparalleled interoperability, efficiency, and collaboration among all participants. By providing a single, consistent source of truth, this vendor-agnostic standard ensures that your data's definitions and value remain consistent as they are interchanged between AI agents, BI platforms, and all other tools in your ecosystem, eliminating inconsistencies across your different tools. Apache Ossie was formerly known as Open Semantic Interchange (OSI). Apache Ossie provides a single JSON- and YAML-based specification that any tool can read and write, addressing the semantic fragmentation common across today's data stack: the same KPI defined differently across tools, teams spending significant effort manually reconciling definitions, and AI agents producing unreliable outputs grounded in inconsistent business logic. What's in this repository core-spec/ — The Ossie core specification (spec.md), the machine-readable schema (spec.yaml, osi-schema.json), and accompanying documentation. converters/ — Reference converters that translate between Ossie and other semantic formats (e.g., dbt, GoodData, Polaris, Salesforce). examples/ — Example semantic models, including a complete TPC-DS model. validation/ — Tooling for validating semantic models against the Ossie schema. docs/ — Project documentation and overview. Get involved Contribute: See CONTRIBUTING.md for how to propose specifi…[truncated]

Hallmark 是一款开源 design skill，专为 Claude Code、Cursor 与 Codex 打造。它内置 57 道 slop-test 门控与 20 套主题系统，在生成前强制 AI 进行自我批判，从根本上拒绝千篇一律的「AI 味」模板，让不同 brief 产出气质迥异的站点；同时支持 audit、redesign、study 四种命令，可直接嵌入现有工作流。

OpenCut 正在完全重写，基于 Rust 核心实现跨平台，并计划加入 MCP Server 让 AI Agent 能直接操控视频编辑，同时提供 Headless 模式与脚本化能力，目标成为开源版的 CapCut。

PostHog 仓库登上 GitHub Trending，官方描述将其定位为“自动驾驶产品”平台，涵盖 AI 可观测性、会话重放、功能标志与实验等工具。然而内容仅为标准 README 式的功能罗列，既无版本更新细节，也未提供设计师可直接上手的工作流或集成方法，信息密度极低。

Open Interpreter 推出基于 Rust 的新版本，作为 Codex 的替代分支，专为低成本模型优化。它支持切换多种 agent harness（如 claude-code、qwen-code 等），内置浏览器自动化、原生应用测试和 MCP 协议，允许在本地沙箱中运行命令。设计师和工程师可立即用廉价模型完成编码、测试和界面操作任务。

PrismML-Eng/Bonsai-demo

Bonsai Demo Bonsai Demo Website  |  GitHub  |  Discord HF Collections: Bonsai 27B · Bonsai (1-bit) · Ternary-Bonsai Whitepapers: Bonsai 27B · 1-bit Bonsai 8B · Ternary-Bonsai 8B Using this demo repository you can run Bonsai (1-bit) and Ternary-Bonsai language models locally on Mac (Metal), Linux/Windows (CUDA, Vulkan, ROCm), or CPU. 🌱 New: Bonsai 27B The family's newest and largest generation, and its first vision-language models (Bonsai 27B collection): Vision: send photos, screenshots, and PDFs; ask about them (see VISION.md). Agentic tool calling: native OpenAI-style tool_calls with full round-trips, plus MCP servers in both demo UIs (see TOOLS.md). Thinking: a reasoning model; pick the reasoning effort per chat in the UI or budget it per request. Long context: 256k+ token conversations. Tiny footprint: the 1-bit Bonsai-27B packs to ~1.125 bits per weight: it fits on a modern iPhone without memory offloading. Ternary-Bonsai-27B (~1.7 bits per weight, packed into 2-bit for fast accelerated kernels) is the higher-quality option and this demo's default. Quick Start below gets you there in two commands: ./setup.sh downloads Ternary-Bonsai-27B by default, then ./scripts/start_llama_server.sh gives you chat, vision, and tools at http://localhost:8080. Quick Start Setting things up with an AI coding agent? Point it at AGENTS.md, a guide written for agents (hardware-specific knobs, defaults, and what to ask the user). macOS / Linux git clone https://github.com/PrismML-Eng/Bonsai-demo.git cd Bonsai-demo # (Optional) Choose a model size: 27B (default), 8B, 4B, or 1.7B export BONSAI_MODEL=27B # Set your HuggingFace token (only required for 27B while its repos are private) export BONSAI_TOKEN="hf_your_token_here" # One command does everything: installs deps, downloads models + binaries ./setup.sh Windows (PowerShell) git clone https://github.com/PrismML-Eng/Bonsai-demo.git cd Bonsai-demo # (Optional) Choose…[truncated]

开发者将 1324 个健身动作整理成结构化数据集并开源，附带数据库模式、API 代码与多语言指令（中英意土俄西），但因版权争议未包含演示媒体。对健身类应用开发者是即拿即用的后端脚手架，但对广义设计师而言可复用价值极低。

GitHub Trending 上的 Awesome LLM Apps 收录了 100 多个可直接运行的 AI Agent 与 RAG 应用模板，涵盖 MCP、多智能体、语音代理等现代 AI 栈，支持 Claude、GPT 等主流模型一键切换。对设计工程师而言，这意味着无需从零搭建脚手架，克隆代码即可快速验证 AI 原型并落地生产。

LobeHub 将自己定位为“首席 Agent 运营官”，支持通过雇佣、排班和报表管理 AI Agent 团队，实现 7×24 小时自动运行。项目由 e/acc 设计工程师团队开发，支持 Vercel 和 Docker 自托管，目前处于活跃开发期并登上 GitHub Trending。

这是一个 GTA 5 增强版实验性作弊菜单，提供 DLL 注入与 BattlEye 绕过功能。该仓库虽登上 GitHub Trending，但本质属于游戏外挂，与产品设计、AI 创作及设计工程完全无关，对目标读者无可复用的工作流价值。

DeepTutor 是 HKUDS 推出的开源 AI 辅导系统，近日登上 GitHub Trending。最新版本迭代了 RAG 知识库修复、LlamaIndex 多模态解析与 LightRAG 检索等功能。但对产品设计师与设计工程师而言，这属于垂直教育领域的技术补丁，未提供可复用于设计工作流的方法或资源。

TypeScript 教育家 Matt Pocock 开源了他自用的 Claude agent skills 仓库，提供一套小型、可组合、模型无关的工程化技能集合，附带一键安装脚本。不同于完全放任的 vibe coding，这套技能旨在修复 Claude Code 与 Codex 等工具的常见失效模式，让开发者保持对真实工程流程的掌控。

github/copilot-sdk

Multi-platform SDK for integrating GitHub Copilot Agent into apps and services GitHub Copilot CLI SDKs Agents for every app. Embed Copilot's agentic workflows in your application with the GitHub Copilot SDK for Python, TypeScript, Go, .NET, Java, and Rust. The GitHub Copilot SDK exposes the same engine behind Copilot CLI: a production-tested agent runtime you can invoke programmatically. No need to build your own orchestration—you define agent behavior, Copilot handles planning, tool invocation, file edits, and more. Available SDKs SDK Location Cookbook Installation API docs Node.js / TypeScript nodejs/ Cookbook npm install @github/copilot-sdk Python python/ Cookbook pip install github-copilot-sdk Go go/ Cookbook go get github.com/github/copilot-sdk/go API docs .NET dotnet/ Cookbook dotnet add package GitHub.Copilot.SDK Rust rust/ — cargo add github-copilot-sdk API docs Java java/ Cookbook Maven coordinates com.github:copilot-sdk-java See instructions for Maven and Gradle API docs See the individual SDK READMEs for installation, usage examples, and API reference. Getting Started For a complete walkthrough, see the Getting Started Guide. Quick steps: (Optional) Install the Copilot CLI For Node.js, Python, and .NET SDKs, the Copilot CLI is bundled automatically and no separate installation is required. For Go, Java, and Rust, install the CLI manually or ensure copilot is available in your PATH. Go and Rust also expose application-level CLI bundling features. Install your preferred SDK using the commands above. See the SDK README for usage examples and API documentation. Architecture All SDKs communicate with the Copilot CLI server via JSON-RPC: Your Application ↓ SDK Client …[truncated]

ibelick 开源了 ui-skills，一个面向 Design Engineer 的 CLI 工具。通过 npx 一键启动，可按类别（如 motion、baseline-ui）整理预设技能集，并自动将 AI Agent 路由到对应的 UI 规范与实现逻辑，省去反复撰写 prompt 的麻烦。

Graphify-Labs/graphify

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph. Read this in other languages 🇺🇸 English | 🇨🇳 简体中文 | 🇯🇵 日本語 | 🇰🇷 한국어 | 🇩🇪 Deutsch | 🇫🇷 Français | 🇪🇸 Español | 🇮🇳 हिन्दी | 🇧🇷 Português | 🇷🇺 Русский | 🇸🇦 العربية | 🇮🇷 فارسی | 🇮🇹 Italiano | 🇵🇱 Polski | 🇳🇱 Nederlands | 🇹🇷 Türkçe | 🇺🇦 Українська | 🇻🇳 Tiếng Việt | 🇮🇩 Bahasa Indonesia | 🇸🇪 Svenska | 🇬🇷 Ελληνικά | 🇷🇴 Română | 🇨🇿 Čeština | 🇫🇮 Suomi | 🇩🇰 Dansk | 🇳🇴 Norsk | 🇭🇺 Magyar | 🇹🇭 ภาษาไทย | 🇺🇿 Oʻzbekcha | 🇹🇼 繁體中文 | 🇵🇭 Filipino | 🇮🇱 עברית Type /graphify in your AI coding assistant and it maps your entire project (code, docs, PDFs, images, videos) into a knowledge graph you can query instead of grepping through files. Code maps for free, fully local. Code is parsed with tree-sitter AST: deterministic, no LLM, nothing leaves your machine. (Docs, PDFs, images and video use your assistant's model, or a configured API key, for a semantic pass.) Every edge is explained. Each connection is tagged EXTRACTED (explicit in the source) or INFERRED (resolved by graphify), so you can tell what was read directly from what was inferred. Not a vector index. No embeddings, no vector store: a real graph you traverse. Ask a question, trace the path between two things, or explain one concept. The FastAPI codebase mapped by graphify. Every node is a concept, colors are detected communities, and the whole thing is clickable in graph.html. Get started (30 seconds): uv tool install graphifyy # install the CLI (or: pipx install graphifyy) graphify install # register the skill with your AI assistant Then, in your AI assistant: /graphify . That's it. You get three files: graphify-out/ ├── graph.html open in any browser — click…[truncated]

这是一个收录了数百个手把手教程的 GitHub 仓库，教你从零开始构建 3D 渲染器、数据库、操作系统、AI 模型等经典技术。对设计工程师而言，深入理解底层实现比调 API 更重要，这是对抗“黑盒焦虑”的最佳实践清单。

ossu/computer-science

🎓 Path to a free self-taught education in Computer Science! Open Source Society University Path to a free self-taught education in Computer Science! Contents Summary Community Curriculum Code of conduct Team Summary The OSSU curriculum is a complete education in computer science using online materials. It's not merely for career training or professional development. It's for those who want a proper, well-rounded grounding in concepts fundamental to all computing disciplines, and for those who have the discipline, will, and (most importantly!) good habits to obtain this education largely on their own, but with support from a worldwide community of fellow learners. It is designed according to the degree requirements of undergraduate computer science majors, minus general education (non-CS) requirements, as it is assumed most of the people following this curriculum are already educated outside the field of CS. The courses themselves are among the very best in the world, often coming from Harvard, Princeton, MIT, etc., but specifically chosen to meet the following criteria. Courses must: Be open for enrollment Run regularly (ideally in self-paced format, otherwise running multiple times per year) Be of generally high quality in teaching materials and pedagogical principles Match the curricular standards of the CS 2013: Curriculum Guidelines for Undergraduate Degree Programs in Computer Science When no course meets the above criteria, the coursework is supplemented with a book. When there are courses or books that don't fit into the curriculum but are otherwise of high quality, they belong in extras/courses or extras/readings. Organization. The curriculum is designed as follows: Intro CS: for students to try out CS and see if it's right for them Core CS: corresponds roughly to the first three years of a computer science curriculum, taking classes that all majors would be require…[truncated]