Today's brief

Cloudflare 开源的 coding-agent skill 将安全审计拆为六阶段（侦察、狩猎、验证、结构化输出、独立复核、中立报告），核心在于用隔离 agent 互相交叉验证。这套多 agent 编排与验证机制对设计工程师构建设计审查或代码审计类 AI 工作流具有直接参考价值。

vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs https://vllm.ai Easy, fast, and cheap LLM serving for everyone | Documentation | Blog | Paper | Twitter/X | User Forum | Developer Slack | 🔥 We have built a vLLM website to help you get started with vLLM. Please visit vllm.ai to learn more. For events, please visit vllm.ai/events to join us. About vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has grown into one of the most active open-source AI projects built and maintained by a diverse community of many dozens of academic institutions and companies from over 2000 contributors. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests, chunked prefill, prefix caching Fast and flexible model execution with piecewise and full CUDA/HIP graphs Quantization: FP8, MXFP8/MXFP4, NVFP4, INT8, INT4, GPTQ/AWQ, GGUF, compressed-tensors, ModelOpt, TorchAO, and more Optimized attention kernels including FlashAttention, FlashInfer, TRTLLM-GEN, FlashMLA, and Triton Optimized GEMM/MoE kernels for various precisions using CUTLASS, TRTLLM-GEN, CuTeDSL Speculative decoding including n-gram, suffix, EAGLE, DFlash Automatic kernel generation and graph-level transformations using torch.compile Disaggregated prefill, decode, and encode vLLM is flexible and easy to use with: Seamless integration with popular Hugging Face models High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more Tensor, pipeline, data, expert, and context parallelism for distributed inference Streaming outputs Generation of structured outputs using xgrammar or guidance Tool calling and reasoning parsers OpenAI-compatible API serve…[truncated]

Orca 是一款跨平台 AI Agent 开发环境，可在桌面和移动端并行调度 Codex、ClaudeCode 等 coding agent。其 Design Mode 支持在 Chromium 中直接点击 UI 元素，将 HTML、CSS 及截图一键送入 agent prompt；配合并行 git worktree 与原生 GitHub/Linear 集成，让设计到前端的无缝协作成为可能。

Headroom 在本地压缩 AI agent 读取的一切内容（工具输出、日志、RAG、文件），coding agent 省 20% token，JSON 省 60–95%。提供 Python/TS 库、零代码代理、MCP Server 及跨 agent 共享记忆，还能自动从失败会话中提取经验写入团队文档。

Ponytail 是一套可复用的 AI Agent 提示框架，通过注入“极简主义资深开发者”人格，迫使 Claude Code 等工具用最少代码解决问题。作者在真实 FastAPI + React 仓库上实测，平均减少 54% 代码量、20% 成本并提升 27% 速度，同时保留了完整的安全护栏。

ComfyUI 近日登上 GitHub Trending，这款面向视觉专业人士的节点式 AI 创作引擎支持图像、视频、3D 与音频生成，提供桌面端、便携版、云端及 API 接入。其模块化架构让设计师能以无代码方式构建和复用复杂工作流，是目前生产级 AI pipeline 中控制力最强的开源工具之一。

Supabase 作为开源 Postgres 开发平台进入 GitHub 每日热门仓库榜，集成了数据库、认证、自动 API、边缘函数及 AI 向量工具包等能力。但本条内容仅是仓库常规简介的残片，既无具体版本发布，也未涉及设计师可直接采纳的工具更新或工程实践。

Twenty 近日登上 GitHub Trending，定位开源 Salesforce 替代方案。它让技术团队能用代码定义 CRM 对象、字段与视图，将业务配置纳入版本控制，并原生支持 AI Agent。对需要高度定制化且想用工程化方式管理业务逻辑的团队，这是比传统 SaaS 更灵活的底层基础设施。

Kronos 是首个针对金融蜡烛图（K线）的开源基础模型，基于全球45家以上交易所的OHLCV数据预训练，采用专业tokenizer将连续多维数据量化为层级离散token，再经自回归Transformer建模。其将专业时序数据“语言化”的架构思路，对处理用户行为序列等时序信息的设计师有跨领域启发。

ai-memory 为 Claude Code、OpenAI Codex 等 AI 编程 Agent CLI 提供长期记忆与跨厂商上下文交接能力。通过 MCP 配置和生命周期钩子，它能在不同 Agent 之间保留项目架构、失败尝试和待解决问题，实现无缝切换。

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]