TypeScript · ★ 33,277 · 🍴 2,707 · 📈 5,604 stars today
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
中文介绍 将任意代码库转化为可交互的知识图谱，支持节点探索、全文搜索和自然语言问答。与 Claude Code、Codex、Cursor、Copilot、Gemini CLI 等主流 AI 编程工具集成，帮助开发者快速理解陌生代码结构，降低大型项目的认知负担，适合代码审查、技术接手和架构分析场景。
Python · ★ 16,163 · 🍴 1,914 · 📈 1,441 stars today
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
中文介绍 Anthropic 官方开源的 Claude 插件集合，专为知识工作者设计，可在 Claude Cowork 环境中使用。插件覆盖文档处理、信息整合等知识型办公场景，帮助分析师、研究员、内容创作者等用 Claude 完成复杂信息任务，作为官方插件库具备较高可靠性和示范价值。
Python · ★ 19,636 · 🍴 3,286 · 📈 3,154 stars today
Learn it. Build it. Ship it for others.
中文介绍 面向 AI 工程师的从零学习资源库，涵盖理论学习、动手实践到项目交付的完整路径。适合希望系统掌握 AI 工程技能并能独立构建和发布产品的开发者，内容强调实战导向，帮助学习者跨越从概念到落地的鸿沟。
JavaScript · ★ 193,229 · 🍴 29,863 · 📈 2,025 stars today
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
中文介绍 面向 AI 编程 Agent 的性能优化框架，为 Claude Code、Codex、Opencode、Cursor 等工具提供技能管理、直觉训练、记忆系统和安全机制。采用研究优先的开发理念，系统性提升 Agent 的任务执行效率与安全性，适合需要深度定制 AI 编程助手能力的开发团队使用。
Python · ★ 9,610 · 🍴 1,157 · 📈 1,004 stars today
754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 26 security domains · Apache 2.0
中文介绍 为 AI 安全 Agent 提供 754 项结构化网络安全技能，同时映射到 MITRE ATT&CK、NIST CSF 2.0、MITRE ATLAS、D3FEND 和 NIST AI RMF 五大主流安全框架。遵循 agentskills.io 标准，兼容 Claude Code、GitHub Copilot 等工具，适合安全研究人员和 SOC 团队构建具备专业安全知识的 AI Agent。
TypeScript · ★ 26,561 · 🍴 1,483 · 📈 3,161 stars today
Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, OpenCode, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
中文介绍 为代码库预构建本地知识图谱索引，与 Claude Code、Codex、Cursor、OpenCode 和 Hermes Agent 集成，通过减少重复的代码检索 token 消耗和工具调用次数来提升 AI 编程效率。完全本地运行，保护代码隐私，适合有大型代码库且注重成本控制的团队日常开发使用。
Swift · ★ 19,674 · 🍴 1,480 · 📈 603 stars today
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
中文介绍 基于 Ghostty 构建的 macOS 终端应用，专为 AI 编程 Agent 设计，提供垂直标签页布局和系统级通知功能。针对同时运行多个 AI 编程任务的场景优化界面组织方式，让开发者在使用 Claude Code 等 Agent 进行长时间异步任务时能高效管理多个会话窗口。
★ 156,047 · 🍴 15,999 · 📈 2,749 stars today
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
中文介绍 以单个 CLAUDE.md 文件形式提供的 Claude Code 行为优化配置，内容提炼自 Andrej Karpathy 对大型语言模型编程常见陷阱的观察与总结。通过预设规则约束 Claude Code 的不良编码习惯，帮助开发者获得更可靠、更符合工程实践的代码输出，适合日常使用 Claude Code 的开发者快速安装使用。
Python · ★ 24,076 · 🍴 3,305 · 📈 317 stars today
FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment.
中文介绍 面向金融专业人士的现代化终端应用，集成高级市场行情分析、投资研究和宏观经济数据工具。采用交互式界面设计，支持数据驱动的决策流程，适合量化分析师、基金经理和金融研究员在命令行环境中高效获取和分析市场数据，替代部分传统 Bloomberg/Wind 终端功能。
Python · ★ 41,490 · 🍴 2,750 · 📈 176 stars today
A community-supported supercharged document management system: scan, index and archive all your documents
中文介绍 社区维护的开源文档管理系统，支持扫描、OCR 识别、自动索引和长期归档各类纸质与电子文档。基于 Django 和 Vue.js 构建，提供标签、自动分类、全文检索等功能，适合个人和小型团队告别纸质文档混乱，实现家庭或办公室文件的数字化无纸化管理。
Jupyter Notebook · ★ 44,226 · 🍴 5,059 · 📈 141 stars today
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
中文介绍 Anthropic 官方维护的 Claude 使用示例 Notebook 合集，以 Jupyter Notebook 形式展示各类实用且有趣的 Claude API 应用方式。覆盖多种典型任务场景，帮助开发者快速上手 Claude 的各项能力，适合希望探索 Claude API 最佳实践的工程师和研究人员参考学习。
Shell · ★ 20,336 · 🍴 1,671 · 📈 264 stars today
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
中文介绍 通过 Skill 配置文件为 AI 注入审美偏好，避免生成千篇一律、缺乏个性的平庸内容。针对 AI 写作、设计描述等创意输出场景，通过约束和引导使模型产出更具品味和独特性的结果，适合对 AI 创意内容质量有较高要求的写作者、设计师和内容创作者使用。
TypeScript · ★ 39,940 · 🍴 4,028 · 📈 62 stars today
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.
中文介绍 可自托管的开源 AI 虚拟伴侣框架，以 Grok 风格的 AI 角色为基础，支持实时语音对话、Minecraft 互动等多模态交互能力，目标对标 Neuro-sama 的技术水准。强调数据自主权（数据归用户所有），适合 VTuber 社区、AI 角色开发者和虚拟陪伴应用研究者部署和定制专属 AI 角色。
Python · ★ 26,269 · 🍴 4,559 · 📈 245 stars today
Kronos: A Foundation Model for the Language of Financial Markets
中文介绍 专为金融市场语言设计的基础大模型，能够理解和生成与金融市场相关的专业内容。针对股票行情、市场情绪、金融报告等领域进行训练，适合量化研究员、金融 NLP 工程师和资产管理机构用于市场分析、事件解读和投资决策辅助等专业场景。
JavaScript · ★ 4,842 · 🍴 244 · 📈 192 stars today
Curated list of the best free apps for PC and mobile
中文介绍 精心整理的 PC 与移动端优质免费应用清单，涵盖多个使用类别，帮助用户快速发现高质量免费替代工具。适合希望避免付费软件、寻找开源或免费工具的普通用户和开发者，是一份实用的软件选型参考索引，定期维护更新确保内容时效性。
★ 4,645 · 🍴 390 · 📈 345 stars today
A skill file for removing AI tells from prose
中文介绍 专门用于去除 AI 写作痕迹的 Skill 配置文件，针对 AI 生成文本中常见的套话、模式化表达和明显机器痕迹进行约束和修正。帮助作者、编辑和内容创作者获得更自然、更具人文质感的文字输出，适合对写作质量敏感、需要在专业场合发布内容的使用者。
TypeScript · ★ 102,881 · 🍴 15,335 · 📈 640 stars today
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
中文介绍 复刻 Garry Tan（Y Combinator CEO）Claude Code 完整工作流的配置集，包含 23 个角色化工具，分别扮演 CEO、设计师、工程经理、发布经理、文档工程师和 QA 等角色，形成完整的虚拟软件团队。适合独立开发者和小型创业团队借助 Claude Code 实现从产品决策到测试发布的全流程 AI 辅助开发。
👍 8
While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between interactions is largely wasted, leaving agents unable to pre
👍 7
In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven instance segmentation as a set-structured query prediction problem and propose an explicit reasoning-to-instance query
👍 4
Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Helix4D, a dynamic mesh generation framework by inheriting the expressive representation of Trellis2, adapting it from image-to-3D to video-conditioned 4D genera
👍 22
Sparse-view 3D reconstruction is increasingly addressed with feed-forward splatting networks that predict explicit primitives directly from images. Yet most existing methods remain centered on Gaussian primitives and expose surfaces only indirectly: extracting a usable mesh for downstream simulation
👍 11
Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate over only narrow slices of that world, limiting context-sensitive reasoning and effective assistance. Existing benchmarks
👍 1
Sparse encoders offer high-precision retrieval by representing term importance within a vocabulary space, yet their English-centric structures pose a critical impediment to language transfer for non-English languages. To overcome this structural limitation, we propose SemBridge, a novel embedding in
👍 20
Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders and frozen language backbones with output heads, recent efforts have shifted the paradigm toward native multimodal mode
👍 78
Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy Optimization, adapting it to real-world multi-reward setting
👍 15
Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging for perspective video generators due to their limited field of view (FoV). Their narrow FoV forces long or multi-view traj
👍 4
Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack of systematic studies on metaphorical video understanding not only constrains the real-world applicability of MLLMs but
👍 1
Mobile GUI agents powered by large language models have progressed rapidly, creating urgent needs for realistic and comprehensive evaluation. Existing benchmarks prioritize reproducibility but are often limited to open-source apps or file-operation tasks for the difficulty of constructing rewards on
👍 0
Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both faithful and informative, avoiding hallucination without omitting salient deta
👍 56
As personal agents evolve to handle complex, user-centric tasks, static plain-text chat is rapidly becoming a bottleneck. Generative UI emerges as the necessary new interface layer, dynamically synthesizing the right controls, options, and state from the interaction context in real time. We present
👍 7
Recent advances in generative models highlight the power of geometry-aware modeling in manifold-constrained settings. Yet, for natural images, the field remains confined to Euclidean assumptions, failing to exploit the potential of intrinsic geometric structures within the data. In this work, we inv
👍 2
Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as Agent-Environment Misalignment: the agent's capability frontier changes during trainin
👍 1
Translating text embedded in Web images is crucial for improving content accessibility and cross-lingual information retrieval, particularly within social media and e-commerce domains. Although Large Vision-Language Models (LVLMs) have advanced multimodal understanding, applying them to Web image tr
👍 1
Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine-tuning LLMs with parallel corpora presents major challenges, namely parameter interference. To address these issues, we propose Mix-MoE, a mixed Mixt
👍 1
Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace these failures to a fundamental mismatch. Streaming geometry is inherently tempora
👍 0
Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions, yielding strong performance on complex logical benchmarks. We hypothesize that such behaviors are beneficial only when the model has sufficie
👍 10
Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a diagnostic benchmark for evaluating this step from experience reuse
👍 19
Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task
👍 51
Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. As these systems scale, the bottleneck shifts away from raw model capability toward coordination. Agents need to form rel
👍 21
Scientific research is being reshaped by AI systems that move beyond isolated assistance toward longer-horizon workflows spanning literature grounding, hypothesis generation, experimentation, validation, reporting, and revision. This shift marks a transition from task-level AI for science to workflo
👍 0
MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions. This ambiguity becomes more severe under high acceleration, where pixel-domain continuous predictors tend to average over feasible reconstructions and suppress high-frequency
👍 3
Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capabilities. This problem is further exacerbated by malicious model publishers who use evasive, or indirect, contamination
👍 3
Scaling test-time compute by iteratively updating a latent state has emerged as a powerful paradigm for reasoning. Yet the internal mechanisms that enable these iterative models to generalize beyond memorized patterns remain unclear. We hypothesize that generalizable reasoning arises from learning t
👍 28
Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video understanding. However, existing native-RL methods dispatch tool calls sequentially (i.e., one per turn): a single wrong crop
👍 16
Computer-aided design (CAD) is the backbone of modern industrial design, yet learned CAD generators still fall short of real engineering pipelines: they neither iterate like engineers nor evaluate what engineering requires. Prior work has treated CAD generation as two disjoint steps, part synthesis
👍 7
Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from significant maintenance overhead due to two key limitations: coarse-gr
👍 4
Unified multimodal understanding and generation models enable richer human-AI interaction. Yet jointly customizing a character's persona, dialogue style, and visual identity while maintaining output consistency across modalities remains largely unexplored. To mitigate this gap, we introduce a new ta
@sairahul1 · 106.0K 粉丝 · 1.4M 阅 · 744 赞 · 87 转
I thought I was using AI to code. I was actually just typing faster. Here is the difference — and the 7-agent system that changed everything. Save this. It will save you months. THE PROBLEM NOBODY
中文介绍 作者分享了一套7个子 Agent 协作的「软件工厂」架构，用 Claude Code 实现自动化功能交付。核心观点：过去只是「用 AI 打字更快」，而非真正自动化。该系统可在无人值守时持续推进开发任务，适合想从「辅助编码」升级到「全流程自动化」的开发者。
@sairahul1 · 106.0K 粉丝 · 203.2K 阅 · 500 赞 · 82 转
Everyone is talking about AI agents in 2026. Most people have no idea how they actually work. This changes today. I spent weeks distilling everything: courses, books, real builds, production failures.
中文介绍 作者历时数周整理了一份 AI Agent 完整学习路径，涵盖课程、书籍、实际构建案例和生产环境踩坑经验。面向2026年依然对 Agent 工作原理一知半解的人群，定位为系统性入门到实战的综合指南。
@cyrilXBT · 179.9K 粉丝 · 127.8K 阅 · 533 赞 · 80 转
Most people start their day the same way. They open Twitter and spend 20 minutes scrolling through noise looking for the three things that actually matter. They open their email and get pulled into
中文介绍 教程分享：用 Claude 构建每日早晨自动浏览互联网、5分钟内生成简报的研究 Agent，替代每天刷 Twitter 和邮件筛选信息的低效习惯。解决「信息噪音多、有效信号少」的痛点，适合需要每日快速获取关键动态的用户。
@poteto · 26.6K 粉丝 · 86.5K 阅 · 540 赞 · 48 转
I need to get something off my chest. Before my interview @cursor_ai, I had never actually used Cursor. At Meta, Claude Code was explosively taking off. I even paid for a personal $200 a month plan
中文介绍 作者坦言加入 Cursor 前从未真正用过该产品，此前在 Meta 一直重度使用 Claude Code（个人付费$200/月）。帖子分享了他切换到 Cursor 后的实际使用方式与体验对比，属于难得的「内部人视角」真实评测。
@TheAhmadOsman · 59.9K 粉丝 · 54.5K 阅 · 512 赞 · 65 转
At some point, reading about LLMs stops being enough. You need to build the stack yourself: Tokenizer first, then embeddings, position, attention, Transformer blocks, objectives, decoding, cache, long
中文介绍 2026版 LLM 工程实战项目路线图：从头构建完整技术栈——Tokenizer → Embedding → Position Encoding → Attention → Transformer → 解码策略 → KV Cache → 长上下文处理。强调「读文章不够，必须亲手搭」，适合想深入理解底层原理的工程师。
@hansolar21 · 30.1K 粉丝 · 50.8K 阅 · 500 赞 · 82 转
tldr: Korea is already being repriced as an AI memory market. But I think the next leg could be Physical AI: robots, actuators, reducers, and the boring precision-machining companies sitting
中文介绍 投资视角分析：韩国已作为 AI 内存市场被重新定价，作者认为下一波机会在 Physical AI——机器人、执行器、减速器及精密机加工零部件企业。点名韩国汽车零部件供应链中被市场忽视的「无聊」精密制造公司可能迎来重估。
@KSimback · 17.1K 粉丝 · 40.0K 阅 · 508 赞 · 69 转
TLDR: this is your definitive guide to all things related to memory systems for Hermes Agent. Why create this? Because every week I see new posts or articles describing some new memory tool for Hermes
中文介绍 针对 Hermes Agent 的记忆系统全面指南，整理了各类记忆工具与架构方案。作者称每周都看到新的「记忆工具」文章却缺乏系统梳理，因此制作这份「权威手册」，帮助开发者理清 Agent 记忆机制的设计选择与最佳实践。
@difflawb · 20.3K 粉丝 · 21.9K 阅 · 1.1K 赞 · 389 转
How a 40-line shell script became infrastructure In August 2024, Andrej Karpathy — co-founder of OpenAI, former AI Director at Tesla — published something unexpectedly small. Not a paper. Not a model.
中文介绍 回顾 Andrej Karpathy 2024年8月发布的一个40行 Shell 脚本如何演变为重要基础设施。帖子以这个「不起眼的小东西」为切入点，探讨极简工具产生深远影响的现象，属于技术历史与工程哲学类内容。
@0xileri · 7.3K 粉丝 · 12.2K 阅 · 533 赞 · 63 转
I’ve been getting a lot of DMs since I started posting AI videos, so I figured I’d just write it all out. Fair warning: I’m still learning too. This is just what’s been working for me. tools
中文介绍 AI 视频制作新手向教程：作者回应大量私信，整理了自己制作 AI 视频的完整工具链与工作流程。定位初学者，强调「仍在摸索中」的真实状态，适合刚开始尝试 AI 生成视频创作的人参考入门。
@ActionModelAI · 57.1K 粉丝 · 5.8K 阅 · 505 赞 · 344 转
We are witnessing the beginning of the biggest economic shift in modern history. And most people still don’t realize it. AI replacement is no longer some distant sci-fi prediction. It has started.
中文介绍 观点类帖子，主张 AI 替代就业已从预测变为现实，称当前是「现代史上最大经济转型的起点」。内容以危机感叙事为主，缺乏具体数据支撑，属于 AI 冲击劳动市场这一老话题的常见论调重述。
OpenAI partners with Grupo Folha and Grupo UOL to bring trusted Brazilian journalism to ChatGPT, expanding access to news with attribution and transparency.
a quiet day lets us tie together a few quotes as all model labs become agent labs
During Tuesday’s Google I/O keynote, Demis Hassabis, the CEO of Google DeepMind, proclaimed that we are currently “standing in the foothills of the singularity.” It was a striking statement—the singularity is the theoretical future moment when AI rapidly exceeds human intelligence and dramatically t
a quiet day lets us feature fundraises!
How Virgin Atlantic used Codex to ship its revamped mobile app on a fixed holiday travel deadline, reaching near-total unit test coverage and zero P1 defects.
OpenAI is named a leader in the 2026 Gartner Magic Quadrant for Enterprise AI Coding Agents, with Codex recognized for innovation and enterprise-scale deployment.
Listen to the session or watch below AI companies want to build systems that understand the external world and overcome the limitations of LLMs. Recent developments have brought world models to the forefront of the AI discussion. Watch a conversation with editor in chief Mat Honan, senior AI editor
We chat with Daytona's CEO about their insane 74% MoM Growth, 850K Daily Runs, Bare Metal Sandboxes, RL Evals, and the New Agent Cloud
Storytelling is core to humanity’s DNA, stemming from our impulse to express ideals, warnings, hopes, and experiences. Technology has always been woven through the medium and the distribution: from early humans’ innovation of natural pigments and charcoals for cave paintings to literal representatio
本期21个候选标的的技术面呈现明显分化格局。美股权益类整体延续多头排列，SPY当前价745.64，高于SMA20（731.58）/SMA50（696.68）/SMA200（678.85），RSI14为68.8，接近超买边缘，但MACD已出现死叉（12.35 vs 13.31），暗示短期上行动能有所收窄。QQQ与AAPL的RSI分别达71.4与78.4，均已进入超买区域，多头结构完整但动量钝化信号值得关注。相比之下，META与MSFT在板块内表现明显偏弱，META价格低于三条均线，MACD深陷负值区间，呈空头排列。加密板块整体承压：比特币现价76621，低于SMA20/SMA50/SMA200，MACD深度负值（-257.46），结合加密恐慌贪婪指数仅34（处于恐慌区间）、加密总市值24小时回落0.94%至2.64T、BTC主导率维持58.2%，显示加密资金持续向BTC集中但整体情绪低迷，ETH与SOL亦均呈空头排列。中概股技术面普遍偏弱，BABA、PDD、JD、腾讯控股均跌破多条均线，腾讯RSI14仅33.9，PDD接近52周低位。商品及外汇方面，WTI原油5日跌幅达-14.26%，技术面压力最重；黄金期货高位回调，低于SMA20与SMA50；美元指数DXY接近52周高位，多头排列，而USDCNY持续走弱并临近52周低位，反映人民币相对强势。宏观指标方面，VIX维持16.75的相对低位，10年美债收益率4.56%高于三条均线，多头排列延续，对风险资产形成一定背景压力。
当前价格717.54，位于SMA20（694.91）、SMA50（642.10）、SMA200（614.66）三线之上，呈多头排列。RSI14读数71.4，已进入超买区域，MACD值20.43虽出现死叉（信号线21.78略高），直方图转负，动量有所收窄。近5日涨幅+1.21%，距52周高仅-0.63%。技术上强势结构维持，但RSI超买叠加MACD死叉提示短期动能或有放缓。
当前价格76621.49，低于SMA20（78595）、SMA50（77093）与SMA200（80272），三线呈空头排列。RSI14为45.5，位于中轴下方。MACD为-257.46，远低于信号线134.72，MACD柱深度负值显示下行动量强烈。近5日跌幅-1.18%，距52周高-39.28%。结合加密恐慌贪婪指数仅34（恐慌区间），加密总市值24h下降0.94%，整体技术面持续承压。
当前价格610.26，低于SMA20（619.10）、SMA50（617.81）与SMA200（669.43），三线呈空头排列。RSI14为45.3，逼近中轴下方。MACD为-7.10，信号线-6.07，MACD直方图继续负值扩大，空头动能强化。距52周高-23.36%，近5日下跌-0.65%。与美股科技板块整体偏强形成背离，技术面显著偏弱。
当前价格308.82，站于SMA20（289.35）、SMA50（270.55）、SMA200（261.55）全部三线之上，多头排列清晰。RSI14达78.4，深度超买。MACD9.97高于信号线8.99，直方图正值，动量延续。近1日+1.26%，近5日+2.86%，距52周高仅-0.83%。技术强势明确，但RSI超买程度在本组中最高，需关注超买修正风险。
当前价格93.17，近1日暴跌-3.55%，近5日跌幅高达-14.26%，为本组跌幅最大标的。价格低于SMA20（100.82）与SMA50（98.27），MACD出现死叉（0.45 vs 信号线1.54），直方图转负。RSI14为43.3，偏低于中轴。距52周高-22.02%，短期下行动量显著，技术面呈现明确弱势格局。
VIX 恐慌指数
10Y 美债收益率 (%)
美元指数 DXY
S&P 500 ETF
Nasdaq 100 ETF
Apple
Microsoft
Nvidia
Alphabet
Tesla
Meta
Bitcoin
Ethereum
Solana
阿里巴巴 (BABA)
拼多多 (PDD)
京东 (JD)
腾讯控股 (0700.HK)
黄金期货
WTI 原油期货
美元 / 人民币
本报告所有内容均基于公开行情数据计算所得技术指标，仅供技术指标解读参考，不构成任何投资建议或买卖信号。过去走势不代表未来表现，市场存在不确定性，投资者须自行承担决策风险。
Mojtaba Khamenei, Iran’s supreme leader, said that after the war Gulf nations would no longer be “shields” for U.S. bases.
中文摘要 伊朗最高领袖哈梅内伊表示，战争结束后海湾国家将不再能成为美国军事基地的"盾牌"，警告称美国在中东地区的军事基地将不再安全。此言论发布于美伊紧张局势持续升级之际。
Five of the deaths were by drowning while two people died competing in sporting events The French government has said seven people have died in an extreme early-summer heat event hitting a swathe of western Europe, as France and the UK set record highs for May, and with temperatures forecast to rise
中文摘要 法国政府确认，因一场席卷西欧多国的极端早夏热浪，已有7人死亡，其中5人溺亡，2人死于体育竞技活动。此次热浪期间，法国和英国均创下5月份气温历史新高。
The driver and passengers of the car managed to escape before the bridge gave way in Xiaogan.
中文摘要 中国湖北孝感市一座桥梁发生坍塌，一辆行驶中的汽车被冲入河中。车内驾驶员及乘客在桥梁垮塌前及时逃脱，未造成人员伤亡。
At the prestigious garden show, attendees jockeyed to buy prizewinning blooms and debated the role of whimsy as a ban on garden gnomes was temporarily lifted.
中文摘要 英国切尔西花展期间，主办方临时解除了长期实施的花园地精禁令，引发观众热议。参展者争相购买获奖花卉，围绕是否应在这一顶级园艺展中引入趣味元素展开讨论。
The co-founder of a prominent A.I. company was nearby as the pope implored A.I. leaders to slow down and consider the technology’s possible perils.
中文摘要 教皇利奥在一场人工智能领袖出席的场合呼吁各方放慢AI发展步伐、审慎评估潜在风险。一家知名AI公司联合创始人当时就坐在距教皇仅3个席位之处，此细节引发外界关注教皇在AI议题上的立场与影响力。
Haitian women are having babies in squalid, unsupervised settings after the Dominican Republic started sending immigration agents to detain migrants at hospitals.
中文摘要 多米尼加共和国向医院派驻移民执法人员拘押非法移民，导致大量海地孕妇因惧怕被驱逐出境而不敢前往医院就诊，被迫在卫生条件恶劣、缺乏医疗监护的环境中分娩，母婴安全风险显著上升。
Lenacapavir, which protects people from H.I.V. infection with twice-yearly shots, is arriving in a country where the health system has been hollowed out by American aid cuts.
中文摘要 每半年注射一次的强效HIV预防药物来那卡帕韦（Lenacapavir）已抵达赞比亚。然而，受美国对外援助大幅削减影响，赞比亚医疗体系已严重受损，药物能否顺利送达最需要人群仍存在较大不确定性。
Thousands who fled Russia after the invasion of Ukraine have built an enclave in Phuket. An air of impermanence hangs over their community.
中文摘要 俄罗斯入侵乌克兰后，数千名出走俄罗斯的民众在泰国普吉岛形成聚居社区，生活状态整体尚可。但受局势不确定性影响，这一群体普遍笼罩在去留未定的漂泊感之中。
Cohort of 12 children and seven women who were held in a Syrian camp arrived in Australia on Tuesday Follow our Australia news live blog for latest updates Get our breaking news email, free app or daily news podcast A group of 19 Australian women and children held in Syria since the defeat of Islami
中文摘要 一批与伊斯兰国有关联、长期被关押于叙利亚营地的澳大利亚籍人员已返回澳大利亚，共19人，包括12名儿童和7名女性，分别抵达墨尔本和悉尼，当局预计不会对其实施逮捕。
The court said the man poisoned the tycoon for sidelining him after he helped secure a deal with Netflix for the 3 Body Problem.
中文摘要 中国一名男子因谋杀知名游戏大亨被执行死刑。法院认定，该男子曾协助促成游戏公司与Netflix就《三体》签订合作协议，但随后遭大亨冷落排挤，因而采取投毒手段将其杀害。
Survivors of a suspected drone strike while fishing in the Eastern Pacific seek restitution after claiming they were forced onto a boat and handed over to Salvadoran officials, with no charges filed.
中文摘要 数名在东太平洋海域捕鱼时疑遭无人机袭击的厄瓜多尔幸存者正寻求赔偿。他们声称事后被强行押送至一艘船上并移交萨尔瓦多当局，至今未受任何指控，事件真相尚无定论。
Dozens of ICE agents clashed with protesters using pepper spray to disperse crowds outside a detention centre.
中文摘要 数十名美国移民和海关执法局（ICE）特工与在某拘留中心外聚集的抗议者发生冲突，执法人员动用胡椒喷雾驱散人群，现场局势一度紧张。
As Kyiv recovers from a Russian attack that hit every district in the Ukrainian capital, Ukraine continues long-range strikes on Russia's war machine even as the Kremlin threatens more strikes.
中文摘要 俄罗斯对基辅发动导弹与无人机袭击，攻击覆盖乌克兰首都所有行政区，克里姆林宫随后威胁将实施更多打击。与此同时，乌克兰持续对俄罗斯军事设施展开远程反击。
How desperate is Russian President Vladimir Putin to get a decisive win in Ukraine? NPR's Steve Inskeep asks Hanna Notte of the James Martin Center for Nonproliferation.
中文摘要 NPR主持人史蒂夫·英斯基普就俄乌局势专访詹姆斯·马丁防扩散研究中心分析师汉娜·诺特，探讨普京在最新一轮攻势后的战略意图，以及其迫切寻求决定性胜利的程度。
Mojtaba Khamenei makes apparent posting on his Telegram channel saying that Gulf powers can no longer be a shield for US bases US strikes Iran missile sites and mine laying vessels Iranian supreme leader Mojtaba Khamenei said on his Telegram channel that Gulf powers will no longer be a shield for US
中文摘要 美国对伊朗导弹阵地及布雷船只实施打击，伊朗最高领袖哈梅内伊随后在Telegram发文警告，海湾国家将不再能充当美国军事基地的屏障，美国在中东地区将不再拥有安全港湾。
Also in today’s newsletter: shrinking real wages and bank deregulation
中文摘要 美国对伊朗导弹基地发动空袭，此举成为当前地缘政治紧张局势的重要节点。与此同时，相关议题还涉及实际工资缩水及银行业放松监管等动向。
The Academy of Medical Royal Colleges says doctors should routinely check on screen time and social media use when seeing younger patients.
中文摘要 英国皇家医学院学会发表声明，称屏幕时间对儿童造成伤害已有「压倒性共识」，建议医生在接诊青少年患者时，应常规询问其屏幕使用时长及社交媒体使用情况。
Japan’s May crude oil imports are expected to rebound to around 1.7 million barrels a day, roughly three-quarters of the level a year earlier, as refiners step up alternative procurement while the Strait of Hormuz remains largely closed.
中文摘要 受霍尔木兹海峡基本封闭影响，日本炼油商加快寻找替代原油来源。预计5月原油日进口量将反弹至约170万桶，较4月有所回升，但仍约为去年同期水平的四分之三。
Karen Ward, JPMorgan Asset Management's EMEA chief market strategist, says that investors are looking beyond the current geopolitical uncertainty to the investment opportunities resulting from increased public and private spending. "The more chaotic the world becomes, the more that's creating spendi
中文摘要 摩根大通资产管理公司欧中东非区首席市场策略师Karen Ward表示，投资者正将目光投向当前地缘政治不确定性之外，关注公共及私人支出增加所带来的投资机会，认为股市将从中受益。
More people are taking second jobs as rising costs and insecure work reshape how we earn a living.
中文摘要 随着生活成本上升及就业不稳定性加剧，越来越多的人选择兼职第二份工作以维持生计，多职并存现象正在重塑当代劳动者的收入结构。
The “Indian curry” lunch is a Japanese staple — and a steal at only 1,000 yen ($6.40) or so. Bloomberg Opinion columnist Gearoid Reidy explains why the beloved meal may be under threat. (Source: Bloomberg)
中文摘要 日本「印度咖喱」午餐长期以约1000日元（约6.4美元）的亲民价格深受欢迎，是日常饮食中的代表性平价餐。彭博观点专栏作者Gearoid Reidy分析认为，这一廉价午餐正面临成本上涨等多重威胁。
Extending our consciousness, one risk factor at a time
中文摘要 《金融时报》对一份引发广泛关注的S-1招股说明书进行延伸解读，逐项梳理其中的风险因素，探讨该文件所揭示的深层商业与监管议题。
Some palm oil refiners in Indonesia are avoiding buying fruit from small farmers, a sign of how the government’s commodity export overhaul risks squeezing grower incomes and crimping supplies of the crop.
中文摘要 印度尼西亚政府推进棕榈油出口制度改革，部分棕榈油精炼商开始拒绝从小农手中收购棕榈果，导致大量果实烂在田间。此举显示政策调整正在压缩小农收入并影响供应。
TikTok owner issues shares tied to AI business unit as China’s tech talent war heats up
中文摘要 TikTok母公司字节跳动向人工智能业务部门员工发放与AI业务挂钩的专项股票，以应对中国科技人才争夺战升温的局面，防止核心AI团队被竞争对手挖角。
Hong Kong-listed biotech firm Insilico Medicine Cayman TopCo is considering a secondary listing in Abu Dhabi, people familiar with the matter said, in a deal that would make it the first company from outside the Gulf to list shares on a regional exchange.
中文摘要 知情人士透露，在港上市的AI生物科技公司英矽智能（Insilico Medicine）正考虑在阿布扎比进行二次上市，若成功将成为首家在海湾地区交易所挂牌的非海湾国家企业。
Indonesia is probing some of the world’s biggest palm-oil companies for suspected export abuses, adding to the upheaval in the industry days after the government announced a plan to nationalize shipments of the crop.
中文摘要 印度尼西亚政府正对多家全球大型棕榈油企业展开调查，涉嫌出口价格违规。此次调查发生在政府宣布将国有化棕榈油出口计划后数日，进一步加剧该行业动荡。
A surge in Copenhagen home prices is spilling over to the rest of Denmark, posing growing risks to the country’s lenders, the central bank said.
中文摘要 丹麦央行发出警告，哥本哈根房价大幅上涨正向全国蔓延，给国内银行体系带来日益上升的风险，呼吁各方关注房地产市场过热问题。
4 回复 · Apple 节点
40 回复 · Apple 节点
10 回复 · Apple 节点
6 回复 · Apple 节点
27 回复 · Apple 节点
4 回复 · Apple 节点
6 回复 · Apple 节点
4 回复 · Linux 节点
7 回复 · Python 节点
3 回复 · Linux 节点
就这个对话流 操作信息展示详细程度 能给你三档设置这一点细节就薄纱各路编辑器了 关于 2.1.20 上线的 collapsed read/search groups 你可以说 Agent Window 嗯 “抄” 的像 Codex Desktop 你信OpenAI对 Electron 的掌控实力还不如 信 Cursor 从 VSCode 那天然获得的性能优化 我只要想到他那坨架构 天天ab测试的开这个不开那个gate 我就三个头都大 某种程度上还不如 Claude Desktop 简单套个壳子来的清爽 更别说 Cursor checkpoint 和 多路模型可切换 上下文接续了 不再推进 Co
@sebastianjuly 这位老哥上手就来了一句让人摸不着头脑的发言，接着就跟自己互博，种种行为非常令人费解。 去查了一圈，很可能是AI养号，申请自述和加入缘由也是AI生成，直接送走。 这是第一例，绝不会是最后一例。 1 个帖子 - 1 位参与者 阅读完整话题
大家再使用公益站链接codex 的时候应该都会跟我一样遇到一些小问题 无法使用codex中的插件功能，可以用codex++去解决：GitHub - b-nnett/codex-plusplus: Codex++ tweak system for the Codex desktop app · GitHub 我使用了但是发现mac的软件兼容性不太好，不太稳定 cc switch 切换key之后的历史记录丢失，可以用： GitHub - Dailin521/codex-provider-sync: Synchronize Codex session provider metadata across
最近测试注册机搞出来的hotmail，大部分为长效，已经活了几天了 用cdk方式领 cdk.linux.do LINUX DO CDK Linux Do 社区 CDK 快速分享平台 - 让分享变得更简单 16 个帖子 - 14 位参与者 阅读完整话题
聊天生图站主帖：【Picpi Chat 工艺站】支持聊天和 image2，支持上传图片，文生图，图生图，正式上线！ 【picpi 皮皮公益站】已3个月稳定不中断！ 主力模型:OpenAI Codex 从 【picpi 皮皮工艺站】开放注册，不再是邀请制，但是订阅仍需LDC购买。 继续 现在已经把聊天站和OpenAI Codex站整合在了一起。 由于邮箱一直爆炸，所以搞了一个新网站专门用于注册。这样就不会炸了。注册之后就可以愉快的聊天生图啦！ regapi.picpi.top picpi sub2api 注册 25 个帖子 - 19 位参与者 阅读完整话题
动态： 刚刚，全球权威编程榜单 Code Arena正式放榜，千问最新旗舰模型 Qwen3.7-Max得分 1541，超越GPT-5.5、Gemini-3.5-Flash、GLM-5.1、Kimi-K2.6等一众模型，仅次于Claude系列，在大模型厂商中排名全球第二。 全球权威编程榜单 Code Arena 编程突出的 Qwen3.7-Max 感谢全球开发者的每一次投票和反馈，我们将继续努力，打磨更好的模型给大家。 链接： 千问大模型的动态 - 哔哩哔哩 62 个帖子 - 54 位参与者 阅读完整话题
狂欢之后是一地鸡毛。。。 27 个帖子 - 26 位参与者 阅读完整话题
1. 先介绍一下我的个人情况 我是本硕先学计算机后生物信息，毕业后在一家生信公司干线上产品的后端开发，刚入职前半年对工作非常有干劲，天天最后走，自己帮公司做AI产品（就是 RAG 产品），到了年底把产品上线使用了，然后我就去和总监谈薪资，说工资太低了租不起附近的房子，他反过来对我说当年毕业他也是这样。我心想你他妈毕业是多少年前的事了（他14年是8k吧好像）。 第二年的 3、4 月份是公司涨薪的日子，我提前找到他们要求给我涨薪，一顿操作下来说我基数太低，只能涨 800。。。骗傻子跟我说是 HR 意思，后面根据其它事情我发现明明就是不愿给争取。从这开始心态就变了，到点就下班，活只干分来的，剩下的时
谁教的它，比我还装 注入的应该是kiro的内置提示词，这个没有手动去掉 我没招了家人们 39 个帖子 - 29 位参与者 阅读完整话题
https://linux.do/t/topic/1830937 —项目地址在此贴！！ fast模式轻松简单配置 或者使用/fast也能同步开启 快速配置文件-多种配置方式任你挑选 直接导入cc-switch快速配置 多主题配置 高清背景图-支持导入mp4 如果对你有帮助的话 给我star吧 12 个帖子 - 11 位参与者 阅读完整话题