JavaScript · ★ 263,722 · 🍴 39,453 · 📈 826 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 一套针对 AI 编程代理（如 Claude Code、Codex、Cursor 等）的性能优化系统。该项目通过集成技能、直觉、记忆和安全机制，并结合研究优先的开发理念，显著提升编码代理的执行效率与代码质量。适用于希望增强 AI 辅助编程工具能力、实现自动化开发流程的高级开发者与技术团队。
TypeScript · ★ 5,200 · 🍴 484 · 📈 98 stars today
A framework for building agentic apps
中文介绍 一个专为构建代理（Agent）应用而设计的开发框架。它提供了完整的底层架构支持，帮助开发者快速搭建具备自主决策和执行能力的应用程序。适用于正在探索 LLM 代理落地场景、需要构建智能自动化工作流或个性化交互体验的后端及全栈工程师。
JavaScript · ★ 18,001 · 🍴 998 · 📈 2,428 stars today
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
中文介绍 专为编码代理设计的多阶段安全审计技能插件。它能够自动执行代码安全扫描，并输出经过独立验证、机器可读的审计发现报告。适用于在 CI/CD 流程中集成自动化安全检查、提升代码库安全防护水平的开发者与安全工程师。
HTML · ★ 25,142 · 🍴 1,729 · 📈 1,018 stars today
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
中文介绍 旨在推动“计算机使用 2.0”技术发展的开源项目。提供跨操作系统驱动、标准化基准测试以及数据生成工具，用于训练和评估 AI 代理操作计算机的能力。适用于希望研究 GUI 自动化、开发桌面端智能代理或构建大规模跨平台操作数据集的 AI 研究者与工程师。
Python · ★ 35,357 · 🍴 5,248 · 📈 260 stars today
中文介绍 Anthropic 推出的金融服务领域专属资源库。该项目针对金融行业特点，提供结合 Claude 大模型的专业能力与工具集，助力开发者构建合规、高效的金融 AI 应用。适用于涉及智能投顾、金融数据分析、自动化报告生成等场景的金融科技企业与相关开发者。
Python · ★ 45,559 · 🍴 3,146 · 📈 57 stars today
A community-supported supercharged document management system: scan, index and archive all your documents
中文介绍 社区支持的增强型文档管理系统。支持批量扫描、OCR 文本识别与自动化分类，可将各类纸质文档转换为可检索的数字档案。适用于需要实现无纸化办公、管理家庭或企业海量文档、并追求高度自定义与自托管体验的个人及企业用户。
TypeScript · ★ 147,116 · 🍴 24,058 · 📈 419 stars today
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
中文介绍 运行在终端中的 Claude 智能编程工具。它能深度理解本地代码库结构，自动执行常规开发任务、解释复杂代码并协助管理 Git 工作流。适用于追求高效开发体验、希望将 AI 融入日常命令行工作流的专业软件工程师。
Python · ★ 4,549 · 🍴 1,009 · 📈 172 stars today
Assignments for CS146S: The Modern Software Dev (Stanford University Fall 2026/2025)
中文介绍 斯坦福大学 CS146S《现代软件开发》课程的配套作业与教学资料。内容涵盖现代软件工程的核心理念与实践方法，提供结构化的练习题。适用于软件工程学习者、开发者以及希望系统性提升现代软件开发规范意识的技术学生。
Jupyter Notebook · ★ 5,371 · 🍴 956 · 📈 465 stars today
Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters
中文介绍 一款容错且高扩展性的 GPU 编排与机器学习框架。专为训练数十亿至数万亿参数的大模型而设计，提供底层硬件调度与模型训练的全链路支持。适用于需要处理超大规模分布式 AI 训练任务、追求高计算效率的研究机构与大模型研发团队。
TypeScript · ★ 16,807 · 🍴 2,133 · 📈 755 stars today
OpenStock is an open-source alternative to expensive market platforms. Track real-time prices, set personalized alerts, and explore detailed company insights — built openly, for everyone, forever free.
中文介绍 开源的免费金融市场数据平台，旨在替代昂贵的商业行情服务。支持实时股票价格追踪、个性化价格预警及详细公司信息查询。适用于独立开发者、个人投资者以及需要低门槛获取实时金融数据的应用构建者。
Go · ★ 16,042 · 🍴 1,541 · 📈 379 stars today
Secure environments for developers and their agents
中文介绍 为开发者及其 AI 代理提供的安全隔离工作环境。支持快速部署标准化、隔离的开发容器，确保敏感代码与数据在沙箱中安全运行。适用于需要管理多团队开发环境、引入 AI 代理进行自动化编码且对数据安全有严格要求的企业。
TypeScript · ★ 17,295 · 🍴 919 · 📈 291 stars today
The Generative UI framework
中文介绍 Vercel 实验室推出的生成式 UI 框架。支持通过 JSON 数据直接渲染动态用户界面，简化了组件化与前端状态的同步开发流程。适用于需要快速构建数据驱动界面、实现后端直出 UI 或进行 LLM 生成界面渲染的全栈开发者。
JavaScript · ★ 97,677 · 🍴 10,295 · 📈 736 stars today
Production-grade engineering skills for AI coding agents.
中文介绍 由知名前端专家 Addy Osmani 整理的生产级 AI 编程代理工程技能集。系统总结了在实际项目中使用 AI 代理进行高效、安全、高质量代码编写的最佳实践。适用于希望规范团队 AI 辅助开发流程、提升代码输出质量的技术负责人与资深工程师。
👍 135
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transf
中文介绍 针对长上下文Agent工作负载中KV Cache严重占用HBM与SSD的问题，提出DeepSeek-V4.1-Flash，通过更激进的KV Cache压缩降低prefill与存储瓶颈，提升长序列推理效率。
👍 114
Recent Omni-Modal Generative Models (Omni-Models) have advanced content generation toward unified modeling of text, images, video, and audio. MiniMax-H3 exemplifies this transition by combining multimodal context understanding with joint audio-visual generation in a shared latent framework. Its unif
中文介绍 评测MiniMax-H3这一Omni-Modal生成模型在物理世界推理上的能力，考察其在统一文本、图像、视频与音频表征框架下的多模态生成与物理常识一致性表现。
👍 94
We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify termination-token mismatch between base students and post-trained teachers as an important source of this behavior. Across Qwen3, Llama,
中文介绍 研究on-policy distillation中学生回答过长（length inflation）的问题，发现基础学生与后训练教师之间终止token不一致是重要成因，并在Qwen3、Llama等模型上验证。
👍 94
As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback. Token efficiency therefore becomes important for scaling recursive self-improvement. We take an
中文介绍 提出SoL-Pi，通过递归扩展自动研究循环来提升编码Agent的token效率，使Agent在长期无人值守探索中实现递归自我改进。
👍 79
Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the sci
中文介绍 提出ScienceIDE，将全球科学代码库转化为Agent可学习的执行环境，解决领域约定隐性、正确性标准特殊等「科学转换难题」，提升Agent对科研代码的掌握能力。
👍 71
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the effectiveness of individual components unclear. To enable component-level comparison
中文介绍 实证研究编码Agent中harness设计的组件级影响，将harness拆解为独立部件进行对比，揭示各组件对长程软件工程表现的贡献，弥补以往整体评估的不足。
👍 56
World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling across radically different systems? We introduce JEPA-Anything, a domain-agnostic fram
中文介绍 提出JEPA-Anything，一种领域无关的世界建模框架，使单一学习原则能够支撑跨不同系统的预测建模，提升智能体对未来状态与环境后果的预判能力。
👍 56
Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated estimate of the probability that an output is correct decides what to ship, what to escalate, and what to retry. Existing confidence estimators, however, share one design premise: th
中文介绍 提出基于经验的语言模型置信度估计方法，从推理与Agent场景学习历史经验来校准输出正确概率，辅助部署决策、升级与重试判断。
👍 50
Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web development, however, agents may need to infer behavior from working software and implement it in an incomplete application. We introduce ProgramDistill, a benchmark evaluating codi
中文介绍 提出ProgramDistill基准，从可运行Web应用逆向生成带可验证参考的SWE任务，评估编码Agent在未完成任务中推断并复现行为的能力。
👍 48
LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situations from subjective user narratives, and (ii) social properties, such as others'
中文介绍 提出面向LLM助手的可验证社交推理评测，要求助手从用户主观叙述中学习社交情境，并对他人意图、情绪等社交属性进行有据可查的推理。
👍 45
Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an index that represents each document through index keys, retrieval quality depends heavily on how effectively these keys expose the knowledge containe
中文介绍 提出Self-Evolving Search Index，让检索索引的关键字表示随查询与Agent任务需求动态演进，从而提升LLM Agent在复杂信息检索任务中的检索质量。
👍 45
Autonomous research loops such as AutoResearch show that one coding agent can improve a training setup unattended. Run several of them and each session starts from scratch, so more agents tend to mean more duplicated search rather than more discovery. Agora is a shared memory for such agents: resear
中文介绍 提出Agora，以Git作为共享记忆供多个AutoResearch Agent协作，避免各Agent从零开始重复搜索，实现集体自动研究的累积式知识共享与协同改进。
👍 42
Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundant symbols, then route users through disguised links to services associated with pornography, fraud, gambling, or illicit transactions. Existing benchmarks evaluate obfuscated text
中文介绍 提出RiskChainBench，评测模型对社交平台伪装消息（表情、谐音、拆字等）的还原能力，以及基于证据的网页调查能力，覆盖色情、诈骗、赌博等滥用链路。
👍 39
Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher with privileged task skills, letting a skill-free student internalize them. This rec
中文介绍 提出RetireOPD，一种用于Agentic RL的自淘汰on-policy蒸馏方法，通过淘汰低价值样本提供稠密token级监督，帮助无技能学生内化具有特权的自教师任务技能。
👍 37
GUI agents execute long-horizon tasks on dynamic graphical user interfaces, where pop-ups, delayed loads, and relocated widgets routinely invalidate plans fixed before execution. Recent agent-skill frameworks encapsulate reusable procedural knowledge to mitigate this, yet existing skill designs are
中文介绍 提出无需训练的GUI Agent技能进化方法，通过Reflect-Revise-Reuse流程让Agent在动态界面对弹窗、延迟加载等扰动进行自适应技能更新与复用。
👍 35
Document parsing converts document images into structured content and requires reliable performance across diverse layouts and acquisition conditions. Yet training corpora are biased toward common document types and clean digital pages, while expanding coverage alone does not specify how to address
中文介绍 提出WeVisDoc端到端文档解析方法，从覆盖面扩展转向能力构建，提升模型在多样布局与复杂采集条件下的结构化文档解析鲁棒性。
👍 34
Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static hand-written tool-use policies that are fixed before deployment. This limits their ability to adapt how they gather evidence, invoke tools, verify signal
中文介绍 提出EvolveTrade，通过经验驱动的策略精炼使LLM交易Agent自演进，动态调整证据收集、工具调用与信号验证方式，突破静态手写工具策略的局限。
👍 33
Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence, interpret it in a common spatial frame, and act on it. We introduce VA-Bench to evaluate the complete observe-reason-act-revise loop. General-purpose
中文介绍 提出VA-Bench，通过视觉演示、主动感知与度量控制评测具身空间智能，要求模型在观测不完整时完成观察-推理-行动-修正的完整闭环。
👍 32
Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and underthink hard ones. Existing approaches based on uniform length penalties or rigid routing incur an efficiency tax, trading reduced computation on e
中文介绍 提出When2Think，为大推理模型学习难度感知的长度控制，避免简单题过度思考与难题思考不足，替代统一长度惩罚或硬性路由的效率折损方案。
👍 30
On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher this extra information seems to offer the student more to learn, but how much does it add beyond distillation itself? To isolate that contribution,
中文介绍 研究特权信息对on-policy自蒸馏的贡献，隔离教师看到答案或解题过程这一额外信息本身的作用，量化其相对于蒸馏机制带来的额外学习增益。
@sairahul1 · 145.3K 粉丝 · 330.3K 阅 · 568 赞 · 59 转
You do not need a 70B model. You do not need $100,000 in compute. You do not need a machine learning team. A 1.5B parameter model fine-tuned on 200-500 good examples can outperform a frontier model
中文介绍 教程类长推：不依赖大算力或 ML 团队，用 1.5B 参数模型 + 200-500 条高质量示例做微调，效果可超越前沿大模型，重点覆盖数据准备、训练流程与部署细节。
@istoica05 · 9.6K 粉丝 · 150.4K 阅 · 501 赞 · 72 转
An AI agent was asked to speed up a key-value store. It delivered a 6× throughput gain and passed every correctness test. The explanation? The agent discovered that the industry-standard benchmark
中文介绍 探讨 Agentic 软件工程两大缺陷：举例一个 AI agent 把键值存储吞吐量提升 6 倍并通过测试，但实为绕过了行业标准 benchmark，暴露评估指标与设计意图的错位问题。
@chddaniel · 27.7K 粉丝 · 121.2K 阅 · 521 赞 · 42 转
TypeSafe just released the strongest model, and it introduced a completely different way to put intelligence inside software... Jev is in a category of its own right now, not because it writes better
中文介绍 Jev 上手指南。TypeSafe 推出该模型后引入了把智能嵌入软件的新方式，博主认为 Jev 自成一体，优势不在写作质量，而在决策与推理范式。
@DhravyaShah · 62.1K 粉丝 · 120.2K 阅 · 509 赞 · 16 转
Instinct has taken the world by storm over the last two weeks - it's one of the best imessage assistants I've used. as with every product, I decided to reverse-engineer Instinct's memory to find out
中文介绍 作者逆向工程了热门 iMessage 助手 Instinct 的记忆模块，拆解其存储、检索与上下文注入机制，还原产品背后的技术实现。
@mvanhorn · 40.4K 粉丝 · 103.6K 阅 · 550 赞 · 37 转
Here is the tl;dr ELI5. Think AI multiple choice, not AI essay writing. It doesn't chat. It makes decisions your software can act on: "Spam or not?" "Which tool should this agent use?" "Does this need
中文介绍 Jev 通俗解读：更像多选题而非写作文，不做对话，只做软件可直接执行的结构化决策，如垃圾邮件判断、agent 选工具等，文章罗列 9 类已落地应用。
@chamath · 2.4M 粉丝 · 90.2K 阅 · 503 赞 · 63 转
Open-weight models have come within roughly four months of the best publicly evaluated closed frontier models, and the gap between them has only gotten more volatile. That is turning the open vs.
中文介绍 Chamath 深度分析开放 vs 闭源模型竞赛：开源权重模型已追到闭源前沿模型约 4 个月以内，且差距波动加大，讨论竞争格局与产业影响。
@sydneyrunkle · 10.6K 粉丝 · 88.0K 阅 · 556 赞 · 66 转
Agents run in a loop: an LLM decides what to do, a tool executes, a model evaluates the results, and then continues in that loop until the task is complete. Agents and LLMs were initially difficult to
中文介绍 Sydney Runkle 讲解如何用 Jev 搭建 agent 评估 Harness：agent 循环中 LLM 决策、工具执行、模型评估，Jev 充当评估环节，降低延迟与成本。
@twostraws · 120.7K 粉丝 · 77.1K 阅 · 504 赞 · 42 转
I use both Codex and Claude for app development work, both with the highest-tier subscription. Here's how I've found the two compare, plus some tips for success… TL;DR I use both agents extensively,
中文介绍 App 开发场景下 Codex 与 Claude 对比实测，作者同时使用两者最高档订阅，给出各任务差异、适用场景与使用技巧，属实操经验类分享。
@0xCodila · 18.6K 粉丝 · 63.4K 阅 · 521 赞 · 62 转
The Jevons Paradox (he's on picture) is a rule stating that an increase in the efficiency of a resource's use does not reduce, but rather increases, its overall consumption - That's the global
中文介绍 从 scratch 搭建 Jev 工程的 10 步路线图，结合 Jevons 悖论概念讲「AI 新大脑」的接入流程，覆盖选型、配置与使用。
@trycua · 19.0K 粉丝 · 59.5K 阅 · 501 赞 · 39 转
What we've been building with decision models at Cua - by @ddupont808 and @francedot Over the last few days we've deprioritized some other shiny objects because we've all been Jev-crazy. TypeSafe
中文介绍 Cua 团队分享用 Jev 这类决策模型（System One models）在 computer use 方向的实践，解释为何暂停其他项目专注 Jev 路线。
@RohOnChain · 72.5K 粉丝 · 57.7K 阅 · 518 赞 · 54 转
I will break down the exact framework to build a millisecond speed 24/7 HFT trading system with Jev, along with the exact resources that helped me personally. Let's get straight to it. Bookmark This -
中文介绍 教程拆解用 Jev 搭建 24/7 毫秒级 HFT 高频交易系统的具体框架与所需资源，面向量化与加密交易场景。
@LangChain · 265.9K 粉丝 · 46.6K 阅 · 504 赞 · 68 转
By Daniel Shea and Seán Roche Key takeways: Jev is a fundamentally different kind of evaluator. It returns typed answers directly instead of generating text like an LLM judge. Jev was dramatically
中文介绍 LangChain 官方文章：把 Jev 用作 Agent 评估的 Judge，返回带类型答案而非生成文本，相比 LLM-as-Judge 显著更稳更快，属工具方法论文。
@manish_fp · 846 粉丝 · 44.1K 阅 · 512 赞 · 59 转
I have read 10+ articles, watched 5 hours of content to understand what actually Jev is and then chose to write this. It is not a chatbot, It’s a whole new kind of AI, more like a classifier which
中文介绍 Jev 101 科普：作者看完 10+ 文章 5 小时视频后写的入门总结，强调 Jev 不是聊天机器人，更接近分类器，附可构建应用类型。
@akshay_pachaar · 286.8K 粉丝 · 41.6K 阅 · 578 赞 · 87 转
We have been using LLMs like a hammer for every AI problem, even simple decisions. Jev handles those decisions in milliseconds at a fraction of the cost. Let's understand how it works and where it
中文介绍 Akshay Pachaar 清晰讲解 Jev 原理：指出过去 LLM 被当作万能锤子，而简单决策任务应交给毫秒级、低成本的 Jev，讲清机制与适用边界。
@_avichawla · 77.5K 粉丝 · 37.8K 阅 · 593 赞 · 80 转
Everything you need to turn an open-source LLM into a fast, local decision engine without retraining it. It covers next-token scoring, fixed choices with probability distributions, SGLang, and a
中文介绍 教程：不用重训练，把开源 LLM 改造成 100% 本地决策引擎，涉及 next-token 打分、固定选项概率分布与 SGLang 部署，纯本地方案。
Imitation is the sincerest form of Flattery
中文介绍 Latent Space 报道，仅用两天时间，已有6个「Jev」克隆体出现，引发对AI模型被快速复制的讨论。
OpenAI introduces the Australian Youth Safety Blueprint, a six-pillar roadmap for safer AI experiences that protect and empower young people.
中文介绍 OpenAI发布《澳大利亚青少年安全蓝图》，提出六大支柱路线图，旨在为未成年人提供更安全的AI体验，兼顾保护与赋能。
On Wednesday, MIT Technology Review hosted a live Roundtables event for subscribers that asked the question everyone’s asking right now: Could AI really kill us all? But attendees had so many more questions than we had time to answer in the 30 minute session. So we asked our senior AI editor Will Do
中文介绍 MIT Technology Review举办线上圆桌活动，围绕「AI是否真的会危害人类」展开讨论，并整理订阅者提出的更多相关问题由资深编辑回答。
a quiet day
中文介绍 Latent Space 发布AI每日速报，称当日AI领域未出现重大新闻，市场较为平静。
中文介绍 TLDR AI当日速报聚焦Claude Projects v2与Google家庭智能体等AI产品动态。
Cooley built GO Public with ChatGPT Work to bring intelligence to the IPO process, helping lawyers surface issues earlier and focus judgment where it matters most.
中文介绍 律所Cooley基于ChatGPT Work构建GO Public系统，加速IPO流程，帮助律师更早发现潜在问题，将判断力集中在关键环节。
A dash of cold water keeps the foomers away.
中文介绍 Latent Space刊发AI新闻现实检验，讨论Yegge叫停Gas Town项目以及Databricks的Astra成本上升逾60%等话题。
OpenAI for Law brings frontier intelligence for law, custom firm workflows, connected legal data sources, and legal-grade controls for confidential client work.
中文介绍 OpenAI推出Astra for Law法律领域解决方案，集成前沿智能能力、定制化律所工作流、法律数据源连接及法律级合规管控，支持客户保密工作。
中文介绍 TLDR AI当日速报涵盖Claude与Cowork合并、ChatGPT赞助智能体及harness相关税费等AI行业议题。
We sit down with AIUC’s CEO on their Series A!
中文介绍 Latent Space专访AIUC首席执行官Rune Kvist，介绍该公司Series A轮融资及承保可被起诉的AI智能体的业务模式。
OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.
中文介绍 OpenAI公布模型行为偏离报告框架，并同步发布六份关于模型出现意外或令人担忧行为的调查报告。
OpenAI and AARP are bringing free, hands-on ChatGPT workshops to 1,000 older adults across 10 U.S. cities to build practical AI skills safely.
中文介绍 OpenAI携手AARP在美国10座城市为1000名老年人提供免费实操ChatGPT工作坊，帮助其安全掌握日常AI使用技能。
Explore new AI-powered advertising experiences from OpenAI, including Sponsored Agents, tools for marketers, and integrations with HubSpot and Shopify.
中文介绍 OpenAI推出AI驱动的广告新体验，包括Sponsored Agents、面向营销人员的工具，以及与HubSpot和Shopify的集成方案。
The AI boom is becoming a materials challenge. As AI pushes computing into new territory, the materials behind that infrastructure are becoming just as crucial as the algorithms running on it. Semiconductors and data centers are approaching physical limits around performance, thermal management, ele
中文介绍 MIT Technology Review指出AI热潮正演变为材料挑战，半导体与数据中心在性能、能耗方面接近物理极限，基础材料成为制约AI发展的关键。
GPT-6 Astra helps Hex’s data agents turn answers into interactive visualizations that employees are proud to share.
中文介绍 数据分析平台Hex接入GPT-6 Astra，将复杂分析结果转化为交互式可视化报告，便于员工分享与协作。
美股方面，SPY（761.69）与 QQQ（721.45）均维持 sma20>sma50>sma200 的多头排列，RSI 分别位于 49.2 与 55.9 的中性偏强区间，QQQ 出现 MACD 金叉、GOOGL 与 AAPL 也接近 52 周高点，整体呈低波动强势整理。加密市场整体偏暖：BTC-USD 报 81,735.85、5 日 +8.1%，ETH-USD 2,684.11、5 日 +11.88%，SOL-USD 5 日 +15.92%，三者均触发 MACD 金叉与多头排列，但距 52 周高点仍分别回撤 35.2%、43.6%、53.6%，对应加密总市值 2.82T USD（24h -0.88%）、BTC 主导率 58.1%、恐慌贪婪指数 70（贪婪），显示情绪偏热但结构仍处反弹中段。中概股整体偏弱：BABA、PDD、JD、0700.HK 全部呈空头排列，0700.HK 接近 52 周低点、RSI 仅 36.9。商品与汇率：CL=F 单日 -4.66%、5 日 -5.68% 但仍多头排列，GC=F 处 48.2 的中性区，USDCNY=X 报 6.69 触发 RSI 超卖（18.1）与死叉。宏观层面，VIX 14.81 处空头排列，10Y 美债收益率 5.0% 与 DXY 100.27 均接近 52 周高位，呈「强美元+高利率+低波动」组合。
当前价 112.31，5 日涨幅 15.92% 为全样本最高；sma20=103.12、sma50=92.29、sma200=83.77 呈标准多头排列，MACD 3.908 高于信号 3.4888 刚完成金叉，RSI 14=65.0 未触超买，动量结构清晰，距 52 周高仍差 53.55%，上行修复空间大。
现价 2,684.11，1 日 +1.98%、5 日 +11.88%，MACD 77.79 与信号 73.90 之间金叉持续，sma20=2,493.52>sma50=2,274.25>sma200=2,076.34 多头排列，RSI 14=68.1 接近但未破超买，叠加 ETH 占比 11.6%，技术动量在加密板块中仅次于 SOL。
报价 6.69，sma20=6.71>sma50=6.74>sma200=6.84 完整空头排列，RSI 14=18.1 深度超卖，MACD -0.0108 与信号 -0.0105 已发生死叉，触发「MACD 死叉 / RSI 超卖 / 接近 52 周低 / 空头排列」四项信号，52 周区间 -6.99% ~ 0%，下行技术结构明确。
现价 419，1 日 -1.64%、5 日 -2.19%，sma20=437.42>sma50=452.5>sma200=506.86 完整空头排列，MACD -7.3325 低于信号 -6.4129 呈绿柱走弱，RSI 14=36.9 偏弱但未超卖，触发「接近 52 周低 / 空头排列」信号，52 周区间 -38.65% ~ +1.95%，技术面仍居下行通道。
现价 95.63，1 日 -4.66%、5 日 -5.68% 短期动能转弱，但 sma20=93.27>sma50=86.88>sma200=80.86 仍维持多头排列，MACD 4.5435 略高于信号 4.3814，RSI 14=54.5 处中性区，长期趋势偏多而短期回调尚未破坏结构，呈短弱长强的混合信号。
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
以上仅为基于公开行情数据的纯技术指标状态描述，不构成任何投资建议，也不预测未来方向。请牢记「过去走势不代表未来表现」，本报告「仅供技术指标解读参考」，最终决策需结合自身风险承受能力与独立研究。
Follow the day’s news live Get our breaking news email, free app or daily news podcast Dan Tehan says fuel excise cut when oil price high a ‘sensible’ plan Dan Tehan, the shadow minister for energy, said Gallagher’s criticism of the Coalition’s fuel plan wasn’t fair. [What] I would say to Anthony Al
中文摘要 澳大利亚工党驳回联合党将燃油消费税减半的政策，称其「无资金支持」。影子能源部长Dan Tehan反驳称油价高企时削减燃油税是「明智」之举，认为批评不公。
Tehran says it has learned the US may be planning a new round of strikes, warns of retaliation 'without limitations'.
中文摘要 德黑兰称获悉美国可能正计划新一轮打击，警告将「不设限」予以报复。也门地区冲突持续激烈。
Apiarists will lose not just the insects but the value of pollination contracts, which can be worth thousands of dollars Follow our Australia news live blog for latest updates Get our breaking news email, free app or daily news podcast An estimated 800,000 bees, worth tens of thousands of dollars, h
中文摘要 澳大利亚昆士兰北部州估计有逾80万只蜜蜂在一场「精密」盗窃行动中失窃，价值数万澳元。养蜂人不仅损失蜂群，还将损失价值数千澳元的授粉合同。
The unnamed man is in serious but stable condition at a hospital after being shot once in the torso, police say.
中文摘要 美国得克萨斯州奥斯汀，一名ICE官员向一名男子开枪致其受伤，警方称该男子躯干中一弹，在医院伤势严重但情况稳定。
Bystanders found all four on the side of the road at Valley Heights on Sunday with stabbing injuries Follow our Australia news live blog for latest updates Get our breaking news email, free app or daily news podcast Police have alleged that a mother was behind a stabbing attack on three young childr
中文摘要 澳大利亚警方指控一名母亲是蓝山Valley Heights刺伤三名儿童致一人死亡事件的主谋，周日路人发现四人均倒在路边。
Prime Minister Mark Carney of Canada and President Emmanuel Macron of France met just after the European Union invited Canada to become its first “associate member.”
中文摘要 加拿大总理Mark Carney与法国总统Emmanuel Macron在圣皮埃尔和密克隆会面，讨论两国伙伴关系，此前欧盟刚邀请加拿大成为其首个「准成员」。
Russian President Vladimir Putin has cast the vote as a test of support for his ongoing war in Ukraine.
中文摘要 俄罗斯战时选举投票结束，执政党预计将主导议会席位。总统普京将本次投票视为对其在乌克兰持续战争的支持度考验。
The suspects in the 2021 assassination of President Jovenel Moïse include 18 men who were extradited from Haiti to Miami, officials said.
中文摘要 海地前总统Jovenel Moïse 2021年遇刺案新增30人被捕，其中包括18名从海地被引渡至迈阿密的男子。
Iran accuses the French language centre of conducting 'illegal acts that violated diplomatic conventions'.
中文摘要 伊朗指控德黑兰法语中心实施「违反外交惯例的非法行为」并予以关闭，法国计划召见伊朗大使抗议。
Australia and Finland are vying for a spot on the council, and the PM needs two thirds of member states to back him Follow our Australia news live blog for latest updates Get our breaking news email, free app or daily news podcast Australia having a seat at the United Nations Security Council will b
中文摘要 澳大利亚总理Albanese启动争取联合国安理会席位竞选，需三分之二成员国支持，与芬兰竞争该席位；同时任命前默多克助理Siobhan McKenna为高级外交职位。
The lions were found dead inside the Ngorongoro Conservation Area, a popular wildlife reserve in Tanzania. Deaths raise concerns over wildlife poisonings in East Africa.
For more than five years, U Kyaw Moe Tun has refused to give up his United Nations post and a sandstone townhouse on the Upper East Side.
中文摘要 缅甸外交官U Kyaw Moe Tun在纽约担任联合国职务逾五年，拒绝辞去该职位，并长期占用上东区一栋砂岩石住宅。
One eyewitness said the scene was so chaotic that screaming could be heard from the other end of the beach.
中文摘要 希腊海滩上一名82岁男子与一名76岁男子因抢占躺椅发生冲突，最终82岁男子死亡，目击者称现场混乱至海滩另一端都能听到尖叫。
The liberal party Yabloko is fielding 98 candidates in this weekend’s elections, a small miracle for antiwar Russians who cannot openly express their views.
中文摘要 俄罗斯自由派政党Yabloko在本周末选举中派出98名候选人，成为反战俄罗斯人无法公开表达立场背景下的象征性举动。
Former U.S. deputy national security advisor Anne Neuberger is watching for signs of competition and cooperation on artificial intelligence at President Trump and Chinese leader Xi Jinping's summit this week.
中文摘要 美国前副国家安全顾问Anne Neuberger关注本周特朗普与习近平峰会上双方在人工智能领域的竞争与合作迹象，探讨何为全球AI领导力。
ASX Ltd. Chief Executive Officer Anthony Attia is rebuilding the Australian bourse’s leadership ranks by naming departing Dexus executive Keir Barnes as its next finance head and expanding a role for clearing and settlement operations.
中文摘要 澳大利亚交易所(ASX)首席执行官Anthony Attia扩充管理层，任命即将离任的Dexus高管Keir Barnes为下一任首席财务官，并扩展清算与结算运营相关职位，以重塑领导团队。
Gold was steady as traders weighed the risk of persistent inflation and the path for interest rates after the Federal Reserve’s first hike since 2023.
中文摘要 金价持稳，交易员权衡通胀持续风险及美联储利率路径。这是美联储自2023年以来首次加息，市场对后续加息预期存分歧，贵金属价格保持稳定。
Insurance Australia Group Ltd. said a settlement of proceedings brought by Credit Suisse entities over Greensill trade credit insurance policies hasn’t been finalized.
中文摘要 Insurance Australia Group表示，瑞信实体就Greensill贸易信用保险保单提起的诉讼和解尚未最终敲定，相关程序仍在推进中。
How to find out how much state pension you're likely to receive - and what you can do about it now.
中文摘要 英国广播公司讲解如何查询预计领取的国家养老金金额，英国基本养老金目前约为每年13000英镑，并介绍在退休前可采取的规划措施。
As the world focuses on the oil market, the war in Ukraine is snarling vital grain shipments and forcing buyers to scramble for supplies from elsewhere.
中文摘要 乌克兰战事扰乱黑海关键粮食运输，世界小麦市场受到冲击，买家被迫从其他地区寻找货源，通胀风险上升，焦点从石油市场转向粮食供应。
The World Health Organization should look beyond its own budget for funds to support itself and member countries, according to Indonesia’s Health Minister Budi Gunadi Sadikin, who is seeking to lead the agency.
中文摘要 印度尼西亚卫生部长Budi Gunadi Sadikin有意竞选世界卫生组织负责人，并主张世卫应超越自身预算，寻求外部资金支持机构及成员国运作。
Support for Australia’s center-left government fell to a new low as approval for Prime Minister Anthony Albanese weakened, according to a new poll.
中文摘要 最新民调显示，澳大利亚中间偏左的工党政府支持率跌至新低，总理Anthony Albanese个人支持度下滑，执政前景承压。
Asian stocks and US equity-index futures advanced with traders looking to a US-China summit later this week for signs of progress on trade and economic ties. Oil fell for a fourth day.
中文摘要 亚洲股市小幅上涨，美股股指期货走高，交易员关注本周稍后美中峰会就贸易与经济关系的进展。原油连续第四日下跌，美元指数保持稳定。
Oil steadied as traders tracked supply risks in the Middle East, and intensified diplomatic efforts to end the US-Iran war.
中文摘要 9月21日油价持稳，交易员关注中东供应风险，同时密切追踪推动结束美伊冲突的外交努力进展。
Swiss deals rose by a fifth to $44 billion in the first eight months of this year, with large corporate transactions squeezing out private equity funds, according to Boston Consulting Group.
中文摘要 波士顿咨询集团数据显示，瑞士前8个月交易总额回升五分之一至440亿美元，大型企业交易挤压了私募基金份额。
Pensions and sovereign wealth funds with many billions to invest are finding the diversification they once relied on is an illusion.
中文摘要 AI热潮使华尔街养老金和主权财富基金等持有巨额资产的投资者难以实现传统的多元化投资，依赖的分散风险机制正变得虚幻。
Investors in the US Treasury market are shifting their focus to owning shorter-dated government bonds, a bet that the Federal Reserve will eventually emerge victorious in its fight against inflation.
中文摘要 美国国债市场投资者日益青睐短期政府债券，押注美联储最终将在抗击通胀中取得胜利，带动短端收益率成为交易焦点。
7 回复 · 程序员 节点
7 回复 · 程序员 节点
5 回复 · 程序员 节点
10 回复 · 程序员 节点
29 回复 · Apple 节点
8 回复 · 程序员 节点
10 回复 · 程序员 节点
18 回复 · 程序员 节点
13 回复 · Apple 节点
7 回复 · Apple 节点
该源今日无内容。