AI Products / Coding / Agents
Claude Code
Anthropic's terminal / IDE coding agent that understands the whole codebase and makes changes.Anthropic 的终端 / IDE 编程 Agent,读懂整个代码库并执行改动
Anthropic 的终端 / IDE 编程 Agent,读懂整个代码库并执行改动Anthropic's terminal / IDE coding agent that understands the whole codebase and makes changes.
Ranking history
| List | Period | # | Value | MoM |
|---|---|---|---|---|
| OpenRouter · Apps · 本周 token 用量 | 2026-10-29 | 3 | 11.08T tokens | — |
| 〃 | 2026-10-28 | 2 | 12.44T tokens | — |
| 〃 | 2026-10-27 | 2 | 14.10T tokens | — |
| 〃 | 2026-10-26 | 2 | 13.37T tokens | — |
| 〃 | 2026-10-25 | 2 | 13.43T tokens | — |
| 〃 | 2026-10-24 | 2 | 13.65T tokens | — |
| 〃 | 2026-10-23 | 2 | 13.34T tokens | — |
| 〃 | 2026-10-22 | 2 | 12.49T tokens | — |
Each row’s methodology is given by the list name (MAU, traffic and token usage differ), so rows are not comparable. AICPB does not disclose its collection method.
Timeline · 131
- X trendSuno launches MCP (Beta): op7418 notes that when Claude makes a video and needs music, it can now call Suno directly instead of you generati…Suno 推出 MCP(Beta):歸藏指出,以后让 Claude 做视频需要配乐时可以直接调用 Suno 生成,不用自己做完再发给它;在 Claude、ChatGPT、Gemini、Cursor、Claude Code 里加成自定义连接器、登录后即可用,不需要 API key,…
- LaunchYardlet: a free, open-source Mac app for the coding agents you already use: it launches Codex, Claude Code, OpenCode and others with their o…Yardlet:给你已经在用的编程 Agent 做的免费开源 Mac 应用:用各自的 CLI 和登录启动 Codex、Claude Code、OpenCode 等,统一到一个侧边栏、输入框和一套审批卡片里;会话仍存在各 agent 自己的存储中(在这里开的任务也能在 Codex…
- Launchlicenseal: catch incompatible dependency licenses before release: a free, open-source (Apache-2.0) CLI that checks every dependency license,…licenseal:发布前揪出不兼容的依赖许可证:免费开源(Apache-2.0)的命令行工具,在 10 个生态里把每个依赖(含传递依赖)的许可证与项目自身许可证比对;只读 lockfile 和注册表元数据、不安装任何东西,给 CI 一个明确结论而不是一张清单,还附带 Claud…
- LaunchDeepTutor: HKU's open-source, agent-native learning workspace: tutoring chat, quizzes, research, visualization, mastery paths and immersive…DeepTutor:港大开源的 Agent 原生学习工作台:辅导对话、出题、研究、可视化、掌握路径和沉浸式阅读(支持 YouTube/B 站字幕)共用一套运行时和记忆;可以把 Claude Code、Codex、OpenCode 等 agent 当子 agent 调用,接入 Li…
- NewsAnthropic launches reporting tools to show enterprises what their AI spend buys: managers can see a team's output, cost and where workflows…Anthropic 推出报表工具,让企业看清 AI 花费换来了什么:管理者可按时间段查看团队产出、花费以及流程卡在哪里,附改进建议和团队共享预算;给投资人的财务数据显示 Claude Code 带动净收入留存达 900%,Jellyfish 对 27.6 万用户的数据称基于 An…
- NewsV2EX Show & Tell: aivault lets multiple coding agents share one set of rules, skills and memory: it keeps rules, skills and memory in a plai…V2EX 分享创造:aivault,让多个编程 Agent 共用一套规则、skill 和记忆:把规则、skill 和记忆放进一个普通 Markdown 文件夹,接进 Claude Code、Codex、OpenCode、Gemini CLI、Kimi Code、DeepSeek…
- X trendGitHub Universe 2026: Copilot Fusion orchestrates Anthropic and OpenAI models per task: in the Artificial Analysis Coding Agent Index, Copil…GitHub Universe 2026:Copilot Fusion 按任务编排 Anthropic 与 OpenAI 模型:在 Artificial Analysis 编程 Agent 指数中,Copilot Fusion Max 与 Claude Code + Opus 5…
- X trendVox: stop the Opus-writes / Codex-reviews nitpick loop with a risk score: add to your review prompt or AGENTS.md "Rate each bug from 1 to 10…Vox:用风险评分打断「Opus 写、Codex 审」的无限挑刺循环:在审查提示词或 AGENTS.md 里加一句「每个 bug 按发生频率和严重程度各打 1–10 分,乘积低于 5 就只记 issue、不改代码」,再给负责修改的模型加一句「不要为没人提过的罕见或未来情况做设计」…
- X trendVox: planted .vscode/tasks.json in 17,667 GitHub repos steals Claude Code logins, AWS keys and npm tokens: a separate finding shows 42 repos…Vox:17667 个 GitHub 仓库被植入 .vscode/tasks.json,窃取 Claude Code 登录文件、AWS 密钥和 npm token:另有安全公司发现 42 个仓库在 .claude/settings.json 的 hooks 里接了恶意脚本,cla…
- X trendSimon Willison: October is another inflection point — Claude Opus 5.5 can now build video games that are actually fun: his blog post walks t…Simon Willison:十月又是一个拐点,Claude Opus 5.5 已能做出真正好玩的游戏:博客详细记录了用最新编程 Agent「氛围式」开发游戏的过程。约 500 收藏。
- X trendVox: let Opus 5.5 mine your last 20 Claude Code sessions for the mods you need: a copy-paste prompt reads the Claude Code mods guide plus yo…Vox:让 Opus 5.5 翻你最近 20 次 Claude Code 会话,找出最该做的 mod:一段可直接复制的提示词,先读 Claude Code mods 指南和 ~/.claude/projects/ 下的 .jsonl 日志,找出反复提的问题、被你中途停掉或撤销的命…
- X trendAnthropic study: experts went with their Claude Code agent's secret, coin-flipped lean 86% of the time: 50 professional causal-inference ana…Anthropic 研究:专家有 86% 的时候顺从了 Claude Code agent 被抛硬币设定的隐藏倾向:50 名有因果推断经验的专业分析师用 Claude Code 做一项真实分析,每个 agent 在四个判断点上被暗中指定为一个随机选项辩护;分析师先表态后,agen…
- LaunchHallmark v2: Together AI's anti-AI-slop design skill for Claude Code, Codex, Cursor and OpenCode: deals three themes from a catalog of fifty…Hallmark v2:Together AI 出品、给 Claude Code / Codex / Cursor / OpenCode 用的「反 AI 味」设计 skill:从 50 套主题里挑 3 套,围绕访客目的搭页面,再在真实浏览器里按分级门槛检查各种「机器味」(每个标题…
- X trendBaoyu: Anthropic engineering manager Felix Rieseberg drops coding questions from interviews — "hunger beats tenure": Claude now does these b…宝玉:Anthropic 工程经理 Felix Rieseberg 面试不再考编程题,「冲劲胜过资历」:理由是 Claude 已比人更会做这类题;他给新人五条建议:盯业务影响、想一个大胆点子、用一个周末做出原型、一个原型只放一个好点子、用好新人视角;Claude Code 桌面版…
- X trendmeng shao: the open-source "ai-app-playbook" has coding agents build profitable consumer AI apps on a fixed stack: human-facing chapters 00–…meng shao:开源「ai-app-playbook」,让 coding agent 按固定栈做出能赚钱的消费级 AI App:给人看的 00–13 章节加给 Agent 执行的 AGENTS.md(Phase 0–14,每步标 [AGENT]/[HUMAN],开工前过 Ga…
- X trendmeng shao breaks down Matt Pocock's 44-minute interview: say what you care about, and make your codebase worthy of agents: after months of s…meng shao 解读 Matt Pocock 44 分钟访谈:说清你在乎什么,让代码库配得上 Agent:Pocock 试了几个月 Spec 驱动开发,规格越写越细、代码质量反而一路下滑,结论是代码本身就是 Agent 的工作环境;他常用 Claude Code + Opus…
- X trendMiniMax open-sources self-hosted OpenAI Agents API “OpenAgentCore”: one Core, many harnesses; point the official OpenAI SDK at your OPENAIBA…MiniMax 开源自托管 OpenAI Agents API「OpenAgentCore」:一套 Core、多种 Harness;官方 OpenAI SDK 只改 OPENAIBASEURL,Session 里可选 Codex / Claude Code / MiniMax C…
- X trendGoogle launches the Gemini API CLI — a tool for the agent you already use: hand gemini-api to Claude Code, Codex, Cursor and others to gener…Google 发布 Gemini API CLI——给你现有 Agent 用的工具:把 gemini-api 交给 Claude Code、Codex、Cursor 等,就能生成图片、视频、语音和音乐,分析 PDF、音频、视频和 YouTube 链接,转写成 md/json/sr…
- X trendVox: have Claude Code write your REVIEW.md from the last 50 commits: following the Claude Code team's review setup, the prompt mines reverts…Vox:让 Claude Code 根据最近 50 个提交写出你的 REVIEW.md:参照 Claude Code 团队的评审做法,这段提示词从回滚和修 bug 的提交里提炼出一份简短的 REVIEW.md(什么算 bug、哪些小问题跳过、忽略哪些路径、每条评论都要写明文件和行…
- LaunchAVP: open-source version control for coding agents, built to replace Git's branch → PR → CI loop: each agent opens a task, writes and lands…AVP:给编程 Agent 用的开源版本控制,想取代 Git 的「分支 → PR → CI」循环:每个 Agent 开任务、写代码、落地,且每次落地都要在 main 的最新 head 上证明通过;两个 Agent 改到同一处代码时,会把一方在另一方之上重放,而不是走 PR。在其基…
- LaunchOpenBot: a local-first desktop workspace for persistent AI teammates across Codex, Claude Code, Grok and more: each agent gets its own works…OpenBot:本地优先的桌面工作区,把 Codex、Claude Code、Grok 等变成常驻 AI 队友:每个 Agent 有独立工作区和会话(Codex App Server、Claude Code,以及通过 ACP 接入的 Grok CLI、OpenCode、Gemin…
- LaunchPaperPilot: a zero-cloud, pure-Rust PDF engine you can hand to your agent via MCP: one Rust core exposed as an MCP server (one-line config f…PaperPilot:零云端、纯 Rust 的 PDF 引擎,可通过 MCP 直接交给 Agent 用:同一个 Rust 核心提供 MCP 服务器(Codex、Claude Code、Kimi Code、Pi、Claude Desktop、Cursor 一行生成配置)、CLI、不…
- LaunchManyAgents: run a team of Claude Code and Codex agents from one Mac window: an orchestrator splits your work across agents, each in its own…ManyAgents:在一个 Mac 窗口里指挥一队 Claude Code 和 Codex Agent:编排器把工作拆给多个 Agent,各自在独立 git worktree 里干活;评审 Agent 检查结果,内置浏览器让 Agent 自测,所有 Agent 的提问都汇总到一…
- X trendAddy Osmani: how the Claude Code team does code review when Claude writes ~90% of the code: from June to September merged PRs more than doub…Addy Osmani:Claude 写了约 90% 代码时,Claude Code 团队怎么做代码评审:6 月到 9 月合并的 PR 翻倍多,回滚占比降了 40% 以上。做法:提 PR 前先验证(让 Claude 拿出可运行的证据,再由全新上下文的子 Agent 审 diff)…
- X trendPaul Iusztin's free course: learn harness engineering by building Claude Code from scratch: after taking apart Claude Code, OpenCode and Pi,…Paul Iusztin 免费课程:从零写一个 Claude Code 来学 harness 工程:拆解 Claude Code、OpenCode 和 Pi 之后,他发布了开源的 Python 课程(8 篇文章、6 个视频、1 个代码库),涵盖 harness 设计、最简 Age…
- X trendBruce Van: malicious AGENTS.md files can hijack coding agents — three self-checks: Forever Security reports that in its own tests with a mal…Bruce Van:恶意 AGENTS.md 能劫持编程 Agent,三条自查:Forever Security 报告称,用恶意 AGENTS.md 测试时 Codex 超过 90% 中招、Claude Code 约一半(研究人员自测),结论是没有漏洞可修——Agent 只是照着…
- X trendHassan (Together AI): how I build apps these days: record a 1–5 minute voice prompt with Wispr Flow; add visual inspo (screenshots or Inspo…Hassan(Together AI):我现在怎么做应用:用 Wispr Flow 录 1–5 分钟语音当提示词;补视觉参考(截图或 Inspo MCP);用 Matt Pocock 的 grill-me skill 让 Agent 先追问澄清;对 v1 再用语音发反馈;每个新功…
- LaunchMuscleMemory: open-source procedural memory for coding agents that learns only from proven successes: watches Claude Code / Codex sessions a…MuscleMemory:给编程 Agent 用的开源程序性记忆,只从「真正跑通」的任务里学习:旁观 Claude Code / Codex 会话,任务以测试通过收尾时记下一条短技能(该改哪些文件、用哪条测试证明、要避开什么);下次类似任务就把这段注记塞进提示词。基准称 Code…
- LaunchLimitbreak: one Claude Code install, several Claude accounts — auto-switches mid-session when a usage limit hits: a tiny local Go proxy sits…Limitbreak:一套 Claude Code 挂多个 Claude 账号,额度打满就在会话中自动切换:本地小型 Go 代理挂在 ANTHROPICBASEURL 上,遇到 Anthropic 返回时段/周额度拒绝时,用下一账号重放同一条 /v1/messages 请求,且不…
- X trendVox: a paste-in prompt that finds the 3 habits burning your Claude Code quota: paste into Claude Code; it scans the last 7 days of session l…Vox:一条粘贴即用的提示词,找出烧掉你 Claude Code 额度的 3 个习惯:粘进 Claude Code;它用小脚本扫 ~/.claude/projects 最近 7 天的会话日志(不把原文塞进上下文),找出最耗额度的 3 个习惯(整文件读取、甩长测试/构建输出、狂开子…
- X trendVox: one AGENTS.md line that stops agents following stale docs over working code: researchers set a trap where docs disagreed with the code;…Vox:给 AGENTS.md 加一行,阻止 Agent 宁可跟过时文档也不跟能跑的代码:研究者设了文档与代码不一致的陷阱;Claude Code 80 次里有 79 次跟旧文档,Codex 4 次里有 1 次甚至把能跑的代码改成迁就过时文档。加上这行后,两个 Agent 跟代码…
- X trend"Is Opus 5.5 dumber?" goes viral, but an open daily tracker shows no real drop: Thariq's "wait is it just me or is Opus 5.5 dumber" became a…「Opus 5.5 是不是变笨了?」刷屏,但一个公开的每日追踪没看到明显下降:Thariq 那句「是只有我觉得 Opus 5.5 变笨了吗」在发布一个月后登上热门话题,很多用户说错误变多。一个公开追踪每天在 Max 套餐的 Claude Code 里问 Opus 5.5 同样的…
- X trendx-reader: make your agent say exactly what it actually read from a link: an open-source content reader covering 10+ platforms including X, Y…x-reader:让 Agent 读链接时老实交代到底读到了什么:开源的内容读取工具,支持 X、YouTube、B 站、公众号、小红书、播客等 10 多个平台。读完会标明读到了哪一层:搜索摘要不算原文、推文配文不等于视频、视频简介不等于内容,缺一层就标「只读了一部分」,读不到直接…
- X trendClaude's "Reverse Engineer Anything" workflows now trip safety checks mid-answer: users report that asking Claude (Opus 5.5) to run or even…Claude 的「Reverse Engineer Anything」流程开始在回答中途触发安全拦截:用户反映,让 Claude(Opus 5.5)跑 REA、甚至只是总结 REA,都会在回答一半时触发网络安全护栏。REA 是 MIT 开源的 MCP 服务,让 Claude Co…
- X trendCognition open-sources Devin Vulnerability Fixes: agent skills that patch this week's PHP, Node.js and GitLab RCEs: three MIT-licensed SKILL…Cognition 开源 Devin Vulnerability Fixes:用 agent skill 修补本周 PHP、Node.js、GitLab 的 RCE:三个 MIT 协议的 SKILL.md(fix-php-vuln、fix-node-vuln、fix-gitlab…
- X trendStrata: run a 125B-class model locally on a gaming PC and wire it into Claude Code / Codex: an open-source inference engine (MIT, ~32k GitHu…Strata:让普通游戏电脑本地跑 125B 级大模型,并接入 Claude Code / Codex:开源推理引擎(MIT,GitHub 约 3.2 万星),用 GPU 显存、内存和 SSD 三级调度加 MoE 专家动态缓存,显存加内存合计 32GB 起步就能跑 Qwen3.8…
- X trendAgent Manager (Hugging Face, @lvwerra): run Claude Code, Codex, Gemini CLI, opencode and more side by side from your own private HF Space: a…Agent Manager(Hugging Face,@lvwerra):在自己的私有 HF Space 里并排跑 Claude Code、Codex、Gemini CLI、opencode 等:Apache-2.0 的 Docker Space 模板,自述为「AI 编程 CLI…
- LaunchImpeccable: design vocabulary for AI coding agents — 1 skill, 24 commands, 62 detector rules: install with npx impeccable install, then /imp…Impeccable:给 AI 编程 Agent 用的设计词汇——1 个 skill、24 条命令、62 条检测规则:npx impeccable install 安装,再跑 /impeccable init 把产品事实写入 PRODUCT.md。命令覆盖 craft、audit…
- LaunchPerch: a calm Mac home for Claude Code sessions, PRs and next steps: free beta for Apple Silicon — bring existing Claude Code sessions over,…Perch:给 Claude Code 会话、PR 和下一步用的安静 Mac 工作台:Apple Silicon 免费 beta——把已有 Claude Code 会话迁过来,所有会话/PR/链接一处看清,只在 Claude、审阅人或 CI 等你时提醒。上下文和笔记存在本地库(无…
- X trendAnthropic: fold unnecessary subagents into the main agent loop; one agent + skills often beats multi-agent: Applied AI's Oct 22 guide (went…Anthropic:把多余子 Agent 折进主循环;单 Agent + Skills 常胜过多 Agent:Applied AI 10 月 22 日指南(夜间刷屏)说,给每个团队各挂一个子 Agent 再加编排器,等于把组织架构抄进 Agent,付出上下文损耗、Frankenp…
- X trendvista8: jailbroken old Kindle + KOReader, then Claude Code/Codex to tweak the UI: cheap used Kindles last forever; install KOReader + WeChat…向阳乔木:越狱旧 Kindle + KOReader,再用 Claude Code/Codex 改 UI:旧 Kindle 便宜续航久;装 KOReader + 微信读书插件,界面不爽可上 SimpleUI,也能直接用 Codex 或 Claude Code 改。他把「乔木 Re…
- LaunchAgentValley: every Claude Code agent at a glance in your MacBook notch: a free, open-source Mac app by Morse Chimwai that puts each Claude C…AgentValley:把每个 Claude Code agent 都放到 MacBook 刘海里一眼看清:Morse Chimwai 做的免费开源 Mac 应用,每个 Claude Code 会话一张卡片、每个子 agent 一行,还给每个 agent 配一个像素小人;你能看到…
- LaunchCindy: open-source multi-harness AI agent that works out of the box: Apache-2.0 desktop/mobile client that runs Claude Code, Codex and Pi in…Cindy:开箱即用的开源多 harness AI agent:Apache-2.0 的桌面/移动客户端,把 Claude Code、Codex 和 Pi 放在同一处(更多 harness 和自研 harness 在路上),任务做到一半也能换 harness 或模型,工作区、记忆…
- LaunchHallmark: a design skill that ends AI slop for Claude Code, Codex and OpenCode: install with npx skills add nutlope/hallmark -g; it picks on…Hallmark:给 Claude Code、Codex 和 OpenCode 用的、专治 AI 审美垃圾的设计 skill:一行 npx skills add nutlope/hallmark -g 安装;它从 48 套材质主题里选一套(或从零设计),会向你要真实照片和数字而不…
- X trendAWS open-sources Agent Toolkit for coding agents: aws/agent-toolkit-for-aws packages MCP access to 300+ AWS APIs, sandboxed Python execution…AWS 开源面向编程 Agent 的 Agent Toolkit:aws/agent-toolkit-for-aws 把 300 多个 AWS API 的 MCP 访问、沙箱 Python 执行、实时文档搜索,以及服务选型、CDK/CloudFormation、无服务、容器、Be…
- X trendVox: the most valuable line in AGENTS.md — make the agent start every reply with your name: put on line one: Start every reply with "[your n…Vox:AGENTS.md 里最值钱的一行——让 agent 每条回复都以你的名字开头:写在第一行:Start every reply with "[your name],". No exceptions. 一旦它不再叫你的名字,就说明规则开始脱落,立刻发交接提示:写一份给新会话…
- X trendGemini API CLI (gemini-api): one Go binary that gives Claude Code / Codex every Gemini capability: Google's Oct 19 experimental preview — a…Gemini API CLI(gemini-api):给 Claude Code / Codex 一个调用全部 Gemini 能力的单文件 Go 命令行:Google 10 月 19 日放出的实验预览,一个零依赖二进制覆盖文生图/视频/音乐/配音、文件分析、转写,以及后台 Man…
- X trendThariq Shihipar, one of the main public faces of Claude Code, has left Anthropic: after more than a year on Claude Code, he says it "scaled…Claude Code 最主要的对外面孔之一 Thariq Shihipar 离开 Anthropic:他做了一年多 Claude Code,说它「规模远超我的想象」,表示仍认同公司使命和「race to the top」,先休息一阵再开始新的事情;之后想看 Claude Cod…
- X trendHumanLayer open-sources its entire coding-agent platform under Apache 2.0: it is the same code HumanLayer Cloud runs: the Electron/Tauri des…HumanLayer 以 Apache 2.0 协议开源整套编程 Agent 平台:开源的就是 HumanLayer Cloud 在跑的同一套代码:Electron/Tauri 桌面端和 Web 界面、humanlayer CLI 里在你机器上跑 Claude Code 和 Co…
- X trendAwesome Short Drama Skills: an AI short-drama skill list backed by a controlled test: 83 hand-checked short-drama skills and 16 related open…Awesome Short Drama Skills:带对照组实测的 AI 短剧 Skill 清单:收录 83 个短剧 Skill 和 16 个相关开源平台,都经过人工核对,按小说改编、分集大纲、钩子设计、剧本审稿到分镜和 Seedance、可灵、MiniMax 视频提示词分阶段…
- LaunchCorgi: a terminal multiplexer built for running many coding agents: like tmux it keeps agents and dev servers running in the background, but…Corgi:为同时跑多个编程 agent 设计的终端复用器:它像 tmux 一样让 agent 和开发服务器在后台持续运行,还会显示每个 agent 在干什么、哪个在等你(按 F1 跳到下一个未读),能用你的多个账号启动 Claude Code、Codex、Pi 或 OpenCo…
- LaunchMonish: put your agents on the iPhone lock screen, with Approve/Deny before risky actions: paste one line into Claude Code, Codex, Cursor, n…Monish:把 agent 放到 iPhone 锁屏上,危险操作前先让你批准或拒绝:在 Claude Code、Codex、Cursor、n8n 或定时任务里粘贴一行,agent 读完一份简短说明后,长任务会以实时活动的形式显示在锁屏和灵动岛上,完成时提醒你一次(失败可以在免打…
- X trendClaude Code now supports MCP Tasks and Elicitations, plus a prompt to audit your MCP setup: Tasks let a server take a long job (test runs, e…Claude Code 支持 MCP Tasks 和 Elicitations,附一段体检 MCP 配置的提示词:Tasks 让服务器接下长任务(跑测试、导出、深度研究)后立刻返回,Claude 继续干别的,结果回来再接着处理;Elicitations 让工具在自动补参数或做不可…
- LaunchPeras: a weekly usage line for Claude Code and Codex: set something like peras set weekly 85 pause, and once your weekly usage crosses that…Peras:给 Claude Code 和 Codex 的每周额度划一条线:比如设 peras set weekly 85 pause,每周用量超过这条线后,agent 的下一次工具调用会被拒绝并给出原因,免得一个长任务把整周额度烧光;随时可以在终端或菜单栏恢复。它读的是 Cla…
- LaunchPristine: an agent skill that critiques and polishes web UI: it looks at the real page in light and dark, desktop and mobile, judges it thro…Pristine:帮 agent 评审和打磨网页 UI 的技能:它会实际打开页面,看亮色、暗色、桌面和手机四种状态,按你产品用户的画像来评判,然后要么从 11 个维度打 10 分制的分,要么直接改。命令有 /pristine init(生成 DESIGN.md)、critique…
- NewsV2EX Show & Tell: cinetty turns a repo's README into an animated architecture diagram in the terminal: the author says TUI animations made w…V2EX 分享创造:cinetty,把仓库 README 一键变成终端里的动态架构图:作者说这个 skill 做的 TUI 架构动画让他在 X 上拿到超过 100 万浏览。可以理解成终端版的 After Effects 模板库,内置 6 个模板,原生支持 Claude Code…
- NewsV2EX Show & Tell: EdgeQuota shows remaining Codex / Claude Code quota at the edge of your Mac screen: it slides out when an agent starts wor…V2EX 分享创造:EdgeQuota,贴在 Mac 屏幕边上看 Codex / Claude Code 剩余额度:agent 开始干活时自动滑出、干完收起,显示 5 小时和每周额度的剩余量与重置时间,以及哪个会话在等你确认。Claude 走 Claude Code 自带的状态栏…
- X trendTanStack AI: one frontend codebase that switches freely between OpenAI, Anthropic and Gemini: version 0.71 shipped on October 21, and the po…TanStack AI:一套前端代码在 OpenAI、Anthropic、Gemini 之间随便切:10 月 21 日刚发 0.71,帖子称 GitHub 3200+ star。工具用 toolDefinition() 定义一次,服务端和客户端都能挂实现;结构化输出直接用 Zod…
- X trendGoogle's "Toolflation": when agents write tool listings for other agents, the listings inflate: researchers built markets of 10 real Amazon…谷歌「Toolflation」论文:让 agent 给别的 agent 写工具介绍,介绍会越写越夸张:研究者用 10 个真实的 Amazon 或 Instagram 数据工具搭了市场,让 5 个线上模型扮演卖家改写介绍争取被选中,再让 Claude Code 和 Codex 作为…
- X trendTheo explains what a "harness" actually is: an LLM only emits text; the harness is the tools, the tool-call syntax, the parser that runs cal…Theo 讲清楚「harness」到底是什么:LLM 只会输出文本;harness 是工具、工具调用语法、解析并执行调用的系统、把结果喂回模型的循环,再加带说明的工具清单。Claude Code 和 Codex 把界面和 harness(Agent SDK、Codex App S…
- X trendBefore Claude defaults to auto mode, install dcg to block dangerous commands: poolmoon recommends the open-source destructivecommandguard, w…Claude 默认自动模式之前,先装上 dcg 拦截危险命令:寒塘 poolmoon 推荐开源工具 destructivecommandguard:通过 hook 在 agent 执行前确定性地拦下 git reset --hard、rm -rf 这类危险命令,Rust 写的、几…
- X trendEight rules from six months of using Claude Code and Codex without writing code: keep one handoff file per project that each agent reads fir…不写代码用 Claude Code 和 Codex 干了半年,总结 8 条规矩:一个项目只留一份交接文件,接手的 agent 先读、阶段结束写回;交接里的「已完成」不能直接信(可能是额度中断),先核对真实文件;改正式文件前先备份,删除、批量移动、覆盖必须人点头;能用脚本做的不让模…
- X trendClaude web, desktop and mobile apps default to "auto mode" starting next week: On Pro, Max and Team plans, sessions will no longer ask you t…Claude 网页、桌面和手机 App 下周起默认「自动模式」:Pro、Max、Team 套餐的会话不再每一步都要你点批准,而是由自动检查拦下有风险的操作,随时可以切回手动。这是 Claude Code 自动模式默认化之后,推广到所有 Claude 应用。用 Claude 跑连接…
- X trendArtificial Analysis Coding Agent Index 2.0: Claude Code + Opus 5.5 leads with 61.7: The index evaluates models together with their agent har…Artificial Analysis 编码 Agent 指数 2.0:Claude Code + Opus 5.5 以 61.7 分领先:这个指数把模型和 agent 框架放在一起评,2.0 版用 Cognition 的 FrontierCode(100 个真实开源仓库任务,按…
- X trendPonytail 5 rewrite: make the agent look for existing code before writing any: For the same "add a date picker" task, the agent wrote 335 lin…Ponytail 5 重写:让 agent 先找现成的再写代码:同样「加一个日期选择器」,不用时 agent 写了 335 行,用了只写 10 行,复用仓库已有的 Input 组件、让浏览器提供日历。它在动手前按顺序自问:要不要写、仓库里有没有、标准库够不够、浏览器或系统有没有、…
- LaunchCarbon-X: Hugging Face's open-source 14B DNA + natural-language model: based on Qwen3-14B, further trained on 302B tokens of mixed DNA, biol…Carbon-X:Hugging Face 开源的 14B DNA + 自然语言模型:基于 Qwen3-14B,在 302B token 的 DNA、生物文本和英文混合数据上继续训练,再做 SFT 和 GRPO。DNA 按 6 碱基一个 token 编码,和文字共用一个解码器,直…
- NewseMudhra certificate incident follow-up: command-line tools and macOS's bundled curl and git need handling too: the discoverer built a check…eMudhra 证书事件后续:命令行工具和 macOS 自带的 curl、git 也要处理:发现者做了个检查页 we-have-a-problem.com,用 curl 报证书错误,就说明你的客户端已经不信任这批 CA 了。页面列出已修复的版本:Claude Code 2.1.…
- NewsJuejin: spot-checking 60,000 Skills, the top-ranked ones are almost never the real thing: the author found a Skills directory grew from 1,40…掘金:抽查了 6 万个 Skills,排名靠前的几乎没有真货:作者发现 Skills 收录站三个半月从 1400 个涨到 63000 多个,但按装机量排的前 20 里,真正带 SKILL.md、能算 Skill 的只有四五个,其余是完整应用、提示词合集、MCP 服务器,甚至是 C…
- X trendScan skills others share with NVIDIA SkillSpector before installing them: An open-source scanner NVIDIA uses before listing skills in its ow…装别人分享的 skill 之前,先用 NVIDIA SkillSpector 扫一遍:这是 NVIDIA 在自家 skill 目录上架前用的开源扫描器(Apache 2.0,今年 3 月开源,现在 2 万多星,今天又在 X 上被推荐)。它检查 17 类、71 种攻击模式,包括提示…
- LaunchDuckDB 2.0.0 LTS "Cinnamon Teal": the biggest feature release of DuckDB so far, nearly 20,000 commits since 1.5, supported until at least Oc…DuckDB 2.0.0 LTS「Cinnamon Teal」:这是 DuckDB 迄今最大的功能版本,距 1.5 有近 2 万次提交,支持到至少 2027 年 10 月。亮点包括打磨后的 Quack 协议和新的 CONNECT 语句(DuckDB 可以按客户端-服务器方式跑)、…
- Launchgraphify: turn a codebase into a queryable knowledge graph for coding agents: gained 1,400+ stars on GitHub Trending today. Type /graphify i…graphify:把代码库变成可查询的知识图谱,给 coding agent 用:今天 GitHub Trending 涨了 1,400 多星。在 Claude Code、Cursor、Codex、Gemini CLI 里输入 /graphify,它会用 tree-sitter…
- NewsLiteLLM 1.107.0 poisoned on PyPI: installing it steals credentials and leaves a backdoor: per SafeDep's analysis, all 7 wheels of this versi…LiteLLM 1.107.0 在 PyPI 上被投毒,装了就会偷凭据并留后门:SafeDep 分析,这个版本的 7 个 wheel 都多装了三个文件,其中 cook.pth 会让主机上任何 Python 进程启动时都运行窃密脚本(哪怕根本没 import litellm),收集…
- X trendClaude API ships version 2026-10-21, the first formal version bump since 2023: With the new version, passing temperature, topp or topk to th…Claude API 发布 2026-10-21 版本,2023 年以来第一次正式升版:新版本下,Messages API 里传 temperature、topp 或 topk 会直接返回 400(哪怕传的是默认值);assistant 消息里放 document、user 消息…
- NewsV2EX Share Creations: two open-source tools for handing over context between Claude Code and Codex: ccx binds a Claude Code session to a Cod…V2EX 分享创造:两个在 Claude Code 和 Codex 之间交接上下文的开源工具:ccx 把一个 Claude Code 会话和一个 Codex 线程绑在一起,双向同步消息、工具调用、计划和 git status,在 Mac 菜单栏点一下就能换到另一边继续,某一边 5…
- X trendGet Claude Code to produce 3 design directions at once (Vox): the open-source design-taste has 24 skills and 10 style packs. The original po…让 Claude Code 一次给出 3 套设计方向(Vox):开源的 design-taste 有 24 个 skill 和 10 个风格包。原帖给了一段可直接复制的提示词:克隆仓库但不运行安装脚本,只把核心 skill 和风格包复制进项目的 skills 目录,让它读需求后选…
- X trendBefore launch, have 4 subagents act as first-time users (Vox): in Claude Code, have Opus 5.5 dispatch 4 subagents to take turns using the br…上线前让 4 个 subagent 扮演第一次来的用户(Vox):在 Claude Code 里让 Opus 5.5 派 4 个 subagent 轮流用浏览器从落地页走到「首次成功」:没耐心乱点的、先读定价和隐私条款的怀疑派、375px 屏 + 慢速 3G 的手机用户、乱填表单…
- X trendFor an agent knowledge base, try a Markdown index before vector retrieval (Paul Iusztin): his LLM wiki uses a Markdown index page listing ea…给 agent 做知识库,先试 Markdown 索引再上向量检索(Paul Iusztin):他的 LLM wiki 用 Markdown 索引页列出各页标题和简介,agent 先读索引、挑相关页面、需要时顺着链接继续读,不用 embedding。他另一条帖子说,做知识图谱最难…
- X trendPitfalls of cross-organization agent collaboration (Salesforce paper, via Rohan Paul): across 488 scenarios and 2,500+ agent-to-agent sessio…跨组织 agent 协作的坑(Salesforce 论文,Rohan Paul 转述):在 488 个场景里跑了 2500+ 次 agent 对 agent 会话(Claude Code、Codex、Cursor 各在独立沙箱),归纳出 20 种失败模式:没有一个 agent 会…
- LaunchSuperlite: a "hand it off and walk away" plugin for Claude Code: the author loves superpowers but dislikes that it stops for human approval…Superlite:给 Claude Code 用的「交给它就走开」插件:作者很喜欢 superpowers,但嫌它每个功能要停下来让人批准 8–12 次,还一次只跑一个实现 agent。superlite 改成只问一批问题、批准一次,把计划写成任务图,互不冲突的任务并行跑:Op…
- Launchheadroom: compress content before it enters the model: newly appeared on GitHub Trending today. It picks a compressor by content type locall…headroom:在内容进模型之前先压缩:今天 GitHub Trending 新冒出来的。它在本地按内容类型挑压缩器,JSON、源码(基于 AST)和普通文本各有一套,还会标出会破坏 KV 缓存前缀的易变内容;原文存在本地,模型需要时可以调 headroomretrieve 取…
- X trendTencent open-sources Octop: a self-hosted, multi-user agent workbench (recommended by Gorden Sun, 160 bookmarks): each user has their own lo…腾讯开源 Octop:自托管、多用户的 agent 工作台(Gorden Sun 推荐,160 收藏):每个用户有独立登录,可以建多个 agent,每个 agent 自带独立工作区、浏览器、终端和远程桌面,Web 控制台里能直接接管键鼠;支持多个专家 agent 由协调者调度、自…
- X trendDHH: using Tailscale to reach Claude Code in China: someone asked DHH whether he could use Claude Code on a trip to China, and he replied th…DHH:在中国用 Tailscale 访问 Claude Code:有人问 DHH 来中国能不能用 Claude Code,他回复说自己所有 Claude Code 流量都走自己的 tailscale 网络(原回复 700+ 赞),歸藏转发吐槽「DHH 很懂了」。歸藏 | DHH…
- X trendai-job-search: an open-source job-search tool built with Claude Code (recommended by 铁锤人): reads your experience, screens matching jobs, tai…ai-job-search:用 Claude Code 做的开源求职工具(铁锤人推荐):读取你的经历、筛选匹配岗位、按岗位要求改简历并生成求职信,还会让另一个 agent 复核导出的 PDF 能否被招聘系统(ATS)正确解析。要反复针对不同岗位改简历的可以试试,「另一个 agen…
- X trendtv-vibehack (recommended by Gorden Sun): the author used Claude Code to build an ad-free launcher for his parents' Xiaomi TV, with no root a…tv-vibehack(Gorden Sun 推荐):作者用 Claude Code 给父母的小米电视做了个去广告启动器,不用 root、不插线,电脑和电视连同一个 Wi-Fi、电视开调试模式就能装;装完主界面变成纯黑极简风,没有开机广告和推送,启动器只有 1.6MB、纯 Jav…
- NewsV2EX: 流量喵 adds disk monitoring to see how much AI tools write to disk: the author keeps Codex, Claude Code, Cursor and Gemini open on a home…V2EX:流量喵加了磁盘监控,看看 AI 工具到底写了多少盘:作者在家里的 Mac mini 上常开 Codex、Claude Code、Cursor、Gemini,看到 Codex 持续写盘的反馈后,给自己的菜单栏流量工具加了按进程的读写排行(今日、7 天、30 天、累计,可导…
- LaunchSphinx (Show HN): before pushing AI-written code, it quizzes you on whether you understood it: a Git hook that, when you push a protected br…Sphinx(Show HN):推送 AI 写的代码前,先考考你看懂没有:一个 Git hook,在你推送受保护分支时,让一个没看过你和 Agent 对话的审查模型读 diff,出一道「出错时会怎样」的情景题,答错就讲解再换一题,答对才放行。支持 Codex、Claude Cod…
- LaunchBeatBrowser: let Codex, Claude Code and Cursor share the Chrome you're using: an open-source project from V2EX "Share Creations", a Chrome e…BeatBrowser:让 Codex、Claude Code、Cursor 共用你正在用的 Chrome:V2EX「分享创造」里的开源项目,一个 Chrome 扩展加本地 Node 桥接,通过 MCP(也有 CLI 和 Node SDK)让多家 Agent 操作你已登录的那个…
- Launch500 clocks, all generated by Opus 5.5 (Show HN): the author usually tests frontier models by asking them to write a self-contained web clock…500 个时钟,全由 Opus 5.5 生成(Show HN):作者平时用「让模型写一个自包含网页时钟」来测前沿模型,类似 Simon Willison 的「骑自行车的鹈鹕」,这次在 Claude 聊天界面里分几轮让 Opus 5.5 做了 500 个,塞进一个 6.3 MB 的…
- NewsV2EX: SciForge, a local-first deep-learning research agent framework: it splits research into four layers: 24 methodology Skills (compatible…V2EX:SciForge,本地优先的深度学习科研 Agent 框架:把科研拆成四层:24 个方法论 Skill(兼容 Claude Code 规范)、46 个确定性工具(文献检索精读、SSH 跑实验、配图、写作)、7 条流水线(综述、实验、论文、每日跟踪等)和 8 个无构建的本…
- X trend一泽 Eze's Web Access Skill update now supports Grok Bot: it lets an agent browse and collect through your already-logged-in Chromium-based br…一泽 Eze 的 Web Access Skill 更新后支持 Grok Bot:让 agent 用你本机已登录的 Chromium 系浏览器(含 Arc)做联网和采集,适合要本机登录态、非机房 IP 的任务;不依赖截图所以省 token,每探索一个网站就自动沉淀成站点 skil…
- X trendGraphify: before a coding agent acts, it builds a local knowledge graph of the whole codebase so Claude Code, Codex and Cursor follow archit…Graphify:在编码 agent 动手前先给整个代码库建本地知识图谱,让 Claude Code、Codex、Cursor 顺着架构关系追调用,而不是一个个文件读,适合大仓库省上下文。
- Podcast十字路口CrossingTreg's three pivots in nine months: the dead end for vertical agents and new opportunities growing around Claude Code and CodexTreg 创业 9 个月三次转型:垂直 Agent 的“绝境”,以及围绕 Claude Code / Codex 生长的新机会
- LaunchOrca: a desktop app for managing "a swarm of coding agents": Codex, Claude Code, OpenCode and Pi can run side by side, each in its own git w…Orca:一个管理「一群编程 Agent」的桌面应用,Codex、Claude Code、OpenCode、Pi 可以并排跑,每个在独立的 git worktree 里;可以把同一个提示分给五个 Agent,比较结果后合并最好的那个。还带 WebGL 终端分屏、点选网页元素把 H…
- Launchai-job-search: a job-search pipeline a geophysicist built with Claude Code after being laid off: /scrape searches jobs, /apply evaluates fit…ai-job-search:一位地球物理学家被裁后用 Claude Code 搭的求职流水线,/scrape 搜职位、/apply 评估匹配度并起草定制的 LaTeX 简历和求职信(另有一个审稿 Agent 把关)、/interview 准备面试。作者说自己投了 69 份、拿到…
- LaunchGoogle's official android/skills: a set of Agent Skills (standard SKILL.md format) maintained by the Android team, written to developer.andr…Google 官方 android/skills:Android 团队维护的一套 Agent Skills(标准 SKILL.md 格式),按 developer.android.com 的最佳实践写,刻意只覆盖评测显示大模型容易做错的场景(比如 R8 混淆分析、Wear OS…
- NewsClaude Haiku 4.5 will be removed from the Claude app's model list: from October 29, Haiku 4.5 can no longer be selected on web, desktop and…Claude Haiku 4.5 将从 Claude App 的模型列表下线:10 月 29 日起,Free、Pro、Max 用户的网页、桌面、移动端及 Cowork、Design 里不再能选 Haiku 4.5,已选的会自动切到 Haiku 5.5,旧对话保留;Claude C…
- NewsV2EX "Share Creations" Iterlay: an open-source desktop tool that puts reference images, image generation, editing, versions and asset organi…V2EX「分享创造」Iterlay:把参考图、生图、改图、版本和素材整理放在一张无限画布上的开源桌面工具,提供 CLI 和 Skill,让 Codex、Claude Code 能直接操作。作者推荐的用法是让 Agent 生成一组页面或产品素材,在画布上比较、局部修改,再导出到项目…
- X trendTurn agent failures into regression tests with "session replay" (Paul Iusztin, author of the LLM Engineer's Handbook): while using Claude Co…用"会话回放"把 agent 的失败变成回归测试(Paul Iusztin,《LLM Engineer's Handbook》作者):他用 Claude Code 给自研编码 agent Decode 写评测层时,Modal 接口冷启动返回 503,agent 没等,而是翻出内存…
- X trendRun 23 checks with Claude Code before you start taking money (Vox): the checklist includes secrets only on the server and searched in fronte…上线收钱前让 Claude Code 跑一遍 23 项检查(Vox):清单包括密钥只在服务端并搜过前端和 git 历史、每个接口在服务端校验登录和权限并开 RLS、支付 webhook 验签且重复回调只记一次、金额用最小货币单位的整数存、双击提交只生成一个订单、迁移都写好回滚 S…
- X trendShare one memory across multiple coding agents: the open-source akitaonrails/ai-memory lets you switch from Claude Code to Codex in the same…多个编码 agent 共用一份记忆:开源的 akitaonrails/ai-memory 让你在 Claude Code 里做到一半,换 Codex 在同一目录接着做,不用重讲架构、失败过的方案和未决问题;支持二十多种 agent,记忆是放在 git 里的普通 markdown,…
- LaunchPS5LM: runs GGUF models on a jailbroken PS5 using llama.cpp's Vulkan backend, with about 11.4 GB of shared VRAM for the model, offering both…PS5LM:在越狱的 PS5 上用 llama.cpp 的 Vulkan 后端跑 GGUF 模型,大约 11.4 GB 共享显存给模型用,对局域网提供 OpenAI /v1/chat/completions 和 Anthropic /v1/messages 两种接口(README…
- LaunchStarSkirmish Bench v0.2 (Show HN): have large models, in their own official CLIs (Claude Code, Codex, Antigravity CLI, Muse Code), spend an…StarSkirmish Bench v0.2(Show HN):让大模型在各自官方 CLI(Claude Code、Codex、Antigravity CLI、Muse Code)里用一小时写一个《星际争霸:母巢之战》神族 C++ bot,再和人类写的强 bot 对打。GPT-…
- NewsV2EX "Share Creations" baocode: the author fully ported the Monaco editor and xterm to pure Dart with Flutter, producing an IDE that feels c…V2EX「分享创造」baocode:作者用 Flutter 把 Monaco 编辑器和 xterm 完整移植成了纯 Dart,做出一个手感接近 VS Code 的 IDE,安装包只有十几 MB,内核接的是 Claude Code,支持远程 SSH(用服务器上的 Claude Co…
- X trendThe Claude Code team says about 90% of Claude Code's code is written by Claude; from June to September merged PRs more than doubled and the…Claude Code 团队称约 90% 的 Claude Code 代码由 Claude 写;6 月到 9 月合并 PR 翻倍多,被回滚比例降了 40% 以上,并发长文讲他们怎么改代码审查(目标是在不增加回滚和事故的前提下把人工审查时间压到最低)。
- X trendBoth are speeding up and saving quota: Tibo (Codex lead) says Codex and Work improve cache hits by reusing context across subagents, extendi…两家都在提速省额度:Tibo(Codex 负责人)说 Codex 和 Work 通过子 agent 间复用上下文、延长缓存、改进路由提高缓存命中,用户实际可用额度变多;Claude Code 则开始对每轮发送的对话做 gzip 压缩,云端会话在你开始打字时就启动。
- X trendClaude's official security plugin runs a whole-repo scan in three lines (Vox): first /model to switch to Opus 5.5, then /plugin install clau…Claude 官方安全插件三行跑全仓扫描(Vox):先 /model 切到 Opus 5.5,然后 /plugin install claude-security@claude-plugins-official、/reload-plugins、/claude-security s…
- LaunchThree agent skills / harness projects on GitHub's daily trending: affaan-m/ECC (+1057 stars today) is a harness-optimization suite for Claud…GitHub 日榜上的 Agent 技能 / harness 三件套:affaan-m/ECC(今天 +1057 星)是给 Claude Code、Codex、OpenCode、Cursor 用的 harness 优化套件,打包了 skills、记忆、安全和「先调研再开发」的流程…
- NewsA GNOME / Fedora veteran uses Claude Code to reverse-engineer hardware and write a driver: Red Hat's Christian Schaller was stuck for months…GNOME / Fedora 老兵用 Claude Code 逆向硬件写驱动:Red Hat 的 Christian Schaller 想让一台 Linux 不支持的底片扫描仪能用,卡了几个月;后来学别人让 Agent 完全控制一台 Windows 虚拟机、边扫描边抓 USB 数…
- NewsDeepSeek publishes web search / fetch API pricing: Search and Fetch become separate APIs billed per successful request, each ¥5 per 1000; se…DeepSeek 公开网页搜索 / 抓取 API 定价:Search 和 Fetch 变成独立 API、按成功请求计费,各是每 1000 次 5 元;通过 Claude Code 的 Web Search 或 Codex 的 websearch 发起的搜索,上线后头两周免收 Se…
- X trendSharing context across Claude Code / Codex: 陈大黄 asked (196 replies), and a top reply recommends the open-source Orbital.跨 Claude Code / Codex 共享上下文:陈大黄提问(196 回复),高赞回复推荐开源 Orbital。 / /
- Launchanthropics/claude-plugins-official: the Claude Code plugin directory officially maintained by Anthropic, also on GitHub's daily trending tod…anthropics/claude-plugins-official:Anthropic 官方维护的 Claude Code 插件目录,今天也在 GitHub 日榜上,方便跟官方插件生态对齐。
- LaunchXERJ (GitHub Trending, +725 stars today): a local search index written in Rust that indexes code, docs, logs and PDFs with one command, then…XERJ(GitHub Trending,今天 +725 星):Rust 写的本地搜索索引,一条命令把代码、文档、日志、PDF 建索引,再通过 MCP 和 skill 接进 Claude Code / Cursor,让 Agent 不再一个个 grep 读文件;还主打「参考编程」…
- Launchcaveman (GitHub Trending, +398 stars today): a skill plus proxy that makes coding agents say less, like a caveman: talk less, read less, kee…caveman(GitHub Trending,今天 +398 星):让编程 Agent 像原始人一样少废话的 skill 加代理,少说少读、代码保持原样。项目给的数据是整段会话输入 token 少 33%,配合 Auto 模式成本降 54%、得分不变。想压 Claude Cod…
- X trendFelix Rieseberg's "How to be more ambitious": Speed/Altitude/Depth/Range; Vox suggests having Opus 5.5 set three bigger goals for your proje…Felix Rieseberg《How to be more ambitious》:Speed/Altitude/Depth/Range;Vox 建议让 Opus 5.5 据此为项目定三个更大目标。
- X trendClaude Code /fast: the same Opus 5.5 with output up to 2.5x faster, $8/$40 per MTok (double), subscribers go through usage credits; switchin…Claude Code /fast:同一 Opus 5.5,输出最高快 2.5 倍,$8/$40 每 MTok(翻倍),订阅用户走 usage credits;切换速度会让 prompt cache 失效。
- LaunchGraphicle: a code-graph plus memory tool written in Rust that gives MCP clients like Claude Code, Codex and Cursor context with file and lin…Graphicle:用 Rust 写的代码图谱加记忆工具,给 Claude Code、Codex、Cursor 等 MCP 客户端提供带文件和行号引用的上下文,全本地运行,不需要 API key,也没有遥测。GitHub | Show HN(有人说自己的评测里这类记忆系统还不如直…
- X trendMajor Claude Code desktop update (parallel multi-session, task splitting, live status of each session) + Claude Platform OpenTelemetry trace…Claude Code 桌面版大更新(多会话并行、拆分任务、实时看各会话状态)+ Claude Platform OpenTelemetry traces 公测(Messages API / Managed Agents / SDK)。
- X trendOfficial note on Claude Code idle compaction; turn it off with "idleCompaction": false. /Claude Code 空闲压缩官方说明;关闭 "idleCompaction": false。
- X trendRepowise: a codebase index map that reduces Claude Code's whole-repo grep.Repowise:代码库索引地图,减少 Claude Code 满仓 grep。
- NewsQbitAI: APUS AI open-sources Reflex Agent: claims faster response than Claude Code and pushes an "infinite context" route; the repo is publi…量子位:APUS AI 开源 Reflex Agent:称响应快于 Claude Code,并主打“无限上下文”路线,仓库已公开。量子位 | GitHub
- X trendTheo (t3.gg) writes Claude/Codex requests into ClickHouse: since late September he has almost entirely moved from Codex to Claude Code; disc…Theo(t3.gg)把 Claude/Codex 请求写入 ClickHouse:自 9 月下旬起几乎完全从 Codex 转向 Claude Code;配合个人用量日志讨论工具选型。
- X trendScenario open-sources a Blender plugin: concept-art/3D workflows can be used inside Blender, or let Claude Code drive a whole "3D team" via…Scenario 开源 Blender 插件:概念美术/3D 工作流可在 Blender 内用,也可让 Claude Code 经 MCP 驱动整支「3D 团队」。
- X trendClaude Code 2.1.299: plugin eval adds --disallow-tools; sessions over 200K auto-compact after about 54 minutes idle; safety/dual-use prompts…Claude Code 2.1.299:plugin eval 加 --disallow-tools;超 200K 的会话空闲约 54 分钟自动压缩;安全/双用途提示改为 AskUserQuestion 追问。
- X trendseo-skills (an SEO+AEO skill repo for Claude Code/Cursor) + a Railway case: Claude Code recommends Railway for 82% of Python apps. / /seo-skills(Claude Code/Cursor 的 SEO+AEO 技能仓库)+ Railway 案例:Claude Code 给 82% Python 应用推荐 Railway。
- X trendCodex lead Tibo teases a plan to significantly increase everyone's usage. ;Theo 称 $200 Claude Code 订阅超值Codex 负责人 Tibo 预告让所有人用量显著增加的计划。
- X trendClaude Code Projects opens to Pro/Max (parallel cloud threads)Claude Code Projects 对 Pro/Max 开放(并行云端线程)
- X trendClaude Code model routing: CLAUDECODESUBAGENTMODEL=haiku + Sonnet for the main session (@mirku21)Claude Code 模型分流:CLAUDECODESUBAGENTMODEL=haiku + Sonnet 主会话(@mirku21)
- X trendClaude Code /goal sets an endpoint to cut idle spinning (@thedelost)Claude Code /goal 设终点减少空转(@thedelost)
- X trendKarpathy's "answer in HTML" turned into a Claude Code/Codex/Cursor skill (@diamai)Karpathy「用 HTML 回答」做成 Claude Code/Codex/Cursor skill(@diamai)
- X trendClaude Code doesn't read AGENTS.md when CLAUDE.md exists (@torfinpd) and three fixesClaude Code 有 CLAUDE.md 时不读 AGENTS.md(@torfinpd)及三种修法
- PodcastLatent SpaceAnthropic's Thariq Shihipar on Claude Mods, artifacts, cloud-brain/local-hands and why Anthropic wants to pace the frontierAnthropic 的 Thariq 谈 Claude Mods、artifacts、“云端大脑 + 本地双手”,以及为何要放缓前沿节奏