adriannoes/awesome-agentic-ai
Connect an agent here. 342 skills (Cursor, Claude Code & Codex), 107 research papers, 201 ML notebooks, 9 textbooks, 18 industry reports, 96 curated projects, 5,380 OpenClaw skills. Start at AGENTS.md.
周报
2026-W39 周报精选:开源 Skills 的商业闭环;A terminal-first multiplayer;本地开源配音与 Claude Code Skill
Connect an agent here. 342 skills (Cursor, Claude Code & Codex), 107 research papers, 201 ML notebooks, 9 textbooks, 18 industry reports, 96 curated projects, 5,380 OpenClaw skills. Start at AGENTS.md.
Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-task orchestration system
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline,
AutoClip : AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具
One-click portable ComfyUI installer for Windows, macOS and Linux, with EZi Desktop: a full dashboard for packages, environments and configuration 🔹 Nvidia GPU support 🔹 Pixaroma Community Edition
The ultimate collection of high-fidelity Seedance 2.0 prompts and Seedance AI resources. Discover Seedance 2.0 how to use for cinematic film, anime, UGC, social media, meme and advertising. Includes Seedance API guides a
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.
A set of custom nodes for ComfyUI
A set of evolving nodes that streamline the best use practices in ComfyUI.
Claude for Small Business now includes 43 workflows and 27 new integrations with tools small businesses already use, including Shopify, Salesforce, TikTok, Atlassian, Zoom, Xero, Gusto, Square, Stripe, and Zapier. The new workflows extend Claude from running the back office to gr
Starting today, Claude Cowork and chat are merging into one Claude. Bring a quick question, or hand over a report due at noon, and Claude takes it from there, even after you’ve closed your laptop. It’s rolling out on Pro and Max plans over the next few weeks, with more plans to f
📌 一句话摘要 作者以提问形式切入,探讨开源项目(特别是 Skills)背后的盈利逻辑与商业闭环。 📝 详细摘要 这是一条简短的提问式推文,核心意图是引导读者讨论或思考「开源 Skills」这一特定技术/产品形态是如何实现商业变现的。结合上下文(如前文提到的 GitHub star 与科普内容价值),该问题指向独立开发者如何利用开源工具构建可持续的商业模式。 📊 文章信息 AI 初评: 65 来源: dontbesilent(@dontbesilent12) 作者: dontbesilent 分类: 商业科技 语言: 中文 阅读时间: 1 分钟 字数:
📌 一句话摘要 介绍开源本地配音工具 yovoice,支持声音克隆与情绪控制,并附带 Claude Code Agent Skill 实现自动化配音。 📝 详细摘要 针对短视频和有声书制作中配音成本高、隐私泄露及操作繁琐的痛点,介绍了开源工具 yovoice。该工具支持 macOS 和 Windows,提供 IndexTTS、VoxCPM2、OmniVoice、Qwen3-TTS 等多种模型,具备本地运行、声音克隆及情绪控制能力。此外,项目附带了 Claude Code Agent Skill,允许开发者通过代码直接生成配音文件,极大提升了批量内容生产的
Hello HN, It started as an experiment: can Claude play chess properly if it uses vision instead of PGN notation? Somehow it can. The next experiment was to see whether Claude + Stockfish could explain a game. Somehow it can too. A few sessions later, I had a system that takes my
arXiv:2609.30249v1 Announce Type: cross Abstract: Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatical
GitHub Actions runner images
Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)
With Codex, GPT-Live-1, and GPT-6 Astra, Proaction builds, operates, and sells modern fleet management faster.
This week’s releases add new models to Copilot, local sandboxing in the Copilot app, and updates to Copilot in Slack, Microsoft Teams, JetBrains, and VS Code. GitHub Copilot Claude Opus 5.5 is available to Copilot Pro+, Max, Business, and Enterprise plans. GPT-6 Sol is available
You can now use an in-product validator for enterprise managed settings for GitHub Copilot. The validator detects malformed JSON, unsupported configurations, invalid team mappings, and other errors that can prevent policies from being enforced. Review and correct errors in the “C
The enterprise and organization repository-level Copilot usage metrics reports now break down how long pull requests spend in each stage of review. A new pull_request_review_times array on each repos-1-day row reports a median and a 90th percentile for the time from ready for rev
Queries for workflow runs in the GitHub Actions API and UI now return a less precise but more accurate count of records when you search by workflow, event, status, branch, or actor. We will continue to return paginated results of up to 1,000 items. However, if the number of found
Anthropic 宣布 Claude 在 Claude Science 系统中仅凭一条提示词、无人监督连续运行数天,算出平面 N=4 超杨-米尔斯理论六粒子振幅的九圈结果,超越 Lance Dixon 团队 2023 年的八圈纪录,总成本几千美元,其中直接自举路线的 Python 运行成本仅约 100 美元。
Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity, Kimi, Augment Code, Qwen, fully end-to-end encrypted
Microsoft is splitting its Copilot app into three sections: Home, Code, and a new agent called "Autopilot." Built on OpenClaw, the agent runs continuously in the cloud, where it can monitor Teams channels and complete tasks on its own, according to Microsoft. For Autopilot and Co
GitHub Security Lab 的 Antonio Morales 开源了基于 Taskflow Agent 的 Fuzzing Taskflow,指向 GitHub 仓库即可自动识别入口点、编写 harness、运行 AFL++、读取覆盖报告并分诊崩溃。
arXiv:2609.30205v1 Announce Type: new Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safety a
arXiv:2609.29014v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems can automate alpha factor mining, but their reliance on external APIs limits control over cost, availability, and confidentiality. Long research loops also tend to revisit a few s
Earlier this month, world model company Runway introduced GWM Worlds 2 , a research preview that “turns high-fidelity video and audio generation into real-time interactive simulation .” Runway calls this an “autoregressive diffusion” model; with autoregressive describing how it g
📌 一句话摘要 作者分享使用 Opus 5.5 结合 TokenRank 数据,通过单条提示词直接生成高质量营销视频的实操案例。 📝 详细摘要 作者指出 Opus 5.5 在结合丰富信息时具备强大的视频生成能力。通过在社群代码中嵌入单句提示词,模型自主完成了从数据分析到视频生成的全流程,且一次成功。提示词核心在于利用榜单多维度数据与参与者背景,针对付费用户设计爆款内容以促成转化。 💡 主要观点 Opus 5.5 在多模态视频生成上表现卓越 作者认为该模型在处理复杂信息并转化为视频时具有“无敌”的表现,能够一次性高质量完成生成任务。 极简交互即可实现自动化
From the earliest days of open-weight models to becoming the neutral routing layer for more than 10 million developers , OpenRouter is one of the clearest bets that the future of AI will be multi-model. In this episode, OpenRouter co-founder & CEO Alex Atallah, with AMP’s Anjney
📌 一句话摘要 作者总结近期工作,宣布随机抽取 5 名用户,免费为其制作产品宣传视频,要求用户提供网站和卖点。 📝 详细摘要 作者剪辑了一个产品合集视频后,发起了一项福利活动:邀请读者留言提供产品网站和核心卖点,将随机抽取 5 人免费制作宣传视频。这是对其前述 AI 视频生成能力的实际应用推广。 💡 主要观点 AI 能力的服务化变现/引流 通过提供免费的高价值服务(视频制作)来吸引精准用户互动,既展示了能力又增加了账号活跃度。 📊 文章信息 AI 初评: 70 来源: Berryxia.AI(@berryxia) 作者: Berryxia.AI 分类:
GitHub Copilot code review now offers additional personal configurations to an expanded set of Copilot plans and an enterprise-level default setting. These improvements are now generally available: A dedicated personal settings page for automatic review and your default review ef
📌 一句话摘要 小米 18 Pro 系列发布,主打 5999 元起步的性价比、硬件级防窥屏、大底潜望长焦以及通过 AI Vibe Coding 驱动的背屏生态,并推出万元级透明特别版以冲击高端市场。 📝 详细摘要 本文详细报道了小米 18 Pro 系列发布会的核心内容。产品线聚焦于小米 18 Pro 和 Pro Max 两款机型,重点升级包括:搭载超级像素 2.0 硬件级防窥屏、大幅提升长焦进光量的影像系统、以及首发第六代骁龙 8 系列处理器。其中,18 Pro 侧重于补全小屏旗舰体验(如 7000mAh 大电池),而 18 Pro Max 则探索性能与
📌 一句话摘要 推测 OpenAI 将在下周的 Dev Day 上发布名为 o 的个人助理产品,对标 Grok Bot。 📝 详细摘要 推文指出 OpenAI 即将在下周的开发者大会(Dev Day)上发布一系列更新,其中重点提及了一个类似 xAI Grok Bot 的个人助理产品,暂定名为 o。这属于基于行业惯例和近期动态的市场传闻与预测。 💡 主要观点 OpenAI 将推出个人助理产品 预计命名为 o,功能定位类似于竞争对手 xAI 的 Grok Bot,旨在进入 AI Agent 市场。 📊 文章信息 AI 初评: 65 来源: 小互(@imxia
Lovable co-founder Fabian Hedin said that apps created on the platform are getting nearly a billion monthly views each month.
Google's new Gemini 3.8 Live update lets users have conversations with the model while watching an animated AI persona respond in real time. The "Live Avatar" will lip-sync and show different facial expressions during conversations, but it's currently only available to Gemini Ent
Generative AI
📌 一句话摘要 作者分享基于 Obsidian 重新开发所需功能的经历,虽投入了较多 AI 编程成本且入不敷出,但获得了社区认可与少量赞赏,乐在其中。 📝 详细摘要 作者回顾了将个人需求转化为 Obsidian 插件的开发过程。提到使用了 AI 编程工具(Codex),消耗了 20 次重置机会,最终收到 100 多元的赞赏。虽然从经济角度看是“入不敷出”,但作者表达了开源助人的快乐和对成果的满意。这反映了独立开发者利用 AI 辅助进行小工具开发的真实生态与心态。 💡 主要观点 AI 辅助开发降低了个人工具定制门槛 作者利用 Codex 等 AI 工具完成
We seem to be entering into an AI agent renaissance. Meta's new consumer-facing AI agent, Muse, topped the App Store charts soon after its release and has 600,000 daily active users in the US, by an Apptopia estimate. And AI agent platform Instinct, whose eponymous creator is fun
📌 一句话摘要 本文探讨 AI 硬件从“对话助手”向“执行智能体(Agent)”的演进,分析了手机、家电、可穿戴设备在实现“能办事”目标下的不同挑战与技术路径,以及阿里云提供的全栈基础设施支撑。 📝 详细摘要 文章以云栖大会「AI 原生硬件论坛」为背景,指出 AI 硬件的竞争核心已从简单的功能演示转向能否真正感知环境、理解意图并完成复杂任务。手机赛道聚焦于通过 Agentic OS 实现跨应用的长程任务执行;家电赛道致力于从单设备控制转向家庭目标的协同管理;可穿戴设备则利用第一视角感知实现主动服务。阿里云通过提供 Qwen Intelligence 方案
Suno’s AI vocalists could learn a thing or two from this glitchy image. | Image: Cath Virginia / The Verge, Getty Images Sony and Universal Music Group filed yet another suit against Suno. The labels claim its new v6 model still infringes on their copyrights because it's trained
Meta launched Muse earlier this month. It soon became the top free iPhone app in the US. It is a cousin of Instinct , the invite-only assistant you text, and of OpenClaw agents like my AI chief of staff, R Mini Arnold . Jolly, Muse’s digital avatar, is just cuter, and probably ea
This is the final notification that Node 20 is no longer available on GitHub Actions runners. Runners now use Node 24 for JavaScript actions. The temporary ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION opt-out is no longer available. If you maintain a JavaScript action, update its runs
arXiv:2609.26274v1 Announce Type: cross Abstract: The rapid evolution of generative AI (e.g., Sora, Hunyuan) makes it essential to develop effective detection strategies that can generalize across ever-evolving synthesis techniques. This study is motivated by the observation of a