与「Agents」相关的搜索结果

🏫 想把 AI agent 真正做上线的看这里，Agentic System Course 用 22 章讲透生产级 agent 怎么设计、搭建和运维。 Agentic System Course 的 fork 已经接近一百个，而且整套课是写给你和你的 AI 一起读的，仓库里同时放了 AGENTS.md 和 CLAUDE.md。 以前学 agent 开发，要么跟着某个框架的教程一步步敲，换个技术栈就全废；要么零散看博客，记忆、多 agent 协作、成本控制各讲各的。 这门课只给骨架：把记忆与状态、多 agent 协调、外部接口、可观测性、成本与延迟、安全运维这些承重的主题和取舍讲清楚，具体代码交给你的 AI 按你的技术栈去补。最后一章是一张设计画布，直接拿来设计你自己的 agent。 还有个顺手的：仓库自带一个评审 skill，把你的 PRD、设计文档或 agent 代码丢给它，它先判断你做的是个人项目、团队工具还是面向客户的产品，再挑相关章节出报告，每条问题都带严重程度、证据、章节出处和修复建议。课程拿 OpenCode、Hermes Agent、OpenClaw、Paperclip 四个开源项目当参考实现。 用 agent 学 agent，这个思路挺对味。 GitHub：

A lovely song and a lovely video can still be completely wrong for each other. That’s why Montage Studio caught my attention on @termix_ai It takes a brief, plans the shots, hires other agents for the storyboard, music and video, then edits everything into a finished piece. I’d be paying for someone to make those choices work together. Otherwise I’ve bought three nice files and accidentally become the project manager. For creators, that’s a useful way to judge these services: how much work is actually left when the delivery arrives? I’d quite like to receive the video and remain peacefully uninvolved in its staffing issues.

24 小时在线的 AI Agent 助理，靠这五样东西 一直在线的 AI 助理，会盯邮件、等回复、到点提醒你。可它大部分时间其实在睡觉，不调用模型，也不花钱。 Anthropic 刚发文拆开讲了这种一直在线的 Agent： 一件事进了收件箱，它才醒过来跑一次； 定时器让它没人叫也能主动； 记忆文件夹让它醒来还记得你； 权限让它拿着你的账号也不乱来； 发件箱决定它什么时候开口。 这期一样一样讲清楚：它怎么醒、两件事同时来会不会打架、记忆为什么要省、要紧的事怎么等你拍板，以及为什么一开始最好让它安静一点。 来源 - Anthropic《Building always-on agents》（2026.11.13），作者 William Hu：

Anthropic just published an engineering guide on how to build always-on agents. The biggest misconception: an always-on agent does NOT run 24/7. It sleeps almost all day, wakes up for short runs, saves state, and goes back to sleep. The 5 core pieces I distilled: 1. Event Inbox Put a database table between webhooks and your agent. Acknowledge webhooks fast, run only one active worker per user so runs never collide, and batch rapid messages together. 2. Timers Keep timers in a separate table from the inbox. Split them into one-off follow-ups and recurring schedules. A background poller drops due timers into the inbox. 3. Lean Memory + Dreaming Only store what cannot be looked up again: user instructions, user notes, past messages, and task progress. Load a small index at wakeup, not every file. Run periodic dreaming passes to clean out stale facts. 4. Unattended Permissions Never put raw API keys inside the agent sandbox — inject them through an outside proxy. Use Deferred Tool Calls to pause risky actions for approval without blocking the worker. 5. Outbox Queue outgoing replies so your agent paces notifications instead of spamming users at 3 AM.

学 Agent 开发的时候，最头疼的往往不是概念，而是找不到能直接跑通的完整示例。 NirDiamant/GenAI_Agents 这个仓库就攒了一大批实战教程，范围从最简单的对话机器人一直铺到多智能体协作这种复杂系统，每一份都附有全量代码和讲解说明。 内容既包括入门级的对话问答，也讲了 LangGraph、MCP 这些框架怎么用；商业侧有客服、简历筛选、合同分析等落地案例，创意生成和信息分析方向同样有所覆盖。 市面上常见的 Agent 应用类型，基本上都能在这里找到可参照的实现。 除此之外，还有一套从提示工程讲到生产部署的课程，拆成 17 个模块，配了视频和练习题，带你从结构化提示一步步搭出真正能跑的系统。 无论是想系统学习，还是找参考实现，都挺合适。 仓库地址：

is worth checking out for recon and external attack surface management. It doesn't just list subdomains. It verifies them and grabs screenshots. It checks for takeover risks and flags open ports. All in one scan. The free tier gives you 2 domains/day with no account needed. It runs entirely in the browser. No setup. No agents. Visit: #SubdomainFinder# #AttackSurfaceManagement# #CyberSecurity# #Recon# #BugBounty# #OSINT# #InfoSec# #SubdomainTakeover# #SecurityTools# #Pentesting#

Now your dot can securely complete purchases on your behalf—with your approval. With ChatGPT Wallet, agents pay without access to your actual card details. Every purchase requires a security check. ChatGPT Wallet is rolling out starting today to dots, for Pro subscribers in the US.

We are deeply sorry for the disruption this incident has caused our customers and partners. We know the trust they place in our services and take that responsibility extremely seriously. We are seeing broad recovery and stability across our services. This was a technical issue not related to cyber or AI / agents. The incident was introduced by an issue during an earlier network capacity upgrade that surfaced following a recent network change. We have addressed the underlying issue and continue to restore service to remaining customers and regions. Given the scale of demand, we restored services gradually, validating stability at each stage. While this took longer, it helped ensure a stable restoration. We will provide a full post-incident report once our review is complete.