阿里云在云栖大会上展示 CIPU 3.0，称其全面超越 Nvidia BlueField 4 / CX9，直接对标 Nvidia 两年后发布的 BlueField 5 和 CX10。CIPU 2.0 在 400Gbps 的发布仅比 BlueField 3 晚几个月，实际性能远超 BF3。阿里云同时发布新一代全栈自研高性能存储 CPFS，将 AI 存储成本降低 69%。
Awaiting translation
PostgreSQL 19 Beta 4 发布，移除了 SQL/PGQ 属性图查询、不停机启停数据校验和、FOR PORTION OF 时态更新删除、分区合并拆分 ALTER TABLE 命令，以及角色、表空间和数据库的 DDL 获取函数。
Awaiting translation
Nous Research 发布 Hermes Agent 0.21.5，为桌面插件引入 SDK，包含草稿 API、会话列表与侧边栏界面元素、设置/技能/配置的类型化桥接，以及插件后端的事件互通。
Awaiting translation
OpenClaw 2026.9.6 的 macOS 初始构建因启动崩溃，已于 9 月 24 日 09:52 UTC 替换为通过 Apple 公证的修复版。受影响的是已安装早期 2026.9.6 构建的用户，需重新安装一次 DMG；2026.9.5 用户可直接在应用内更新。npm 上的 2026.9.6 包未变动，该项目免费且不提供自有云服务。
Awaiting translation
CloudNativePG 1.30.1 修复了扩展路径校验绕过漏洞：此前含 `..` 的绝对路径可通过验证，运行时解析后能逃出扩展挂载点，现在这类记录会在 admission 检查、主版本升级和已存 Cluster 规格处理时被拒绝或跳过。
Awaiting translation
Cloudflare 的 workerd 1.20260924.1 新增 env.AI.websearch 接口，为 Workers AI 提供网页搜索，并把 REST 请求的调用方上下文传给下游 AI Gateway。
Awaiting translation
Lovable launches Chats, an agent that runs at the workspace level, can hold conversations across projects and trigger builds; once changes are confirmed, it hands the task off to the project's builder agent and brings progress back into the conversation.
Why it matters: Lovable shares the three-layer architecture behind Chats—trajectory, inbox, and activation—which you can adapt for your own multi-agent orchestration.
Lovable 聊天功能现已免费开放，Free、Pro 和 Business 工作区每天都有免费聊天额度。用户可以让它评估该做哪个创意、把客户反馈整理成计划，或分析已上线应用的代码和 Lovable Cloud 数据库用量。聊天在生成图片、视频或转交 Plan、Build 时仍照常消耗 credits，当前聊天定价（含每日免费额度）适用至 2026 年 10 月 31 日。
Awaiting translation
Visual Studio Code 1.139 稳定版发布，AI 智能体现在可以在 SSH、Tunnel 和 WSL 远程主机的 Dev Containers 中构建和测试项目，使用容器内配置的工具与依赖。
Awaiting translation
GitHub 于 9 月 23 日为 GitHub Copilot App 推出本地沙箱，目前处于公开预览，仅适用于使用本地仓库和工作树的会话。沙箱可分别限制文件系统读写路径、外网与局域网访问，以及 Git credentials 和 GitHub CLI 数据的使用，企业策略还能进一步收紧；若操作系统无法应用规则，隔离环境会报错退出而不执行命令。
Awaiting translation
UiPath 于 9 月 23 日更新 UiPath Platform，Automation Suite 全栈现可在本地 Linux 基础设施上运行，面向有数据存储、安全和环境控制要求的企业。
Awaiting translation
systemd 262 于 9 月 22 日发布，可将 PID 1 与 executor 编译为单一静态链接二进制文件，用于小型容器，且不通过 dlopen() 加载额外库、无需 NSS 查找用户和组。
Awaiting translation
Cursor has released two bots, Rollouts and Security Review, both available on Team and Enterprise plans.
Why it matters: The official docs cover the monitoring and security review workflows for both bots, so readers can judge whether they fit into their existing delivery pipeline.
Lovable has shipped Opus 5.5, which the company says matches Opus 5 in results while cutting the number of steps by one-third to one-half. On Lovable's internal benchmarks, Opus 5.5 ties Opus 5 on 0-to-1 builds and iterative code changes, and comes out 4% to 6% ahead on validation discipline; across all reasoning effort levels, steps per task drop by 26% to 57% and input tokens fall by 21% to 59%, with the differences significant at the 95% confidence level.
Why it matters: Lovable shares official comparison data between Opus 5.5 and Opus 5 on step counts and tokens, so readers can judge the real change in build efficiency.
Cline CLI 3.0.63 发布，修复了 Windows 下可能从工作目录而非系统 PATH 执行 rg、git、powershell 的问题，恶意仓库放置的 rg.exe 等文件可能在索引阶段、确认提示之前就被执行，新版本在 CLI 及其后台服务启动时禁用该行为。
Awaiting translation
Lovable 与 AWS、CrowdStrike、Databricks、Docker、Google Cloud、Okta、Proofpoint、Salesforce、ServiceNow、Wiz、Zscaler 共同成为 Blueprint Alliance 创始成员，该联盟推动面向企业级 AI 智能体安全与治理的开放参考架构。
Awaiting translation
Foremerge 是一个位于 git 之上的本地协调层，不改变 git 和 worktree 的工作方式。每个智能体在编辑前先发布意图和将要改动的范围及操作，第二个智能体发布时若与已有意图冲突会返回 HIGH 级别的 destructive_vs_additive 提示，检测是确定性的，不依赖评审模型读代码。
Awaiting translation
Superpowers 6.4 发布，新增对 Meta Muse、OpenCode 2.0 和 Qwen Code 三个编程智能体的支持，并重写了 executing-plans 技能中的 Native Execution。
Awaiting translation
Claude Code 从 2.1.277 版本开始支持 AGENTS.md：当文件夹中没有 CLAUDE.md 时，Claude 会检查并使用 AGENTS.md。该支持基于 Claude Code mods 构建，这是其即将推出的定制 Claude Code harness 的方式，属于内置 mod，用户之后也可以自行构建自定义版本的项目指令。
Awaiting translation
Ordewell 是一个面向编码智能体的任务编排工具，把用户给出的一个目标转成可读可改的任务计划，每个任务指定所用的编码智能体、模型和思考强度，独立任务并行执行且各自使用独立 git worktree。
Awaiting translation
Lovable has released OJ, a preview engine written from scratch in Rust. It reads your existing vite.config.ts and runs real Vite plugins through a compatibility layer, all in a single binary, with no toolchain installed into the project.
Why it matters: Lovable rewrote its preview engine OJ in Rust, sharing cold start and memory comparisons against Vite, plus canary data from production.
Cline has released an early version of its open-source desktop app, Cline Desktop, moving the agent runtime that previously lived in the VS Code extension and CLI into a standalone workspace. It supports parallel sessions, scheduled tasks, and a Marketplace for extending tools and integrations.
Why it matters: The official release lays out the desktop app's capabilities and open entry points, so readers can judge whether it fits their multi-agent parallel workloads.
Cursor introduces “Projects,” a feature built for long-running work like a single feature, a migration, or an entire application. It keeps context over months and delegates tasks to thousands of sub-agents. Projects are powered by cloud agents: the coordinating agent doesn’t write code, it only plans, assigns work, and hands back results, spinning up local agents when on-device testing is needed. Each project keeps a set of files synced between the cloud and local machines, steadily accumulating research findings, artifacts, and knowledge of the codebase.
Why it matters: The official docs lay out the context-sharing and auto-triggering mechanisms for project-based multi-agent collaboration, which you can use to judge how long-running tasks get taken over.
Lovable 正式启动 Partner Program，分为面向独立开发者和小型机构的 Expert 与面向咨询公司、系统集成商的 Solution Partner 两条路径，并提供 Partner Directory 供企业查找和雇佣伙伴。
Awaiting translation
Lovable 上线 drafts 功能，为项目创建带独立对话和预览的副本，团队可并行探索同一项目的多个版本，改动只有接受并发布后才会应用到线上应用。该功能适用于任何项目，首个版本仅覆盖前端改动，涉及数据库结构或登录设置的修改仍需在项目对话中完成。
Awaiting translation
GitHub has launched Project HydraFusion as a research preview in the Copilot CLI. It uses runtime orchestration to pick an execution plan across models from multiple providers. Users select it just like any other model, and billing follows each model's standard rates.
Why it matters: GitHub lays out three orchestration modes for HydraFusion and compares cost versus quality across three benchmarks, so you can judge the trade-offs of multi-model orchestration on real coding tasks.
前 Yandex 搜索与广告负责人 Andrey Styskin 与曾为 Alexa 构建 web grounding 的 Matthias Petri 推出 Keenable，已从 Accel 和 Conviction 融资 2600 万美元，自建 crawler、索引和 ranking stack，索引超过 1000 亿文档。
Awaiting translation
Cursor supports self-hosted machines: code repositories, build artifacts, and secrets all stay on internal machines within your own infrastructure, and the agent handles tool calls locally. My Machines connects a single laptop or VM to a personal workflow, while Team Pools are named worker queues for teams or enterprises—scaling capacity up with requests and down when workers disconnect. Pools aren't tied to code repositories, and idle machines can sleep and then resume within a reconnection window.
Why it matters: The official docs lay out pooled scheduling and sandbox integration for self-hosted machines, so readers can judge whether tool execution can stay within their own network.
Lovable 现已接入 Fable 5.1，早期测试显示其在修复和改进现有应用上比 Fable 5 最高提升 17%，单任务成本最多降低 31%。该模型在中等和高推理强度下的 UI 与视觉设计质量最高提升 3.5%，并会在完成任务前打开浏览器运行应用进行自我验证。Lovable 正将卡住的会话以及更长、更复杂的任务路由到 Fable 5.1。
Awaiting translation
Terminal-Bench 发布 4.0 版本，校准任务的时间、CPU 和内存资源，修复 19 个任务并移除 8 个饱和或存在质量问题的任务，所有任务统一设为 8 小时 agent 超时。
Awaiting translation
Cursor 云端智能体不再需要连接 GitHub 或其他第三方 SCM 提供商，用户可直接输入提示开始工作，Cursor 会在后台创建 Origin 代码仓库。满意后可点击“创建代码仓库”将工作保存到 Origin，并设置私有或内部可见性。Cursor 还能通过端口转发在浏览器中实时预览云端智能体环境，连接 Vercel 账户后点击“发布”即可生成可访问 URL。
Awaiting translation
Vercel Connect 结束公开测试正式 GA，用运行时按任务申请、自动过期的短期 token 取代长期凭证，应用无需存储 provider secret。
Awaiting translation
Proliferate 发布开源、可自托管的 AI IDE，可在同一处使用 Claude Code、Codex、OpenCode、Cursor 和 Grok，并保留各自的推理与配置选项，包括 Bedrock、Azure 和自托管推理。
Awaiting translation
OpenAI has launched Daybreak, combining ChatGPT, Codex Security, and the open-source Codex Security CLI into a security defense workflow that covers pre-merge PR reviews, repository and vulnerability backlog scans, and regular CI checks.
Why it matters: The official documentation walks through the full Codex Security workflow—from PR reviews and repository scans to CLI-based batch scanning—so you can decide how to plug it into your existing security processes.
Cursor has updated its cloud agents and Cursor harness so cloud agents can subscribe to event sources, resume when there's new activity in a PR, Slack thread, or scheduled task, and keep going until the work is done—fixing CI failures and handling bot comments.
Why it matters: Cloud agents are moving from one-shot runs to subscribing to events and following up continuously on PRs and Slack threads, which gives readers a way to judge how the boundaries of automation are shifting.
OpenAI has open-sourced the harness that drives the Codex app, CLI, and IDE extensions, and through the Codex app-server client protocol it exposes capabilities like creating threads, starting turns, receiving events, and handling approval requests.
Why it matters: With the Codex harness and app-server protocol now public, developers can see how to embed the agent in their own products and where the boundaries are.
作者发布 Claude Session Viewer（github.com/jerrywu001/cc-sessions-viewer），面向 Claude Code、Codex、Antigravity CLI 和 opencode，集中管理本机 AI 编程会话。
Awaiting translation
Augment Code has extended its Cosmos review system from code review to a full PR-to-merge loop, adding four capabilities: Verifier, PR Fixer, Review Dashboard, and cosmos approve. Dedicated Experts handle risk analysis, line-by-line correctness review, design review, runtime verification, and fixes.
Why it matters: Augment has expanded code review into a PR-to-merge loop covering fixes, verification, and approval, giving readers a way to judge how multi-agent division of labor plays out in practice.
Lovable 宣布完成 4 亿美元 C 轮融资，估值达 133 亿美元，由 Menlo Ventures 领投、Scaleup Europe Fund 联合领投。
Awaiting translation
Anthropic 宣布从 8 月 14 日起，Pro、Max 和 Team 套餐的新会话默认运行 auto mode，并停止对分类器额外 token 开销收费；Enterprise、Claude API、AWS、Bedrock、Google Cloud 和 Microsoft Foundry 暂时保持可选，计划下个月改为默认。
Awaiting translation
Why it matters: Anthropic 公布 auto mode 的安全评测数据与内部拦截案例，可据此判断默认权限模式对现有工作流的影响。