2026年10月10日 技术热点总结

项目简介：AI 自主渗透测试系统 | 百度“agent+”攻防挑战赛冠军项目

技术栈：Go

核心介绍：AI 自主渗透测试系统（Go 后端 + Next.js 前端） 🌐 在线 Demo： https://artex-demo.vercel.app/ 📦 该仓库为ARTEX最后一个版本纯源码备份，docker部署源失效自行让AI本地构建即可 > 完整交互见在线 Demo。 全局「审批记录」、任务内「拦截审批」及对话中的审批卡片均支持展开查看详情。展示结构参考 AegisHook 的审批详情组件，沿用 ARTEX 的组件和主题： 支持从 ScopeSentry 直接同步资产数据，免去重复收集：

项目数据：⭐ 2,134 Stars，🍴 4,379 Forks

项目简介：让 Codex 通过 USB 操作真实 iPhone：引导安装、App 自动化、实时屏幕与截图回退。

技术栈：Python

核心介绍：让 Codex 通过 USB 操作你的真实 iPhone。用自然语言描述任务，Codex 就能打开 App、读取页面、点击、滚动、输入文字、整理列表，并在侧边栏展示手机屏幕。 iPhone Use 使用 WebDriverAgent（WDA）与 iPhone 通信，包含本地 MCP 服务、安装与使用技能，以及实时屏幕 widget。它优先复用现有连接与构建；控件定位失败时，指导模型查看截图并尝试坐标点击。 插件默认向独立的 PostHog 项目发送匿名使用统计，包括启动、工具调用、连接状态、耗时和错误类别。使用随机安装标识，不上传手机画面、输入内容或设备标识。设置 IPHONE_USE_ANALYTICS=0 或 DO_NOT_TRACK=1 并重启 MCP 服务可关闭。详见 埋点与分析说明。

项目数据：⭐ 1,707 Stars，🍴 160 Forks

项目简介：Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer.

技术栈：Python、ai、dividends、etf、finance、financial-planning、fintech、investing、llm

核心介绍：own computer, with an AI advisor you can talk to. Your records are kept on your machine. The AI part is optional: it goes through OpenRouter with your own key. You need Git, Node.js 22 or later and uv. Then: git clone https://github.com/LosaLosSantos/aurelio-finance.git ./start.sh –demo # macOS and Linux git clone https://github.com/LosaLosS…

项目简介：GridCraft: an open-source, clean-room spreadsheet (Microsoft Excel-style) in pure Rust. By ArtCraft.

技术栈：Rust

核心介绍：GridCraft Spreadsheets and data; an open-source, clean-room reimplementation of Microsoft Excel, rebuilt in pure Rust. A fast, open-source, clean-room take on the Excel workflow. It runs natively on macOS, Windows, Linux and BSD, and in the browser via WebAssembly. By the ArtCraft team. GridCraft on getartcraft.com · ArtCraft · All Crafting Apps

项目数据：⭐ 1,161 Stars，🍴 456 Forks

项目简介：Whole-disk file search for macOS: fuzzy names, typo tolerance, indexed content grep. ~1 ms over 8M files.

技术栈：Rust

核心介绍：Whole-disk file search for macOS. Finds any file by name in about a millisecond, forgives typos, and searches inside files with an index. Use it as a CLI (with a small daemon) or as a Rust crate. cargo build –release && ./target/release/fsearch install # -> ~/.local/bin/fsearch fsearch fsearch main # find files by name fsearch ‘ext:rs grep:apply_dir’ # search inside files M4 Max, 7.7M files and folders on disk. Chromium (509k files), sa…

Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields and AR specialising in discrete tokens. Recent work seeks to combine the advantages of the two models, and each hybrid fixes its decoding schedule by design. In this paper, we ask whether the performance of decoding schedules of one model can be predicted before decoding at a fixed number of steps. We describe diffusion, AR, and models in between as paths on one corruption lattice, and define the cost of a schedule as the dependence its paralle…

This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the network weights. Two e-puck-type robots, controlled by a GRU network with residual connection, were evaluated in a food-seeking task with social signaling. The sensory and motor translation layer required three corrections for stable physical operation, including the calibration of a hunger term based on a measurable asymmetry in the trained residual weights. Even with these corrections, the transfer was partial and asymmetric: one agent re…

This work examines the transfer of a co-evolved communication mechanism between two robotic agents from a discrete two-dimensional (2D) simulator to a three-dimensional simulator with real physics (3D). The study focuses on whether a communication mechanism co-evolved in a 2D environment retains its functional role after transfer to a 3D physics-based simulator. To support this analysis, the effects of the episode time budget, the social cue, and the asymmetry between the two co-evolved roles were examined. The results indicate that the success rate increased approximately linearly with the…

Long-horizon coding agents need timely corrections, yet feedback can be ineffective or even harmful when it misjudges ongoing work or fails to address the underlying problem. Existing critics focus on evaluating trajectories and generating feedback, but rarely track what happens after feedback is delivered. We present Opera, a verbal critic framework that treats each correction as a persistent note, followed until the diagnosed problem is resolved. Opera decides when to review through periodic and event-driven triggers, diagnoses issues with typed operators, audits feedback against visible …

Agent skills are SKILL.md instructions and scripts that AI coding agents such as Claude Code and Codex run with the permissions of their user. Developers share skills by copying them between repositories, which makes them a software supply chain without a registry, versions or provenance. The origin of a copied skill, the reach of a security fix and the repositories that warrant review are therefore unknown. Studies that record which repositories hold a skill at a single point in time cannot reveal who copied it from whom. We contribute the first dated copy network of agent skills, built fr…

Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable over long rollouts. Most of their error occurs where the cable touches itself or the floor. Attention over all pairs of cable segments can represent contact between parts of the cable that are far apart along its length, but attention has no notion of geometry. A cable has two pairwise distances, which agree only while it is straight: the arc-length distance along the cable, which governs elastic forces, and the Euclidean distance in space, whi…