2026年9月22日 技术热点总结

项目简介：Z.ai’s coding agent harness. Powerful, intelligent, extensible.

技术栈：TypeScript

核心介绍：飞书社群 · Discord 简体中文 | English ZCode 是 AI 编程工作台，提供桌面应用、浏览器界面和终端 Agent。本仓库包含客户端、后端服务、共享 UI，以及 Agent CLI 与运行时源码。 准备 Git、Node.js 24.14.0 和 pnpm 10.33.2，版本以 mise.toml 为准。以下开发和打包命令均在仓库根目录执行。 pnpm bootstrap 安装 workspace 依赖、准备桌面本地运行资源，再执行 build:bootstrap。 Agent CLI 与运行时源码位于 apps/zcode-cli/，作为普通目录随本仓库一起克隆，无需单独拉取或初始化 Git submodule。 根据需要选择其他初始化或构建入口： 默认 bootstrap 跳过远程资源准备，适

项目数据：⭐ 5,559 Stars，🍴 1,581 Forks

项目简介：Apple Wallet Card Skinner for iOS 18+ (No Jailbreak Required)

技术栈：Swift

核心介绍：> Apple Wallet Card Skinner & Lockscreen Passcode Themer for iOS 18+ (No Jailbreak Required) > Tested on iOS 27 release. > Powered by the airlift AirTraffic sync exploit.

关键特性：🎨 Custom Card Skins： Assign custom artwork, textures, or bank logos to Apple Pay and Wallet cards.；🔢 Lock Screen Passcode Themes (.passthm)： Apply custom keypad button artwork from popular .passthm themes directly to iOS 18+ lockscreen.；🧩 Passcode Theme Creator： Create custom themes from a single wa…

项目简介：A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI’s System One model for typed decisions.

技术栈：Python、awesome、awesome-list、jev、llm

核心介绍：A curated awesome list of public projects and practices built on Jev, TypeSafe AI’s System One model for typed decisions. This README is the homepage aggregate of the current category files, so the latest accepted entries are visible here without drilling into subpages.

项目数据：⭐ 976 Stars，🍴 128 Forks

A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subtasks. Collecting additional full-task demonstrations for supervised fine-tuning (SFT) requires operators to repeat behaviors the policy already performs well. Reinforcement learning (RL) fine-tuning offers a promising path to bridge this gap, but existing approaches struggle to solve long-horizon tasks using only sparse rewards. We present PARTS (Policy Adaptation with RL on Targeted Subtasks), a real-world subtask RL framework that concentrates practice at these bottleneck…

Concurrent local LLM serving on unified-memory desktops must preserve memory headroom and output fidelity, which speed-only rankings overlook. We introduce SiliconBench, which evaluates nine Apple Silicon serving engines through three lenses: speed, memory, and fidelity. We evaluate chat and agent serving on Qwen3, Qwen3.5, and Gemma 4. We use a classification task to check for quality regressions against an NVIDIA reference. DGX Spark provides a complementary serving-performance reference. Three desiderata guide interpretation: serving architecture readiness, memory discipline, and multi-n…

Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau. In traditional BI workflows, users need to prepare data by (1) identifying relevant tables, (2) performing data transformations, and (3) building join relationships, before they can (4) answer their business questions. These steps can be complex and time-consuming, making BI challenging.
Given the strong capabilities of large language models (LLMs) in working with data, we study their ability to answer BI questions end-to-end, without r…

Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes admit no reliable programmatic oracle. We introduce a continual adaptation framework in which a frozen frontier model operates professional design software through more than 230 tools, while an external procedural memory of natural-language skills accumulates and refines reusable design procedures from experience. The memory widens by acquiring procedures for recurring uncovered subtasks and deepens by revising existing procedures against t…

We need studies on conversational AI (CAI) at scale to understand human behavior and shape CAI design. However, fragmented reporting of systems and study configurations hinders replication, extension, and knowledge accumulation. We present Gricea, an open-science platform representing studies as configurable, deployable research artifacts that researchers can run, inspect, share, and reuse. Informed by a formative analysis of prior CAI research, Gricea couples study procedures, participant-facing systems, and conversational task behavior in. In a replication study using Gricea, we replicate…

Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engineering workflows whose outputs are persistent, structured artifacts. Mechanical computer-aided design (CAD) is a particularly demanding setting: an agent must manipulate geometry and constraints over long interaction horizons while producing a native project whose dimensions, construction structure, and downstream engineering state remain valid. We introduce CADWorld, a benchmark for long-horizon computer use in FreeCAD. CADWorld contains 20…