2026年8月31日 技术热点总结

项目简介：✨ agentic app store previews and screenshots

技术栈：TypeScript

核心介绍：goldie makes App Store screenshots and app preview videos for an iOS app. argent replays flows on a simulator; goldie frames the captures with a device bezel, background and headline, joins the clips into a preview video, and checks the result against Apple’s upload rules. goldie is framework agnostic. It drives the app through the simulator, so it works the same for SwiftUI, UIKit, Flutter, React Native and Kotlin

项目数据：⭐ 716 Stars，🍴 58 Forks

项目简介：Free & Open-Source CapCut replacement.

技术栈：TypeScript、audio-processor、auto-caption、automation、capcut、capcut-alternative、content-creation、cross-platform、desktop-app

核心介绍：WolfCut is everything you use CapCut for — without the watermarks, paywalls, or subscriptions. A native Rust engine does the heavy lifting, a clean React interface does the editing, and it all runs on your machine: install it and start cutting, no account, no extra downloads, no setup.

关键特性：Free and local Text-to-Speech features.；🎬 Multi-track editing, with several timelines per project when one isn’t…

项目简介：An agent organization for Claude Code, structured as a company — 15+ departments, 125+ skills, each independently installable.

技术栈：Markdown、agent-marketplace、claude-code、claude-code-plugin、claude-plugin、claude-skills、mcp

核心介绍：headcount Add a department, not a prompt. Open the interactive org chart — search every skill, open a department, jump to the source. An agent organization for Claude Code, structured as a company: a chief executive over 16 departments, 146 skills in total. Every department is an independently installable plugin, so a project loads only the f…

项目简介：Run iOS/ macOS in Qemu. Virtual iPhone 17, 16, 15, 14, 13, 12 and M5-M1 Apple Si Macs supported.

技术栈：Python

核心介绍：Run iOS/ macOS in Qemu. Supports emulating iPhone 17, 16, 15, 14, 13, and 12 (A19-A14) and M5-M1 Macs (tested with Macbook Air and Mac Mini). You can debug the kernel, edit the root filesystem, and run a root shell + custom programs. Darwin Kernel Version 27.0.0: Tue Aug 11 22:05:33 PDT 2026; root:xnu-13432.1.9~3/RELEASE_ARM64_T8142 pmap_startup() init/release time: 893478 microsec vm_page_bootstrap: 463555 free pages, 25917 wired pages VM bootstrap: 73 maps, 2…

High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representation should include physically based rendering (PBR) modalities such as albedo, metallic-roughness, and surface normals. We propose Luce, a 3D representation that unifies geometry and PBR materials within a voxelized multimodal Gaussian cloud, using dedicated Gaussian primitives for each modality. A variational autoencoder compresses this representation into a unified material-aware latent space. …

Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs). However, these methods typically rely on repeated generation or external verification. To address this limitation, we introduce CritICL, a novel inference-time framework that improves reasoning while maintaining high efficiency. Our key insight is that LLM failure modes exhibit structured patterns across model scales within the same family. Instead of treating failures as undesirable outputs, CritICL leverages them as a source of guidance. Specifically, we utilize…

Contact-rich manipulation requires adapting to contact states that can evolve substantially within an action horizon. However, chunk-based vision-language-action models predict complete action chunks from observations collected before execution, leaving tactile conditioning stale during execution. Existing tactile-reactive approaches typically rely on separate high-frequency controllers, which increase both architectural and training complexity. In this paper, we introduce TacForcing, a streaming action-generation framework that effectively incorporates execution-time tactile feedback. Inst…

Evaluation artifacts specify a forward computation: a task, scorer, and reported metric. They do not necessarily license the claim attached to that metric because the historical evidence and alternative semantics needed to replay it may be unbound. We formalize this missing claim-replay layer through a frozen substrate D, a grounded family F, a claim query q, and the resulting identified set. We then census all 124 mechanically eligible Inspect Evals units at a pinned commit. Every unit receives a terminal disposition; 110 stop before deterministic inference because required historical evid…

Conventional video editing primarily focuses on scene-level content, whereas live streaming places greater emphasis on the human subject. However, directly applying existing video-editing methods to human-centric live streaming remains challenging, as they may introduce facial-expression inconsistencies and typically depend on multiple offline inference steps, making them unsuitable for real-time interaction. We propose EditaLive, a novel framework for real-time streaming character video editing. In detail, we start from a pretrained image animation model (Wan-Animate), which naturally deco…

Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run or immediately apply and validate lessons learned from it. We argue that self-improvement should instead be live, using emerging experience both to redirect the active run and to update the persistent harness. Existing agent architectures do not fully support this goal. Single-agent self-correction combines task execution and trajectory assessment within one context, while su…