2026年8月24日 技术热点总结

项目简介：x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger’s full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

技术栈：Zig、ai-agents、ai-debugging、binary-analysis、claude、claude-code、malware-analysis、malware-research、malware-scanner

核心介绍：x64dbg-MCP Server MCP-powered agentic reverse engineering for x64dbg. Features • Install • Usage •…

项目简介：Purge multi-vendor AI watermarks: clean Unicode text, apply statistical rewrite hooks, and clear C2PA plus metadata from PNG, JPEG, SVG, PDF, DOCX, HTML, and MD.

技术栈：Python

核心介绍：_ _ _ ____ ___ ____ ____ _ _ ____ ____ _ _ ____ ____ ____ _ _ ____ _ _ ____ ____ Agent skill + stdlib Python service that strips multi-vendor AI provenance marks from text and files. For privacy and hygiene on content you own. The skill is a thin HTTP client — the agent host needs no Python. All work runs in the service. Covers class-level marks from Claude, Gemini/SynthID-Text, OpenAI …

项目简介：DeepSeek Harness（DSH）一只住在 DSH 界面右下角的小鲸鱼娘，帮你盯着DeepSeek账户余额。QQ弹弹，支持拖拽吸附、左吸附翻转、数字滚动动画，随界面自动启用，建议直接喊来你的dsh安装

技术栈：JavaScript、cordis、deepseek、deepseek-harness、developer-tools、dsh、dsh-plugin、dsh-plugins、floating-widget

核心介绍：DeepSeek Harness（DSH）Web 界面右下角的常驻余额挂件：小鲸鱼气泡图 + DeepSeek API 余额 + 今日已用 + 每轮对话消耗统计，每次打开界面自动启用。本项目是标准 DSH 插件包，可通过 dsh plugin 安装/卸载。

项目数据：⭐ 714 Stars，🍴 28 Forks

项目简介：Provider-neutral Codex Skill for producing verified AI presenter videos from a script and an authorized presenter image.

技术栈：Python、ai-video、codex、codex-skill、digital-human、video-generation

核心介绍：一个面向 Codex 的通用数字人视频制作 Skill。输入主题或文案与授权人物图后，它会组织文案、配音、人物生成、口型校准、字幕与关键词动效、剪辑、渲染和质量验收。 它按能力选择当前环境可用的工具，项目源码不绑定服务商、模型名称或私有接口。 1. 一个主题或一份完整文案。 2. 一张经过授权、包含清晰成年人物的参考图。 可选输入包括声音样本、屏幕录制、图片、B-roll、品牌素材、目标平台、时长、横竖屏、风格、水印和结尾引导。

项目数据：⭐ 648 Stars，🍴 105 Forks

Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures discovered in one episode are usually discarded after execution. Existing skill libraries provide reusable executable routines, but are typically assembled offline and do not grow from the agent's own workflows. We introduce FlowEvo, a training-free framework in which workflows and skills co-evolve at inference time. FlowEvo compiles successful workflows into callable skills, stores them in a persistent bank, and uses retrieved skills either through direct execution or as conte…

We introduce TinyCast, an attention-free zero-shot forecaster that emits a predictive distribution from 146,505 parameters, on the premise that at this size the periodic structure of a context is worth computing rather than learning. A zero-parameter spectral detector supplies the dominant periods, the context is folded on their phase, and a dilated convolutional encoder and a block-autoregressive quantile decoder model the rest. It is smaller than every zero-shot entry on the GIFT-Eval board whose parameter count can be established. On probabilistic accuracy it defines the size-accuracy fr…

Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pair classification, and retrieval. In aggregate the two paradigms are effectively tied: the best LLM (Gemini 3.1 Pro, 77.6) and the best embedding model (77.2) differ by 0.4 points. Their strengths differ by task: LLMs lead on reasoning-heavy retrieval, embedding models lead on classification, and…

Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no mechanism to allocate additional computation to difficult or consequential choices. We introduce τ_0-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem through world-model-guided test-time computation. At each inference step, the high-level policy uses executi…

LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish command-generation errors from failures introduced after generation. QuoteBench measures this boundary with exact final-state validation on 56 one-shot tasks from 14 incident-derived families, crossing the generation contract with the execution transport around one deliberately unescaped added parser. Escaping at the interpolation point reproduces each replayed reply's raw-path outcome, so any recovery under a disclosed boundary must …

Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model—the harness—is typically treated as a fixed artifact after deployment. This work studies an alternative where the harness is task-specific and continuously evolvable: each task family maintains its own harness, which is hot-swapped across iterations through a fixed task-injection seam and rewritten using environment feedback. We introduce Hierarchical Self-Improvement (HSI), a framework in which a single frozen LLM M operates across three hierarchi…