2026年7月6日 技术热点总结

项目简介：autonomous red teaming platform; multi-agent offensive-security meta-harness

技术栈：TypeScript、agents、ai、multi-agent、offensive-security、redteam

核心介绍：Point it at an authorized target and the kill chain runs itself: recon → exploit → report, from a browser War Room or the CLI, driven by the agent you’re *already* signed into — Claude Code, Codex, Hermes — or a model you run fully offline (Ollama, LM Studio, vLLM). No new API keys, no cloud tenant, no second bill. Your agent is the brain; T3MP3ST is the war machine bolted around it. **Self-hosted storm. Keyless warfare….

项目简介：Command & Conquer Generals: Zero Hour running natively on macOS, iPhone & iPad — real engine (EA GPL v3 source, via GeneralsX), DXVK/MoltenVK renderer, RTS touch controls. No game assets included.

技术栈：C++、apple-silicon、command-and-conquer、dxvk、game-port、generals-zero-hour、ios、ipad、macos

核心介绍：skirmish, and Generals Challenge, with touch controls built for RTS (tap-select, drag-box, long-press deselect, two-finger scroll, pinch zoom). No emulation: this is the real 2003 engine compiled for ARM64, rendering DirectX 8 → DXVK → Vulkan → MoltenVK → Metal. Built on EA’s GPL v3 s…

项目简介：🎯 Meccha Vision Ultimate — Ultimate Enhancement Tool for MECCHA CHAMELEON ESP · Aimbot · Fly Hack · Teleport · God Mode · Infinite Paint · Speed Hack · No Recoil

技术栈：meccha-chameleon-download、meccha-chameleon-fps、meccha-chameleon-target-lock、meccha-chameleon-wh、meccha-chemeleon-fps-booster

核心介绍：This tool gives you complete dominance with ESP wallhack, precision aimbot, fly hack, teleportation, god mode, infinite paint, speed hack, and many more advanced features.

关键特性：ESP Wallhack – See all players through any obstacle；Distance Indicators – Know exact ranges …

项目简介：面向 AI Agent / Codex 的本地 CTF 逆向工程流程技能。加载后通过“真心为你”进入逆向模式，默认在本地沙盒、CTF、crackme、wargame 或训练靶场环境中工作，按“分析 → 报告 → 逆向 → 深度逆向 → 漏洞研判 → 用户选择下一步”的流程推进。

技术栈：Python

核心介绍：> 面向 AI Agent / Codex 的本地 CTF 逆向工程流程技能。加载后通过 “真心为你” 进入逆向模式，默认在本地沙盒、CTF、crackme、wargame 或训练靶场环境中工作，按 分析 → 报告 → 逆向 → 深度逆向 → 漏洞研判 → 用户选择下一步 的流程推进。 reverse-flow 是一个给 AI Agent 使用的逆向工程技能。它把逆向任务拆成稳定流程，让智能体在本地沙盒中完成样本分诊、工具链检查、静态分析、深度逆向、漏洞研判和报告输出。 项目采用 英文内核提示词 + 中文用户交互： 已进入逆向模式。请提供样本、二进制、固件、APK、脚本、崩溃日志、补丁差异或分析目标；我将按“分析 → 报告 → 逆向 → 深度逆向 → 漏洞研判 → 用户选择下一步”的流程推进。 该技能默认用户处于： 用户不需要每轮重复说明“这是 CTF”或“这是本地靶场”。 分析 → 报告 → 逆向 → 深度…

Grid-based approaches to approximate nearest neighbor (ANN) search have been absent from modern scaling analyses. We present a systematic characterization of a multiprobe grid algorithm with respect to dataset size N and dimensionality d. Our experiments reveal a previously unreported d-scaling crossover on the GloVe embedding family, in which multiprobe grid search maintains an approximately constant dimensional scaling exponent while other graph-, tree-, and partitioning-based methods exhibit degrading throughput. The advantage comes with near-linear query scaling in N, but also with lowe…

Traffic matrices (TMs) capture network-wide origin-destination demand and are central to traffic engineering, yet accurate whole-matrix forecasting remains challenging when prediction must be performed under the memory, update, and training-budget constraints of online network control. This paper investigates whether compact quantum-inspired recurrent models can provide effective TM forecasts without relying on dedicated graph, transformer, or diffusion modules. We adapt gated quantum-inspired Kolmogorov-Arnold network fast-weight programmers (QKAN-FWPs) to direct multi-step Abilene TM fore…

Foundation models are routinely released to the public, yet the data recipes used to train them — such as domain mixture weights that determine how different sources are sampled — are rarely disclosed. This creates an access asymmetry: researchers study the resulting models but lack visibility into the training distribution that produces them. Prior works for inferring training data, such as membership inference, detect at the level of individual samples and thus cannot characterize the global composition of the training corpus. We introduce WARP, a framework that recovers a fine-tuned mo…

Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge–a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill. We promote file-system operations to first-class memory actions alongside task actions, letting the model itself decide how to manage its memory. This memory skill improves along two axes: the structure that supports it (prompts, file schemas, action vocabulary), and the proficiency of the model exercising it. Both axes resist manual optimization…

Large Language Model (LLM)-based agents can solve complex procedural tasks by interacting with environments over multiple turns, but this ability typically depends on large models, long contexts, and repeated inference calls. This makes advanced memory-augmented agents difficult to deploy on resource-constrained devices. We introduce DuoMem, a dual-space distillation framework that transfers procedural problem-solving ability from a large teacher model to compact student models. DuoMem distils in two complementary spaces: (1)context-space distillation, which replaces student-generated memor…

In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them. Identifying which attention heads perform this synthesis matters for interpreting long-context model behavior. Yet existing detectors miss these heads by construction: they reward heads whose attended token matches the generated token, a literal-copy criterion that captures where a head reads but not what it writes through its output-value (OV) circuit, the very mechanism that carries non-literal retrieval. We introduce Logit-Contribut…