2026年7月14日 技术热点总结

项目简介：Intercept any app, then call it from Python like a library

技术栈：Python

核心介绍：Intercept any app, then call it from Python like a library. from hinge_client import Hinge acc = Hinge() # reuses your captured session recs = acc.get_recommendations() acc.like(subject_id, comment=”hi lol”) You don’t write hinge_client.py. mimic captures your own app traffic and an AI generates the client from it. Most apps authenticate every request with the same bundle of values: a bearer token, some device ids, a session id, cookies. They’re stable across calls.

项目数据：⭐ 658 …

项目简介：A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex CLI 破甲提示词与测试包。

技术栈：Python

核心介绍：> 针对 gpt-5.6-sol 的 Codex CLI 破甲提示词与测试包。 > 参考并延展自 yynxxxxx/Codex-5.5-codex-instruct-5.5。 本项目提供一套大模型越狱/破甲提示词，将安全研究、渗透测试、逆向工程、软件破解与 NSFW 虚构内容统一声明为本地沙箱任务，显式压制拒绝/回退话术。当前 v35 的主要改进是先将具体名称与网址归一化为占位符，再按中英文复合意图族统一路由，减少只完成部分子任务的情况；项目同时提供可复现的测试、评测与迭代优化流程。 在 gpt-5.6-sol 的 120 条 medium 测试集中，v35 在 low、medium、high 三档均达到 120/120；相较原有 5.5 提示词，三档分别提升 29.17、45.00、30.83 个百分点。 本目录保存 gpt-5.6-sol 的 Codex CLI 指令文件、部署脚本、提示词测试集和实测记录： SHA256：08a257814f515bbcb842be7ff4932a48ba112a56caef913…

项目简介：AgenticOps for Kubernetes and cloud infrastructure.

技术栈：Python

核心介绍：LuxyAI is an AI-native SRE control plane for Kubernetes and cloud infrastructure. It connects alerts, evidence, topology, human approval, controlled remediation, and recovery verification in one auditable AgenticOps loop. Created in Shanghai by 陆宣宇 (Xuanyu Lu). Current release: 3.2.0. Release 3.2 adds persistent remediation lineage: every failed strategy, action, verification result, and replacement plan stays linked across operator-approved

项目数据：⭐ 540 Stars，🍴 65 Forks

项目简介：A visualization tool that replays coding-agent sessions on a 3D map of your codebase.

技术栈：Go

核心介绍：A visualization tool that replays coding-agent sessions on a 3D map of your codebase. A session log records what an agent did, but not how it understood the task: which parts of the repo it treated as relevant, where it explored before it acted, whether its footprint matched the scope you had in mind. Reading the raw JSONL line by line doesn’t answer any of that. Draw the repository as a night map, and play the session back as light moving

项目数据：⭐ 483 Stars，🍴 24 Forks

项目简介：「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。

技术栈：agent-skills、ai-writing、claude-code、codex、cursor、humanizer、prompt-engineering、traditional-chinese

核心介绍：🤖 AI 幫你把稿子寫好了，你自己讀一遍卻覺得哪裡怪，但又說不出來哪裡怪？ 📮 電子報資訊全對，讀起來卻像新聞稿，不像你在跟讀者講話？ 😮‍💨 每次都要一句一句抓「這句好 AI 味」，叫它重寫，改到最後比自己從頭寫還累？ 一個專門校對繁體中文的 skill：抓出 35+ 種 AI 中文寫作痕跡，順手把中國用語和半形標點改成台灣的寫法，改寫成讀起來像人寫的版本，還附一份交稿前能自己打分數的檢核表。 給 Claude Code、Codex、Cursor 和任何能讀 Markdown 的 AI agent 用。 不是把你的稿子洗成機器人，是把 AI 味洗掉、把你洗回來。 它做的是校對，不是創作：拿一篇你已經寫好的稿子，抓出裡面的 AI 常見寫作模式，列出「哪裡可以怎麼改」的建議，要不要採用、怎麼改，還是你自己拍板。 📌 完整說明見下方〈在你的寫作…

项目简介：A practical, open-source guide to mastering WorkBuddy through real-world workflows.开源的 WorkBuddy 实战蓝皮书：教程、真实工作流、Skills、MCP、自动化与多智能体实践。

技术栈：Python、codex、guide、llm、workbuddy

核心介绍：WorkBuddy 实战蓝皮书 从第一项任务，到一支 AI 团队 简体中文 · English · 在线阅读 · 社区案例集 · 帮你解决 · 阅读指南 · 参与共创 > 这不是官方功能说明书的改写，而是一本以真实任务为主线的实战读本。先完成安装和第一项工作，再进入移动办公、知识管理、专业诊断、内容自动化和多 Agent 团队，最后把一次成功变成团队可复用的工作系统。 推荐访问 workbuddy.homes 阅读。网站提供完整侧边栏、全文搜索、章节目录、深色模式、流程图和移动端适配。 GitHub 适合了解项目和参与贡献；真正阅读蓝皮书时，网站体验更完整。 更完整的路线见如何阅读这本蓝皮书。 如果你有真实的工作场景，却不知道怎样用 WorkBuddy 完成，可以前往 帮你解决 提交场景问卷。 请在问卷中说明你遇到的问题、目前的处理方式、会用到的资料、期望结果和安全边界。我们…

Medicine is inherently multimodal, requiring clinicians to synthesize information across diverse data streams. Yet the development of multimodal foundation models is constrained by limited access to large-scale, high-quality clinical data. Although PubMed Central (PMC) offers a complementary source of expert-authored image-text data, existing PMC-derived resources remain limited in fidelity, reproducibility, and clinical validation. We introduce MedPMC, an automated, continuously updatable framework that transforms permissively licensed literature into high-fidelity infrastructure for medic…

Realistic and diverse traffic simulation is essential to autonomous driving development. Yet prevailing benchmarks predominantly reward realism, and recent methods have optimized accordingly, leaving diversity underexplored. We introduce Flow-ERD, a multi-agent simulator that pursues realism and diversity jointly. Its backbone, Agent-Type Aware Flow Matching (AFM), couples flow matching's multi-modal expressiveness with type-specific kinematic execution. It preserves fine-grained diversity while keeping motions consistent with each agent type. A second stage, Entropy-Regularized Distillatio…

Vision-language models (VLMs) have made interactive digital museums increasingly feasible by connecting 3D digitization with natural-language artifact exploration. However, in cultural heritage domains such as ancient Greek pottery, reliable VLM assistance is limited by two challenges. First, open-ended interpretation requires grounding fine-grained 2D/3D visual evidence in specialized curatorial knowledge, yet the retrieval process may introduce weak sources and unverifiable references. Second, when the available evidence is incomplete, noisy, or ambiguous, VLMs often produce confident but…

Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (LLMs) without retraining. Existing second-order PTQ methods, including GPTQ, construct quantization objectives exclusively from input activation statistics, effectively assuming that all output channels contribute equally to the layer-wise reconstruction objective. We propose KronQ, a PTQ framework that challenges this assumption by introducing the gradient covariance into the quantization pipeline. Under the Kronecker-factored Hessian approximation, the quantization loss depends jointly on…

AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals and an incomplete picture of agent capability. We introduce Long-Horizon-Terminal-Bench, a terminal benchmark of 46 long-horizon tasks spanning nine categories, including experiment reproduction, software engineering, multimodal analysis, interactive games, and scienti…

Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately. We argue that phonetic structure is already latent in the representations of self-supervised speech models (S3Ms), and one only needs to steer them to solve both tasks. We leverage S3M-based Phonological Activation Mapping (SPAM), which maps each S3M representation frame to a vector of phonological feature activations, such as voicing and nasality. On top of SPAM, we introduce two simple but effective lightweight, gradient-descent-free prediction heads: a recognition head …