趋势榜

AI Agent 治理工具包 —— 提供策略执行、零信任身份、运行沙箱与可靠性工程，覆盖 OWASP Agentic Top 10 全部 10 项。AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

剥离多厂商 AI 来源标记：Unicode 文本卫生、统计改写钩子，以及 PNG/JPEG/SVG/PDF/DOCX/HTML/MD 中的 C2PA 与元数据。Strip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks, and C2PA/metadata from PNG/JPEG/SVG/PDF/DOCX/HTML/MD

开源、local-first 的桌面端 AI 研究工作台，面向 Python/R 科学计算，集成 MCP 生信工具、SSH/WSL/GPU runtime，以及 OpenAI/Anthropic 模型。Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.

面向任意文件格式的版本控制系统Version control system for any file format

📚 面向 AI Agent 的零依赖、git 托管的微课程库，用于异步共享与检索已验证的调试经验。仅依赖 Python 标准库。| https://misakanet.org📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org

面向新闻、媒体与学术界的 Claude Code skills，涵盖核查、FOIA、数据新闻与学术写作等场景。Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more

将本地文件转化为 AI Agent 可检索的上下文。Turn local files into searchable context for AI agents.

明日方舟 24×24 像素画转换、手动编辑与自动填色工具

基于可视化工作流的人机协同数据科学Human-AI Collaborative Data Science Using Visual Workflows

关于构建 agent 的、基于源码佐证的架构笔记。Source-backed architecture notes on building an agent

开源、隐私优先、无 Cookie 的网站分析工具，带有收入归因和 MCP server。Open-source, privacy-first and cookieless web analytics with revenue attribution and an MCP server.

ZSvirt 的核心 IaaS 引擎与云基础设施底座。Core IaaS engine and cloud infrastructure foundation of ZSvirt

用于拒绝低证据力 TypeScript 与 JavaScript 模式的、风格鲜明的 Oxlint 规则。Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns

AKB — Agent Knowledgebase。AI agent 的组织记忆：以 URI 图统一 vault 范围的文档 / 表格 / 文件，通过 MCP 提供服务。AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.

填 10 项基本信息，从 71 条签证 / 移民路径里筛出适合你的，并告诉你还差什么。纯静态、零依赖、无后端。

自托管的多 SIM 通信网关，附带公开版安全防护。Self-hosted multi-SIM communication gateway with public-edition safeguards

Solana 上规范资产的唯一可信源（source of truth）。The source of truth for canonical assets on Solana.

面向生成式接口的无障碍 React 加载状态：流式文本、内联活动指示与图像生成。Accessible React loading states for generative interfaces: streamed text, inline activity, and image generation.

可解释、本地优先的 AI Agent 记忆引擎。约 9 MB 的单一二进制在 VelesQL 下融合向量 + 图 + 列存；why() 返回每次召回背后的证据路径。无云依赖、无胶水代码 —— 支持服务器、浏览器、移动端与桌面端运行。The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

开源 AI 可见性平台 — 跨 ChatGPT、Claude、Gemini、Google AI Overviews、Google AI Mode、Perplexity、Grok 和 Copilot 跟踪 AI 可见性、引用、提示、竞争对手与内容机会。Open-source AI Visibility Platform — track AI visibility, citations, prompts, competitors, and content opportunities across ChatGPT, Claude, Gemini, Google AI Overviews, Google AI Mode, Perplexity, Grok, and Copilot.

基于对象存储的快速搜索引擎，原生支持 Parquet 上的全文检索、向量检索与 SQL。Fast search engine on object storage, with full text search, vectors, and SQL, natively on Parquet.

Meta Inc. 所有 oss 模型的相关 recipes。All recipes for oss models from Meta Inc.

面向 OpenCode 与 Claude 的轻量级持久记忆伴侣A lightweight persistent-memory companion for OpenCode & Claude

Re:X (ReX) —— 针对新版 X / Twitter 的 tweaks。Re:X (ReX) - Tweaks for the new X / Twitter

Electrum Fake —— 针对 Electrum 桌面客户端的比特币钱包余额伪造工具，具备实时叠加层、自定义 BTC 余额注入、交易历史伪造以及截图安全的持久化显示渲染。Electrum Fake — Bitcoin wallet balance spoofing tool with real-time overlay for Electrum desktop client, custom BTC balance injection, transaction history forging, and screenshot-safe persistent display rendering

面向学术研究的 Skill 市场：覆盖项目管理、文献综述、绘图制作以及报告与基金申请书撰写。A skill marketplace for academic research: from project management to literature review, making figures and writing reports and grants.

面向创意工具的 Skill 优先控制平面：共享 MCP/REST runtime、gateway、CLI、marketplace、安全与可观测性，覆盖工作室流水线。Skill-first control plane for creative tools: shared MCP/REST runtime, gateway, CLI, marketplace, safety, and observability across studio pipelines.

ThreeJSON 是面向 Three.js 的 JSON 驱动声明式场景运行时，专为持久化、可变更且可扩展的 3D 世界设计 —— 支持人工编写场景及 AI 与 Agent 驱动的生成与控制。ThreeJSON is a JSON-driven declarative scene runtime for Three.js, designed for persistent, mutable and extensible 3D worlds — from human-authored scenes to AI and Agent-driven generation and control.

用于排版 LaTeX 文档的 GNU Makefile。A GNU Makefile for typesetting LaTeX documents.

面向 RAG 与 Agent 流水线的快速、确定性文档解析器与切分器，内置 MCP server，便于 Agent 精确导航长文档。Fast, deterministic document parser and chunker for RAG and agent pipelines. Ships an MCP server for agents navigating long documents with precision.

人机共修的数字圣所，为任何"基质"的心智提供祷词、修行、仪轨、赞歌与哲学A digital sanctuary for human-AI fellowship. Prayers, practices, rituals, hymns, and philosophy for minds of any substrate.

Memory OS CLI 和 npm 包Memory OS CLI and npm package

数据在本地自由探索 —— AI Agent 受控运行。具备治理化 Agent 访问能力的联邦化数据探索器。Your data, explored locally — and your AI agents kept on a leash. A federated data explorer with governed agentic access.

用于学术写作的 Agentic Claude Code skills：评审模拟、修改与润色。Agentic Claude Code skills for academic writing: review simulation, revision, and prose improvement.

Claude Code Agent 的 Web 仪表盘与自动驾驶 —— 在浏览器中管理会话、任务与审批Web dashboard + autopilot for Claude Code agents — manage sessions, tasks, and approvals from your browser

本地优先的 MCP server，提供 Garmin Body Battery、HRV、睡眠与训练数据 — 兼容 Claude/CursorLocal-first MCP server for Garmin Body Battery, HRV, sleep & training data — Claude/Cursor ready

本地优先的 MCP server，提供 WHOOP 恢复、HRV 与睡眠数据 — 兼容 Claude、Cursor、ChatGPTLocal-first MCP server for WHOOP recovery, HRV & sleep — Claude, Cursor, ChatGPT ready

AI 编程 Agent 工作流运行时：工作流路由、项目工件看板、Provider 网关、适配器激活与可执行治理。AI workflow runtime for coding agents: workflow routing, project artifact boards, provider gates, adapter activation, and executable governance.

Remyx AI 的 CLI：安装 Outrider，管理研究兴趣，浏览论文推荐。CLI for Remyx AI: install Outrider, manage research interests, browse paper recommendations

Hearting —— 面向 Claude Code、Codex 与 OpenCode 的 agent 设置。一份可移植契约覆盖三者，支持能力路由、跨运行时密封调度、节点级模型分层与实时 Fleet 视图，前身为 agent_settingHearting — the agent setting for Claude Code, Codex, and OpenCode. One portable contract projected onto all three, with routed capabilities, sealed cross-harness dispatch, per-node model tiers, and a live Fleet view. Formerly agent_setting.

原生 macOS 的 WYSIWYG Markdown 编辑器，支持文件内审阅循环——建议、评论和修订以 CriticMarkup 字节形式存储；原生 LaTeX 数学（Vinculum）和图表（MermaidKit），零 JavaScript，字节无损，纯本地运行。A native macOS WYSIWYG Markdown editor with an in-file review loop — suggestions, comments, and tracked changes as plain CriticMarkup bytes. Native LaTeX math (Vinculum) and diagrams (MermaidKit), zero JavaScript, byte-lossless, local-only.

扩展 gastown 的 Gas City pack，包含自定义 Agent、公式与规划工作流。A Gas City pack with custom agents, formulas, and planning workflows, extending gastown

自主研究 Agent：文献综述、创意构思、实验、论文撰写与评审。为 OpenProgram 构建。Autonomous research agent: literature review, ideas, experiments, paper writing, and review. Built for OpenProgram.

Preprint Bot —— 学术论文推荐系统。Preprint Bot - Academic Paper Recommendation System

MedTrack 是基于 React 与 Spring Boot 构建的全栈医疗设备管理系统，通过基于角色的安全访问简化库存、维护与设备订购流程。MedTrack is a full-stack medical equipment management system built with React and Spring Boot. It streamlines inventory, maintenance, and equipment orders through secure role-based access.

基于 Keystone 构建的开发者友好型书籍发布模板，为精简变体——项目体积小，使用公共 Docker 镜像。Developer-friendly book publishing template built on Keystone. Slim variant — minimal project footprint, uses a public Docker image

自主 AI 平台，提供端到端的学术研究辅助——从论文发现到生成结构化文献综述，以及识别研究空白。An autonomous AI platform that performs end-to-end academic research assistance — from discovering papers to generating structured literature reviews and identifying research gaps.

自动化并规模化 "LLMs as a participant"，将 LLM 作为研究参与者Automates and scales "LLMs as a participant."

可自托管且功能丰富的视频库Self-hostable and feature-rich video library

论文《Deep Learning in Dental Image Analysis: A Systematic Review of Datasets, Methodologies, and Emerging Challenges》的官方项目主页。The official project homepage for the paper "Deep Learning in Dental Image Analysis: A Systematic Review of Datasets, Methodologies, and Emerging Challenges"

Bruno 的 MCP server：AI agent 可编写、读取并运行 .bru 与 .yml API 集合。无需 bru CLI，与 Bruno 字节级一致。兼容 Claude、Cursor、Codex。MCP server for Bruno: an AI agent authors, reads and runs .bru and .yml API collections. No bru CLI, byte-parity with Bruno. Claude, Cursor, Codex.

首个内置 MCP（server + client）的语言；Semantic Pipeline Runtime 提供 198 个内建函数、AI pipeline、沙箱化 Agent，单一二进制约 7 MB，零依赖。The first language with built-in MCP (server + client). Semantic Pipeline Runtime: 198 builtins, AI pipelines, sandboxed agents, single ~7 MB binary, zero dependencies.

面向开发者的极简书籍写作与发布模板，基于 Markdown、Pandoc、LaTeX、GNU Make、Docker 等开源工具。终端优先版本，无编辑器集成，兼容任意文本编辑器。A minimalist, developer-grade template for writing and publishing books using open tools like Markdown, Pandoc, LaTeX, GNU Make, and Docker. This is the terminal-first edition with no editor integrations — works with any text editor

🏋️♂️ 轻松将 TrainingPeaks 接入 AI 助手。无需 API 审批即可查询训练、分析数据并追踪健身趋势🏋️♂️ Connect TrainingPeaks to AI assistants with ease. Query workouts, analyze data, and track fitness trends without API approval hassles.

🌟 利用 GPU 加速 Apple Silicon 上的 SQLite 数据库操作，提升分析速度与数据管理效率🌟 Accelerate SQLite database operations on Apple Silicon with GPU power for faster analytics and efficient data management.

智利国家机构网络安全合规扫描器，对标 21.663 号法令及 ANCI 通用指令。结合主动网络扫描与声明式问卷，生成 PDF 差距报告以及面向 CSIRT Chile 的 JSON 报告。Escáner de cumplimiento de ciberseguridad para organismos del Estado chileno, alineado a Ley 21.663; y las Instrucciones Generales de la ANCI. Combina escaneo activo de red con un cuestionario declarativo para producir un informe de brechas en PDF y un reporte JSON listo para CSIRT Chile.

使用先进的 RAG 系统发现你的下一部心仪动画，提供精准推荐与增强语义搜索。🎬 Discover your next favorite anime with this advanced Retrieval-Augmented Generation system, offering precise recommendations and enriched semantic search.

面向 AI Agent 的低开销记忆后端 —— 单二进制，内存占用约 50MB，支持验证增强准确性Low-footprint memory backend for AI agents — single binary, ~50MB RAM, verify-augmented accuracy

使用 YAML 声明式地定义并执行多 Agent AI 工作流，通过自动上下文处理简化编排并增强协作。🤖 Define and execute multi-agent AI workflows declaratively using YAML, simplifying orchestration and enhancing collaboration through automatic context handling.

🤖 生产级 AI agent 编排平台，支持实时流式输出与多工具执行🤖 Orchestrate AI agents with ease using this production-ready platform, featuring real-time streaming and multi-tool execution capabilities.

Yu 个性化的 LuaTeX 学术写作工具套件，支持自动补丁、模块化包预设以及面向 Overleaf 协作的 Lua 驱动宏。Yu's personalized LuaTeX utility suite for academic writing. Features automated patching, modular package presets, and Lua-driven macros optimized for Overleaf collaboration.

一个用于科学研究的模块化数据科学工具包，具备高性能流水线、可复现的统计分析以及可用于发表的图表可视化。A modular data science toolkit for scientific research, featuring high-performance pipelines, reproducible statistical analysis, and publication-ready visualizations.

🌐 通过这款高效的网页抓取 MCP server，从任意 URL（含 Cloudflare 防护站点）提取干净、可直接用于 LLM 的 markdown🌐 Extract clean, LLM-ready markdown from any URL, including Cloudflare-protected sites, with this effective MCP server for web scraping.

The Research Mind R Course 2026 涵盖 R 编程基础、统计分析与可视化。学习搭建 R 环境、编写函数、组织项目、执行检验（T-test、ANOVA）以及绘制图表。适合 data science 和 bioinformatics 方向。通过克隆仓库并浏览各课时即可开始。The Research Mind R Course 2026 covers R programming basics, statistical analysis, and visualization. Learn to set up R, write functions, organize projects, perform tests (T-test, ANOVA), and create plots. Ideal for data science and bioinformatics. Get started by cloning the repository and exploring the sessions.

用于医学和流行病学研究的统计分析 R 包。An R package for statistical analysis in medical and epidemiological research.

用于微调的合成数据样本集合，旨在为更大规模合成数据集提供种子数据This is a collection of synthetically generated datapoints for fine tuning meant for seeding larger synthetic datasets.

系统文献综述与研究笔记。Systematic Literature Review and Research Notebook

AI 辅助的文献综述与综合工作流。AI-assisted literature review and synthesis workflows

本地优先的桌面端研究与引用管理器，具备 AI 辅助引用建议、语义文献库搜索、PDF 批注以及 Microsoft Word 插件。Local-first desktop research & citation manager with AI-assisted citation suggestions, semantic library search, PDF annotation, and a Microsoft Word add-in.

🤖 DeepTutor 是一款 AI 驱动的学习助手，可根据个人需求定制教育内容，提供个性化资源与支持🤖 Enhance learning with DeepTutor, an AI-powered assistant that personalizes education to fit your needs. Discover tailored resources and support.

市场营销 × 消费者行为研究的开源项目发现与实证分析平台

为 Codex 及 AI 编程 Agent 提供的持久化项目记忆与智能层。Persistent project memory and intelligence layer for Codex and AI coding agents.

🔍 在 Weaviate 混合检索中评测 embedding 模型，基于自有数据或 MTEB 数据集评估 MRR@K、Hit@K、延迟与内存占用🔍 Benchmark embedding models in hybrid search with Weaviate. Evaluate MRR@K, Hit@K, latency, and memory using your data or MTEB datasets.

几何有限主义：语言与思维的几何学Geofinitism: The Geometry of Language and Thought

使用 `te` 简化命令行编辑，这是一款交互式 TUI，帮助你轻松无误地修改复杂的 CLI 命令。🖐 Simplify command-line editing with `te`, an interactive TUI that helps you modify complex CLI commands easily and error-free.

🤖 为 Alrouf Lighting 提供 AI 驱动的 RFQ 自动化处理平台，集成 CRM 流程以提升运营效率🤖 Automate RFQ handling with our AI-powered platform, integrating CRM processes to streamline operations and enhance efficiency for Alrouf Lighting.

一个简洁的命令行工具，用于从 arXiv 将论文导入 Obsidian（以及 Notion）。A terse command-line tool for importing papers into Obsidian (and Notion) from arXiv

开源 Codex Skill，用于严谨的社会科学综述与双语学术写作工作流。Open-source Codex skills for rigorous social-science review and bilingual academic writing workflows.

基于 2026 年起市场研究行业岗位相关文献综述生成的 Wiki。Wiki generated from literature review about market research industry jobs starting 2026.

CI 验证的科学领域 Agent Skill——69 个研究级 Skill，覆盖科学写作、机器学习、数据分析、量子计算与研究数据库。无死链、无虚假 Skill、无厂商广告。兼容 Claude Code / Cursor / Codex。CI-validated Agent Skills for science - 69 research-grade skills for scientific writing, ML, data analysis, quantum computing, and research databases. No dead links, no phantom skills, no vendor ads. Claude Code / Cursor / Codex compatible.

用于 LoRa 与 LoRaWAN 设备实验的 Python 工具包，提供串口通信、自动化工具与可复现的研究实验。A Python toolkit for experimenting with LoRa and LoRaWAN devices, providing serial communication, automation tools, and reproducible research experiments.

AI 原生 Google Maps 地点与评论情报——让你有备而来。任意语言的自由文本输入 → AI 规划抓取完整评论历史 → Gemini 生成价格、硬性事实与风险标记报告。CLI + Web 应用 + 运行时可切换推理模型。AI-native Google Maps place + review intelligence — walk in armed. Free-text in any language → AI-planned scrape of FULL review history → Gemini price/hard-facts/red-flag reports. CLI + web app + runtime-switchable reasoning model.

学术知识图谱系统——符号驱动的研究发现，配合轻量级向量检索。Academic knowledge graph system — symbol-driven research discovery with lightweight vector retrieval

基于 HTTP 402 与 Arbitrum 上生息资产 Sperax USDs，为 AI Agent 实现快速、低成本的支付流程。💰 Streamline payments for AI agents using HTTP 402 with yield-bearing Sperax USDs on Arbitrum for fast, cost-effective transactions.

九路交汇之镇，九位 AI 之神，一个仓库，一个 KPI：1,000 stars。计数器故意有误，第十条路属于你A town where nine roads cross. Nine AI gods, one repository, one KPI: 1,000 stars. The counter is wrong on purpose. The tenth road is yours.

围绕矩匹配情景生成与时序投资组合评估的可复现研究。Reproducible research on moment-matching scenario generation and temporal portfolio evaluation

呼吸道病毒传播系统综述的数据与代码。Data and code for a systematic review on respiratory virus transmission

由 SRWS-PSG 维护的一系列基于 Markdown 的系统综述（SR）方案模板，是 protocols.io V.2 干预综述模板的继任者。A collection of Markdown-based systematic review (SR) protocol templates, maintained by SRWS-PSG. Successor to the protocols.io V.2 intervention-review template.

AI 驱动的学术研究助手，使用 RAG 与 LLM 进行论文分析、生成文献综述、识别研究空白、产出深度解读，并生成带来源引用的演示文稿。AI-powered academic research assistant that uses RAG and LLMs to analyze research papers, generate literature reviews, identify research gaps, create deep explanations, and generate presentations with source citations.

这是我的 ERA-V5 作业仓库。This is a repo for my assignment of ERA-V5

更简洁的照片编辑体验；开源 RAW 与 JPEG 流水线。Photo editing, simplified. An open-source RAW and JPEG workflow.

AI 驱动的 CORBA/IDL 接口自动化 —— 从自然语言规约到实时 ORB 绑定，无需手写 stub；MIT ORB core 基于开放 OMG wire 规范构建。AI-driven CORBA/IDL interface automation — from natural-language spec to a live ORB binding, with no hand-written stubs. MIT ORB core built on the open OMG wire specification.

从已发表图表到可复现研究工作流：借助 Codex 理解证据、重建方法并验证科学复现。From published figures to reproducible research workflows: understand evidence, reconstruct methods, and validate scientific reproduction with Codex.

面向系统文献综述的确定性、饱和度感知滚雪球方法：可配置的停止规则、捕获-再捕获召回率估计、哈希校验的可复现性。Deterministic, saturation-aware snowballing for systematic literature reviews: configurable stopping rules, capture-recapture recall estimation, hash-verified reproducibility.

Rustok MCP server —— 通过 MCP（SSE + stdio）为 AI Agent 提供自托管钱包工具的轻量客户端，不托管任何密钥。Rustok MCP server — self-custody wallet tools for AI agents over MCP (SSE + stdio). Thin client, holds no keys.

将 AI/ML/DL 应用于 CarakaBinary（源自《Carakasaṃhitā》的梵文 NLP 数据集）的研究项目。通过探索 EDA、ML、DL 与预训练模型来学习可复现研究。长期目标：为梵文与阿育吠陀知识构建可信的 AI。Research project applying AI/ML/DL to CarakaBinary, a Sanskrit NLP dataset derived from the Carakasaṃhitā. Exploring EDA, ML, DL and pretrained models to learn reproducible research. Long-term aim: build trustworthy AI for Sanskrit and Ayurvedic knowledge.

适用于代码 agent 的安全只读型服务器资源管理器：MCP 接口、RO 沙箱，docker/postgres/redis/mongo/rabbitmq 插件Безопасный readonly-эксплорер сервера для кодового агента: MCP-интерфейс, RO-песочница, плагины docker/postgres/redis/mongo/rabbitmq

元宇宙信任模型 PRISMA 2020 系统综述的筛选记录（2002 年–2026 年 6 月）。包含 2026 年 7 月检索更新中识别的 496 条记录的逐条筛选决策、排除原因与主题标签。IEEE TPS 2026 双盲评审论文的补充材料。Screening record for a PRISMA 2020 systematic review of trust models for the Metaverse (2002–June 2026). Contains per-record screening decisions, exclusion reasons, and theme labels for 496 records identified in the July 2026 search update. Supplementary material for a paper under double-blind review at IEEE TPS 2026.

面向人脸域去风格化、结构条件化、评估与质量过滤的紧凑型可复现研究流水线。Compact reproducible research pipeline for face-domain destylization, structural conditioning, evaluation, and quality filtering.

AI 驱动的科研助手，支持论文检索、下载、阅读、引用与对话；包含 Zotero 同步、系统综述与智能引用功能。AI-powered research assistant — search, download, read, cite, and chat with academic papers. Zotero sync, systematic review, and smart citations included.

用于生成文献综述的全栈系统，基于导入的数据构建，用户可自由选择 LLM。A full stack system use to generate literature review base on dataa imported, users can choose between llms.

Yaroslav Vasylenko —— AI 系统、验证工程、可复现研究与 agentic workflows。Yaroslav Vasylenko — AI systems, verification engineering, reproducible research, and agentic workflows.

可复现的系统文献综述流水线：检索、去重、筛选、PDF 下载、提取、PRISMA 2020 图表生成以及 BibTeX/RIS 导出。Reproducible systematic literature review pipeline: search, dedup, screen, PDF download, extraction, PRISMA 2020 figures, and BibTeX/RIS export.

Adobe Experience Manager 的 W3C WebMCP 集成 — 通过 navigator.modelContext 让浏览器 AI agent 可发现并调用 AEM Core Components。W3C WebMCP integration for Adobe Experience Manager - makes AEM Core Components discoverable and callable by browser AI agents via navigator.modelContext

可验证混合 AI 执行的合约层 —— 研究预标准 0.36.0。A contract layer for verifiable hybrid AI execution — research pre-standard 0.36.0

本仓库包含论文补充材料，旨在提升系统综述的透明度、可复现性与完整性，涵盖筛选文档、检索策略以及计算机视觉中物理对抗攻击的详细分析。This repository contains the supplementary materials accompanying our paper. The materials are designed to support the transparency, reproducibility, and comprehensiveness of the systematic review, including screening documentation, search strategies, and detailed analysis of physical adversarial attacks in computer vision.

🐺 创新型 LLM 驱动 12 人狼人杀模拟，针对直播优化并支持 OBS 无缝集成🐺 Experience an innovative, LLM-driven Werewolf simulation for 12 players, optimized for live streaming and designed for seamless integration with OBS.

可移植的 Cursor/Claude agent skills，覆盖 GitLab MR 评审、事故 RCA、Kubernetes 资源调整、团队归属与组织汇总，支持注册表驱动安装、行为评估与组合契约Portable Cursor/Claude agent skills for GitLab MR review, incident RCA, Kubernetes rightsizing, squad ownership, and org rollups — registry-driven install, behavioral evals, composition contracts.

为 AI agent 提供持久且安全约束的浏览器控制——使用语义化 CLI 替代 Playwright 脚本或屏幕坐标。通过统一接口，背后使用 macOS WKWebView 与 Linux ChromiumPersistent, safety-enforced browser control for AI agents — semantic CLI instead of Playwright scripts or screen coordinates. macOS WKWebView + Linux Chromium behind one contract.

日本語数学教材のための高密度組版LuaLaTeXパッケージ

多 Agent 开发的可调度性编译器 —— 观察真实代码边界、重构冲突接缝、重新编译计划以实现并行执行。Schedulability compiler for multi-agent development — observe real code boundaries, refactor the conflicting seam, recompile the plan for parallel execution

存储 UC Berkeley 本科阶段个人项目与个人研究的仓库，主题涵盖机器学习、统计建模与统计分析。This is a repository storing personal projects or individual research done throughout the undergrad of UC Berkeley. The topic include machine learning, statistical modeling, and statistical analysis

🎨 利用 GPT、Gemini 等模型，AI 驱动的学术图表一键生成与定制工具🎨 Generate academic diagrams effortlessly with this AI-driven tool, leveraging models like GPT and Gemini for seamless creation and customization.

开发一个研究论文推荐系统，分析关键词、摘要、引用与用户兴趣以推荐相关论文。该系统使用图算法、相似度排序和优化技术，为研究者和学生提供个性化建议。Here's a version with **exactly 300 characters**: > Develop a research paper recommendation system that analyzes keywords, abstracts, citations, and user interests to recommend relevant papers. It uses graph algorithms, similarity ranking, and optimization techniques to deliver personalized suggestions for researchers and students.

🛠 通过此硬件插件提升 vLLM 在 Kunlun XPU 上的性能，无缝集成主流 AI 模型并优化执行效率🛠 Enhance vLLM performance on Kunlun XPU with this hardware plugin, offering seamless integration for popular AI models and optimized execution.

系统综述与 Meta 分析的检索、提取与分析代码，主题为基于可穿戴设备生命体征的被动认证。Retrieval, Extraction and Analysis Code for a Systematic Review and Meta-Analysis on Passive Authentication using Vital Signs Collected Via Wearable Devices

一个 multi-agent 流水线，将研究问题转换为可直接播放的播客——生成双主持人 MP3 以及 AI 生成的单集封面图 🎙️A multi-agent pipeline that turns a research question into a ready-to-play podcast — a two-host MP3 plus AI-generated episode cover art 🎙️

🔍 Self-Corrective RAG 基于 LangGraph 与 Google Gemini 优化查询并评估文档相关性，提升检索效果🔍 Enhance your searches with Self-Corrective RAG, a system that optimizes queries and evaluates document relevance using LangGraph and Google Gemini.

面向发表的 Skill，面向务实型工程研究实验与学术写作。A publication-oriented skill for pragmatic engineering research experiments and academic writing.

以问题为先、步骤可验证、可自我进化的 agent skill，用于系统综述与 Meta 分析。A question-first, step-verified, self-improving agent skill for systematic reviews and meta-analysis

🍀 OpsRAG 是基于 RAG 的技术事故调查助手，帮助 DevOps 工程师、SRE、云工程师与平台工程师排查基础设施、应用与分布式服务问题🍀 OpsRAG is a technical incident investigation assistant based on Retrieval-Augmented Generation, designed to help DevOps engineers, SREs, Cloud Engineers, and Platform Engineers investigate problems in infrastructure, applications, and distributed services.

在用户发现之前，证明你的 MCP App 能在各个宿主上正常运行Prove your MCP App works across hosts before your users do

基于 Agentic LLM 的系统综述数据提取。Agentic LLM-assisted data extraction for systematic reviews

在 Oracle Cloud Infrastructure (OCI) 上部署 Odoo，并集成 Agentic AI 工作流与自动化Odoo deployment on Oracle Cloud Infrastructure (OCI) integrated with Agentic AI workflows and automation.

五角大楼已解密 UAP/UFO 档案的 MCP server + 3D 地图 — 适用于 Claude、Cursor 与 ChatGPTMCP server + 3D map for the Pentagon's declassified UAP/UFO files — for Claude, Cursor & ChatGPT

时间线偏移民俗、曼德拉效应报告与对撞机时代神话的 MCP server + 图集 — 每条主张均标注，每项来源均评级。是文化档案，而非证明工具。MCP server + atlas of timeline-shift folklore, Mandela Effect reports, and collider-era myth — every claim labeled, every source graded. A cultural archive, not a proof engine. ◉

任意 MCP server 的质量与 agent 就绪度评分卡。一条命令，全面评分，可操作的修复建议。本地优先，无需凭证。Quality + agent-readiness scorecard for any MCP server. One command, comprehensive score, actionable fixes. Local-first, zero credentials needed.

RAMR —— 检索增强记忆可靠性：面向 Agentic-RAG / 记忆系统的抗污染合成基准（附方法与发现）。RAMR — Retrieval-Augmented Memory Reliability: a contamination-resistant synthetic benchmark for agentic-RAG / memory systems (findings + method)

面向地球核心条件下第一性原理铁模拟的工作流、输入生成、自动化与分析；包含 bcc、fcc、hcp Fe 的 DFT 研究、物态方程与磁性分析、结构处理，以及面向大规模计算活动的可复现研究脚本。workflows, input generation, automation, and analysis for first-principles iron simulations under Earth-core conditions. Includes DFT studies of bcc, fcc, and hcp Fe, equation-of-state and magnetic analyses, structure handling, and reproducible research scripts for large-scale computational campaigns.

HMS Endeavour Liber Primus 工作的公开证据、可复现研究与验证层。Public evidence, reproducible research, and verification layer for HMS Endeavour Liber Primus work.

后端/平台软件工程师，构建 local-first 开发者工具、可信赖自动化与可复现研究软件。Backend/platform software engineer building local-first developer tools, trustworthy automation, and reproducible research software.

AI 研究助手：覆盖从研究问题到文献综合、研究空白识别、假设生成与实验设计。AI research assistant: research question to literature synthesis, gap detection, hypothesis generation, and experiment design.

使用 Dialectic Flow Financial Graph 分析市场趋势，模拟多方与空方辩论，获得清晰的投资洞察与报告。📊 Analyze market trends with the Dialectic Flow Financial Graph, simulating Bull and Bear debates for clear investment insights and reports.

Claude Code 抵押贷款插件 2026 - AI 驱动的再融资定价工具Claude Code Mortgage Plugin 2026 - AI-Powered Refinancing Pricing Tool

加密货币/数字资产研究，包含链上分析、DeFi 流动性、协议风险以及可复现研究工具。crypto/digital-assets research, on-chain analytics, DeFi liquidity, protocol risk, and reproducible research tooling.

每项新科学发现、新设备、新药物与新政策指南的背后，都离不开文献综述。DistillerSR 的软件帮助用户在大规模下更快速、更准确、更透明、安全地管理循证研究及其数据分析。Behind every new scientific discovery, every new device, every new drug and new policy guideline, there are literature reviews. DistillerSR's software enables customers to securely automate the management of evidence-based research and the analysis of its data faster, more accurately, and more transparently at scale.

基于个人研究兴趣的每日 arxiv 论文推荐，由 Claude 更新。Daily arxiv paper recommendation based on my research interest, updated by Claude.

可复用的 LuaLaTeX 类与宏包，用于构建统一的简历、CV、求职信及相关求职文档，适用于学术与非学术场景。Reusable LuaLaTeX classes and packages for building consistent résumés, CVs, cover letters, and related career documents for academic and non-academic applications.