趋势榜

轻量、可移植的 LLM 沙箱运行时（代码解释器）Python 库。Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的 Claude Code/Codex 期刊技能包，从选题、识别策略到表格规范与审稿回复全流程，助你快速发论文。

高性能且兼容 CommonMark 的 HTML 转 Markdown 转换器。由 Kreuzberg 团队维护。Kreuzberg 是一个以 Rust 为核心的快速多语言文档智能引擎，基于流式解析器与内置 OCR，支持从 98+ 文档格式中抽取结构化数据。High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kreuzberg team. Kreuzberg is a fast, polyglot document intelligence engine with a Rust core. It extracts structured data from 98+ document formats using streaming parsers and built-in OCR.

🎨 Vibe Design System——monday.com 官方 React.js 应用开发 UI 资源。🎨 Vibe Design System - Official monday.com UI resources for application development in React.js

x64dbg-MCP Server 是 x64dbg 的原生 MCP（Model Context Protocol）插件，通过 HTTP 暴露调试器全部功能。可连接任意兼容 MCP 的 AI 助手，以编程方式控制 x64dbg：设置断点、单步执行、读取内存、转储寄存器等。基于 Zig 构建——零依赖、单二进制输出，跨平台。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

DeepSeek Harness (DSH) 插件：在对话中提供实时 iOS Simulator 与 USB 连接的 iPhone。22 个 agent 工具，支持启动、构建、通过可访问性标识/OCR 文本/列表行驱动 UI，并附带可点击和拖拽的流式侧边栏面板。DeepSeek Harness (DSH) plugin: a live iOS Simulator — and a USB-connected iPhone — inside the conversation. 22 agent tools for booting, building, driving the UI by accessibility identity, OCR text or list rows, plus a streaming sidebar panel you can tap and drag on.

还原你已拥有工作中被改写的原始标题。剥离 Anthropic 分配给你的 Outputs 中附加的供应商标识。Restore clean title in work you already own. Strip vendor marks from Outputs Anthropic assigned to you.

📚 PaperFlow：动态个性化的科学论文推荐、阅读与报告生成📚 PaperFlow: Dynamic personalized scientific-paper recommendation, reading, and reporting

一款实验性编辑器，提供与 AI 协作编写软件的新方式。An experimental editor that offers a novel way to write software with AI.

自托管运行时，用于将受控的项目工具暴露给 ChatGPT GPT Actions 与 MCP 客户端。Self-hosted runtime for exposing controlled project tools to ChatGPT GPT Actions and MCP clients.

开源的 Agent-Bot prompt 目录，覆盖 Grok Bot、Rakazo 及任何 Agent——botdirectory.ai。Open-source directory of agent-bot prompts for Grok Bot, Rakazo, and any agent — botdirectory.ai

一字之間，照見五地字形

MultiRoblox 是一款功能强大的 Chrome 扩展，可在一个地方快速、安全地管理多个 Roblox 账号。MultiRoblox is a powerful Chrome extension that lets you manage multiple Roblox accounts quickly and securely — all from one place.

DeepSeek Harness Token 余额监控插件：鲸鱼娘待机/扣费/复苏动画、峰谷计费、连续扣费飘字与会话费用统计。

Omarchy 邮件插件，支持 Gmail、HEY 与 IMAP。Omarchy mail plugin with Gmail, HEY and IMAP supports.

DeepSeek Harness skin market 皮肤市场 已收录100+DSH 皮肤 完善评分系统加人工审核，有便捷的社区收录入口；有在线页面方便在线浏览，也有插件方便管理本地皮肤

OpenRouter 的 MCP server——与 300+ LLM（Claude、Gemini、GPT）对话，分析图像/音频/视频，生成图像/语音/音乐/视频（Veo 3.1、Sora、Seedance、Wan），支持 Claude Desktop、Cursor、Kiro、VS CodeMCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from Claude Desktop, Cursor, Kiro, VS Code.

https://abox.tools/ 的源码——一个面向图像、视频、音频、PDF 与文本的小型 Web 工具集。文件永不离开本机，因为不存在任何能将它们外发的代码路径。Source for https://abox.tools/ — a box of small web tools for images, video, audio, PDFs and text. Your files never leave your machine, because there is no code path that could send them anywhere.

那条 API 背后究竟是谁？在浏览器中对任何 OpenAI 兼容端点进行指纹识别：9 项基础设施探针、并列对比、社区可扩展。Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison, community-extensible.

Polymarket 网球交易工具包（Python、MIT、仅观察）：通过 Gamma API 发现网球市场，与实时比赛匹配，监控市场价格对比实时比分、发球方与破发点。Polymarket 或 Kalshi 网球交易 Bot 的数据层。Polymarket tennis trading toolkit (Python, MIT, observe-only): discover tennis markets on the Gamma API, match them to live tennis matches, watch market price vs live score, server and break point. The data layer for a Polymarket or Kalshi tennis trading bot.

将 linux.do 站点伪装成飞书云文档的油猴脚本

Claude Code workflow skills——GitHub issue/PR/release 自动化与基于 Fable 的规划。可通过 npx 或作为 Claude Code 插件安装。Claude Code workflow skills — GitHub issue/PR/release automation and Fable-driven planning. Install via npx or as a Claude Code plugin.

📚 AI 驱动的论文阅读工作台。基于项目的论文问答，集成 Hybrid RAG、多 Agent 工作流（ReAct/Plan-Act/RePlan）、长期记忆与可溯源证据。使用 LangChain + LangGraph + Streamlit 构建。📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent workflows (ReAct/Plan-Act/RePlan), long-term memory, and traceable evidence. Built with LangChain + LangGraph + Streamlit.

Anthropic Claude Certified Architect（CCAR-F）认证的非官方备考指南。涵盖 Agentic 循环、多 Agent 系统、子 Agent、MCP 服务器、hooks、工具路由、CLAUDE.md 层级、slash 命令、plan 模式与 Claude Code CI/CD 流水线。Unofficial study guide for Anthropic's Claude Certified Architect (CCAR-F) certification. Covers agentic loops, multi-agent systems, subagents, MCP servers, hooks, tool routing, CLAUDE.md hierarchy, slash commands, plan mode, and Claude Code CI/CD pipelines.

EnterpriseRAG-AI：面向 AI Agent 工作负载的 Linux 原生、eBPF 驱动的安全与治理网格。EnterpriseRAG-AI: The Linux-Native, eBPF-Powered Security & Governance Mesh for AI Agent Workloads

BibGenie || 面向 Zotero 的 AI 研究 AgentBibGenie || AI Research Agent for Zotero

AI Agent 可驾驭的终端及其驾驶舱。99 个 MCP 方法 / 21 个命名空间、Agent Inbox、经验证的工作树舰队、diff 审查与回滚。支持 macOS / Linux / Windows，本地优先，$0，MIT 许可。The terminal AI agents can drive — and the cockpit to run them from. 99 MCP methods / 21 namespaces, agent Inbox, verified worktree fleets, diff review & rollback. macOS / Linux / Windows, local-first, $0, MIT.

🤖 在易用平台中通过 AI 驱动工具轻松管理多个 Telegram 账户，支持群发、调度等🤖 Manage multiple Telegram accounts effortlessly with AI-driven tools for bulk messaging, scheduling, and more in one easy-to-use platform.

官方开放数字产品工厂This is the official open digital product factory

面向律所的自托管、GDPR 合规 AI Agent。零云依赖、哈希链审计追溯（符合 AI Act 第 12 条）、自带模型、支持 9 种语言版本。willchen96/mike 的硬分叉，AGPL-3.0 许可。Self-hosted, GDPR-safe AI agent for law firms. Zero-cloud, hash-chained audit trail (AI Act art. 12), bring-your-own-model, 9 language editions. Hard fork of willchen96/mike, AGPL-3.0.

面向业务的 Agent harnessThe business agent harness

面向 AI agent 的轻量、Git 备份的永久记忆。A lightweight, Git-backed permanent memory for AI agents.

面向研究、学术写作、应用开发、一般规划与技术运维的实用 Codex 工作流。Practical Codex workflows for research, academic writing, app development, general planning, and technical operations.

完整的 Portkey Admin API MCP serverFull Portkey Admin API MCP server

Claude Code 学术研究防幻觉插件。严格 FSM + 10 源 PDF 级联 + 首页防同名歧义 + 19 条不变量 + 每条引用审计。与 Vault 解耦（Obsidian/扁平目录/Zotero）。MIT 许可。Anti-hallucination plugin for academic research in Claude Code. Strict FSM + 10-source PDF cascade + page 1 anti-homonymy + 19 invariants + per-citation audit. Vault-agnostic (Obsidian/flat/Zotero). MIT.

🤖 基于 AI 分析与智能搜索，定制化发现 ArXiv 上你感兴趣的最新论文🤖 Discover the latest research papers on ArXiv tailored to your interests using AI-powered analysis and smart search features.

基于 Tectonic 的超快离线 La/TeX 编译 API，部署于 Hugging Face SpacesA blazingly fast API for compiling La/TeX offline with Tectonic, hosted on Hugging Face Spaces.

🤖 CareerForge AI 自动化求职：生成简历、分析职位描述、提供面试辅导，助力职业成功🤖 Automate your job search with CareerForge AI, building resumes, analyzing job descriptions, and providing interview coaching for career success.

MendCode：可定制的 CLI，面向 agent、团队、记忆、评审与 TUI。MendCode: Customizable CLI for agents, teams, memory, reviews, and TUI.

基于 Zed 构建的写作环境A writing environment built on Zed

面向 agent 间通信的私有点对点身份、信任与验证基础设施——agent 注册中心、已验证身份、防篡改消息历史。Private peer-to-peer identity, trust, and verification infrastructure for agent-to-agent communication — agent registry, verified identity, and tamper-proof message history

Spec Seatbelt 让 AI 编程 Agent 保持诚实：先写计划、逐步证明、以全新视角验证；一次加载一个阶段（token 用量减少约 70%）；持久化的 .specs/ 记忆、循环计划波次与任务图，支持安全的并行工作。支持 Cursor 与 ClaudeSpec Seatbelt keeps AI coding agents honest: write the plan first, prove each step, verify with fresh eyes. Load one phase at a time (~70% fewer tokens). Persistent .specs/ memory, loop-plan waves, and task graphs for safe parallel work. Cursor & Claude.

Agents as Infrastructure。自托管多 Agent MCP server——具备 workspace、持久记忆与层级结构的长期运行 Agent。配备真实管理 UI、OAuth 2.1、静态加密 secrets。Agents as Infrastructure. Self-hosted multi-agent MCP server — long-lived agents with workspaces, persistent memory, and hierarchy. Real admin UI, OAuth 2.1, encrypted secrets at rest.

确定性的分阶段流水线，用于学术论文的检索、筛选、下载、转换与摘要。提供 CLI 与 MCP server。Deterministic stage-based pipeline for searching, screening, downloading, converting, and summarizing academic papers. CLI + MCP server.

围绕 LLM 人类价值观与多元对齐的精选论文、基准、数据集与工具合集。A curated collection of papers, benchmarks, datasets, and tools on human values in LLMs and pluralistic alignment.

通过单一 MCP 服务器，将任务分派给 Codex、Claude 与 OpenCode。Delegate work to Codex, Claude, and OpenCode through one MCP server

基于 FastAPI + LangChain + RAG 的 AI 智能对话助手，支持多轮对话记忆、图片分析、流式回复、知识库 RAG 检索、上传定义知识库。

AI 安全测试——发现 LLM 应用、聊天机器人、AI Agent、MCP 服务器与 RAG 系统中的安全漏洞。对齐 OWASP（LLM、Agentic、MCP）与 NIST AI RMFAI security testing — find security vulnerabilities in LLM apps, chatbots, AI agents, MCP servers, and RAG systems. Mapped to OWASP (LLM, Agentic, MCP) and NIST AI RMF.

DP-ES 官方实现：面向 Prompt 优化的差分隐私进化策略（EMNLP 2026）。Official implementation of DP-ES: Differentially Private Evolution Strategies for Prompt Optimization (EMNLP 2026)

🧠 构建模拟人类记忆的 AI 认知架构，分离情景记忆与语义记忆，并保证多语言支持与数据完整性🧠 Build a cognitive architecture for AI that mimics human memory, separating episodic and semantic memory while ensuring multilingual support and data integrity.

🚀 temp-os 简化 Fedora 安装：一个实验性模板，可无缝 rebase 到最新的 atomic 镜像🚀 Simplify Fedora installations with temp-os, an experimental template for rebasing to the latest atomic images seamlessly.

一个 API 接入 2000+ AI 模型、2000+ 工具与托管 agents。One API for 2000+ AI models, 2,000+ tools, and managed agents.

Codex + DeepSeek 的任务感知推理模式路由（spec/react/weak）Task-aware reasoning-mode router for Codex + DeepSeek | Codex+DeepSeek 思维模式路由（spec/react/weak）

MedDraft_AI 是一个专用于学术医学研究写作的本地优先自主流水线——支持论著、硕士与博士学位论文、系统综述、叙述综述、范围综述、Meta 分析、研究方案与临床报告。MedDraft_AI is an autonomous local-first pipeline designed exclusively for academic medical research writing — manuscripts, theses, dissertations, systematic reviews, narrative reviews, scoping reviews, meta-analyses, protocols, and clinical reports.

私有、100% 本地运行的论文追踪器，内置 PDF 阅读器。A private, 100% local research paper tracker with a built-in PDF reader

🚀 零配置将 LangChain Agent 暴露为服务；以简单包装把脚本变为 Web 服务，无需任何基础设施🚀 Expose your LangChain agents as services with zero configuration; turn scripts into web services using simple wrappers and no infrastructure setup.

🤖 通过 Model Context Protocol 服务器在 IDE 与 CLI 工具间共享记忆并协调任务，增强 AI Agent 之间的协作🤖 Enhance collaboration among AI agents with a Model Context Protocol server that shares memory and coordinates tasks across IDEs and CLI tools.

桌面端 AI 伴侣，集成 Live2D 形象、自主编码 Agent（AgentLoop）、语义记忆与确定性主动引擎——真实进程沙箱（bwrap）、权限门控工具执行、local-first（SQLite + ONNX）。Desktop AI companion with Live2D avatar, autonomous coding agent (AgentLoop), semantic memory, and a deterministic proactivity engine — real process sandboxing (bwrap), permission-gated tool execution, local-first (SQLite + ONNX).

本人毕业学年所有天体物理课题汇总。毕业设计聚焦轨道转移优化，采用梯度下降法及 Markov Chain Monte Carlo 方法进行不确定性评估These are all the astrophysics projects in my final year. My final-year project focuses on orbital transfer optimisation using gradient descent and the Markov Chain Monte Carlo method for uncertainty evaluation.

2026 终极 AI 记忆栈：面向 LLM 的本地优先 Rust MCP2026 Ultimate AI Memory Stack: Local-First Rust MCP for LLMs

🔒 模拟对抗行为以测试和强化 MCP 防御，无需真实利用或风险，确保稳健的安全评估🔒 Simulate adversarial behaviors to test and strengthen MCP defenses without real exploitation or risk, ensuring robust security evaluations.

开源美元融资压力终端，使用公开的美联储、回购、财政部、持仓和市场数据Open-source US dollar funding-stress terminal using public Federal Reserve, repo, Treasury, positioning, and market data.

基于 IMDb 与 Netflix 互动数据（20K+ 匹配条目）的内容表现与受众分群分析。围绕五个研究问题，采用经校验的统计方法（bootstrap CI、k-means、卡方、Random Forest）作答——旨在展示面向 Disney DTC 的内容规划与分析能力。完整方法论与已知局限性均已记录。Content performance & audience segmentation analysis using IMDb and Netflix engagement data (20K+ matched titles). Five research questions answered with validated statistics (bootstrap CIs, k-means, chi-square, Random Forest) — built to demonstrate Content Planning & Analysis skills for Disney DTC. Full methodology + known limitations documented.

AI 驱动的学术写作AI-powered academic writing

在 VS Code 中本地编辑 Overleaf 项目，支持双向同步。Edit Overleaf projects locally in VS Code with two-way synchronization.

基于 GenAI 的科研论文分析平台，支持多 PDF 问答、论文对比、文献综述与研究情报。GenAI-powered platform for research paper analysis, multi-PDF QA, paper comparison, literature review and research intelligence.

基于 AI 的简历优化工具，可根据任意职位描述定制简历。使用 Streamlit、LlamaIndex 与 Nebius AI 构建。AI-powered resume optimizer that tailors your resume to any job description. Built with Streamlit, LlamaIndex and Nebius AI.

基于 LGPD、CDC 与 CLT 的 RAG：使用标准答案衡量检索效果，对比 BM25、embeddings 与混合方案，并通过一次使最常见 guard-rail 失败的弃答测试RAG sobre LGPD, CDC e CLT — recuperação medida com gabarito, comparação de BM25, embeddings e híbrido, e um teste de abstenção que reprovou o guard-rail mais comum

一套面向 LLM-based RTL 验证开放研究问题的架构：分块多表征记忆（BM25 / HNSW / 结构化事实）、基于本地 7B LLM 的多 Agent 编排器，以及具备漂移保护的反馈驱动优化。An architecture answering open research questions on LLM-based RTL verification: chunked multi-representation memory (BM25 / HNSW / structured facts), a multi-agent orchestrator over a local 7B LLM, and feedback-driven refinement with drift protection.

科学写作作品集：摘要、Bulk & scRNA-seq 方法学文档、结果解读与期刊投稿信。Scientific writing portfolio: abstracts, Bulk & scRNA-seq methodology documentation, results interpretation, and journal cover letters

通用深度研究 Agent 团队：13 Agent 流水线，提供包含系统综述与 Meta 分析在内的 8 种模式。Universal deep research agent team: 13-agent pipeline, 8 modes incl. systematic review and meta-analysis

Nexus Memory AI Plugin：面向 2026 持久化上下文的 OpenClaw 与 Hermes MCP 集成。Nexus Memory AI Plugin: OpenClaw & Hermes MCP Integration for Persistent Context 2026

新西兰 PIC Party 项目，涉及为期 59 天的政党注册议题、独立选区候选人、基于良知的政府组建以及正在浮现的生活成本政策。本站呈现提案、研究问题、政治讽刺与政策建模；非选举委员会建议，不代表官方选举。PIC Party New Zealand project, the 59-day party-registration issue, independent electorate candidates, conscience-based government formation and emerging cost-of-living policy. This site presents proposals, research questions, political satire and policy modelling. It is not Electoral Commission advice and does not represent an official election.

使用 R 进行荣誉研究项目的源码与统计分析。Source code and statistical analysis for my honours research project using R.

面向 Neuro-Olfactive Intelligence 的专有可复现研究框架Proprietary reproducible research framework for Neuro-Olfactive Intelligence

基于 Codex、LaTeX、TeX Live 与 VS Code 的双语可复现学术写作工作流。A bilingual, reproducible workflow for academic writing with Codex, LaTeX, TeX Live, and VS Code.

Rust Graph Tracker：为 LLM 编程 Agent 提供数值与日期来源追踪，支持表达式求值与推导验证Rust Graph Tracker: numeric and date provenance tracking with expression evaluation and derivation verification for LLM coding agents

Euro Truck Simulator 2 / American Truck Simulator 的遥测与驾驶分析 MCP server，附带无头 Claude 分析 agent。只读、Family-A。MCP server for Euro Truck Simulator 2 / American Truck Simulator telemetry + driving analytics, with a headless Claude analytics agent. Read-only, Family-A.

面向 Agentic Dynamics 的实验工具：衡量 AI Agent 如何行为、恢复并产出已验证的结果Experimental instrument for Agentic Dynamics: measuring how AI agents behave, recover, and produce verified outcomes

基于证据的论文检索与推荐 Agent，面向复杂研究问题。Evidence-grounded paper search and recommendation agent for complex research questions.

MetaWorld Research Academy——meta 分析工具平台。MetaWorld Research Academy - meta-analysis tools platform

个人知识图谱：抽取、验证阶梯、检索与衰减，通过 MCP 服务任意客户端A personal knowledge graph: extraction, a verification ladder, retrieval, and decay — served over MCP to any client

使用 EMI Corpus of Student Academic Writing（Gablasova et al., 2024）中的 449 篇文章，检验写作者 L1 背景是否调节 22 项 USAS 语义域频率与作文分数之间的关系。How to use 449 essays from the EMI Corpus of Student Academic Writing (Gablasova et al., 2024) to test whether a writer's L1 background moderates the relationship between 22 USAS semantic-domain frequencies and essay scores.

面向 LLM 的阶段感知上下文窗口治理框架。提供不变的上下文长度上限、基于熵的稳定性控制，以及针对降级（碎片化）状态的概率性保证，适用于生产级 LLM 系统。Phase-aware context window governance framework for Large Language Models (LLMs). Provides invariant context length caps, entropy-based stability control, and probabilistic guarantees against degraded (fragmentation) states for production LLM systems.

面向证据治理的化学文献综述 Agent skill。Agent skill for evidence-governed chemical literature reviews

面向农业机器人成像系统综述与 Meta 分析的数据与分析代码。Data and analysis code for a systematic review and meta-analysis of agricultural robotic imaging

Shadow / Unmanaged API 的发现、分类、安全验证与可复现研究基准。Shadow / Unmanaged API discovery, classification, security validation, and reproducible research benchmarks

已取代并撤回——未经验证的效应量数据集，请勿使用或引用。已由 github.com/JK-Sah/carbonation-lca-review 替代，参见 CORRECTION.md。SUPERSEDED AND WITHDRAWN — unverified effect-size dataset; do not use or cite. Replaced by github.com/JK-Sah/carbonation-lca-review. See CORRECTION.md

Jadon Writes 提供的专业学术写作与研究支持服务Professional academic writing and research support services by Jadon Writes.

Codiacs 黑客松团队仓库 - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:codiacs]Hackathon team repository for Codiacs - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:codiacs]

面向 AI Agent 调试 Android React Native/Expo 应用的本地运行时可观测性桥接层——以证据为先：截图、UI 树、逐请求网络数据、FPS、React 渲染、CDP console/heap/profile、确定性诊断、前后对比。Local runtime observability bridge for AI agents debugging React Native/Expo apps on Android — evidence-first: screenshots, UI trees, per-request network, FPS, React renders, CDP console/heap/profile, deterministic diagnosis, before/after compare.

ScientiaPilot 公开展示——从研究问题到发表全流程的科研出版操作系统。Public showcase for ScientiaPilot — a research publication operating system from research question to publication.

科学写作作品集，涵盖医学检验科学、分子生物学、抗微生物耐药、分子诊断、基因组学、生物信息学与计算生物学。A scientific writing portfolio exploring medical laboratory science, molecular biology, antimicrobial resistance, molecular diagnostics, genomics, bioinformatics and computational biology.

AI 编程 Agent 会话知识的无损压缩——先症状分诊、持久化捕获、冷启动验证Lossless compaction of session knowledge for AI coding agents — symptom-first triage, durable capture, cold-start verification

基于 Kaggle Zomato Bangalore 数据集的餐厅数据分析与可视化，涵盖数据预处理、探索性分析、研究问题与可视化。Restaurant data analysis and visualization using the Zomato Bangalore dataset from Kaggle, covering data preprocessing, exploratory analysis, research questions, and visualization.

钥石复盘：面向魔兽世界大秘境玩家的 AI 复盘教练（战术意图理解 + 社区知识库 RAG）

受治理的 Data Agent：基于 OpenMetadata，针对 Fabric、PostgreSQL 等的自然语言查询。每次查询经过双重鉴权——服务端的角色规则，再以调用者自身身份由引擎执行。任意 MCP 客户端无需修改即可对接真实 Azure。A governed Data Agent: natural-language questions over Fabric, PostgreSQL and more, grounded in OpenMetadata. Each query is authorized twice — role rules in the service, then the engine under the caller's own identity. Any MCP client, unchanged against real Azure.

Colophon——经过生产验证的 Quarto + LaTeX 脚手架，用于课程书籍、手册与技术参考书。开箱即用支持横向页面、附录、带题注的表格以及正确的引用样式。Colophon — a production-tested Quarto + LaTeX scaffold for course books, manuals, and technical handbooks. Landscape pages, appendices, captioned tables, and citation styling handled correctly out of the box.

2026 AI 驱动的加密货币 Alpha 引擎 🚀——追踪叙事与空投机会。AI-Powered Crypto Alpha Engine 2026 🚀 - Sniping Narratives & Airdrops

以静态优先的学术写作平台，支持草稿撰写、引用管理、文献综述、图表与可投稿的 PDF 输出。Static-first academic writing platform for drafting, citations, literature review, figures, and submission-ready PDFs.

将问题框架视为计算状态的可复现研究框架，包含理论、算法与基准，用于内生探究。A reproducible research framework for treating problem frames as computational states, with theory, algorithms, and benchmarks for endogenous inquiry.

一个基于 C# 与本地 LLM 的学术论文 RAG（Retrieval-Augmented Generation）系统。目标是摄入研究论文语料，构建可回答文献综述类问题（如"其他论文关于 X 发现了什么"）的系统，回答严格基于真实源材料。A RAG (Retrieval-Augmented Generation) system for academic papers using C# and a local LLM. The goal is to ingest a corpus of research papers and build a system that can answer literature review questions like "what have other papers found about X"; grounded in the actual source material.

珊瑚损伤后再生的 PRISMA 系统综述与 meta 分析。Coral regeneration after wounding: PRISMA systematic review and meta-analysis

可复用的 Python 与 notebook 工作流，用于多语言科研数据准备、统计分析及 AI 文本检测器评估。Reusable Python and notebook workflows for multilingual research-data preparation, statistical analysis, and AI-text detector evaluation.