趋势榜

AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」，桌面本身也是「插件」。

Astrid：面向可组合软件的轻量级、能力安全（capability-secure）操作系统。Astrid is a portable, capability-secure operating system for composable software.

AI 原生网络安全的执行系统——意图转化为受治理的执行，证据成为可运营的记忆，每一次操作都让下一次更优。The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

WFGY 正迈向 WFGY 5.0 Polaris Protocol，面向 AI reasoning、RAG、agents 与真实工作流的重要开源版本，包含 Problem Map、Global Debug Card、WFGY 4.0 与 CFV Easter EggWFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

RepoPrompt 社区版：面向 AI 编码 Agent 的原生 macOS 上下文工程应用，附带 MCP CLI。Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

本地优先的视觉生成运行时与工作台，面向人类与编程 agent，跨多提供商提供可复现的图像与视频工作流。Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.

DSH Web 鲸鱼娘皮肤系列(深海女仆工坊 maid-atelier)——CC BY-NC-SA 4.0

拓扑不动点理论：由两个公理推导标准模型、α⁻¹ 与宇宙学的机器可验证离散编译器。包含论文、验证套件（Python/Wolfram/Lean）、实验及网站。Topological Fixed-Point Theory: a machine-checked discrete compiler for the Standard Model, α⁻¹, and cosmology from two axioms. Papers, verification suite (Python/Wolfram/Lean), experiments & website.

Hermes 桌面端 Bot 模式：一组具名 Agent，各自拥有聊天、头像、任务例程与 Bot 间消息。桌面插件，无需修改核心。Bot Mode for the Hermes desktop: a roster of named agents with their own chats, avatars, routines, and bot-to-bot messaging. Desktop plugin, no core patches.

精选的可复现研究案例、项目、教程与媒体资源列表。A curated list of reproducible research case studies, projects, tutorials, and media

一份配置即可统管所有 AI agents：跨项目跨会话可移植、内置精选写作/路由/skills、更安全（内置破坏性命令防护）One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

dsh-tianshu-tui — DeepSeek Harness terminal UI +harness workflow。是官方 DeepSeek Harness 上的交互式终端 UI 插件。渲染核心从本仓库自研的harness agent Tianshu-Tui 演进而来，在官方的基础上增加了TDD、证据门、视觉图像模块等工作流。

由 AI Pulse Georgia 策划的尖端 AI agent 框架、开发者工具与自动化资源精选集A curated collection of cutting-edge AI agent frameworks, developer tools, and automation resources — by AI Pulse Georgia

一款现代化的本地离线 LaTeX 与 Typst 编辑器，同时支持可视化编辑与源码编辑。A modern, local, offline LaTeX & Typst editor with both visual and source editing.

一款便捷的 lib，用于流畅地与大语言模型（LLM）交互及构建 AI 应用。A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.

故障开放（fail-open）的 OpenWrt WLOC 定位网关 PoC，配套可审计的 multi-agent 开发流程。Fail-open OpenWrt WLOC location gateway PoC with auditable multi-agent development workflow

FreeBuff 编码模型的 OpenAI 兼容网关。Token 池、会话生命周期、TLS stealth、嵌入式管理后台。无广告、无 CLI，只有 /v1/chat/completions。OpenAI-compatible gateway for FreeBuff coding models. Token pool, session lifecycle, TLS stealth, embedded admin dashboard. No ads, no CLI, just /v1/chat/completions.

技術書を読みながら、気になった箇所を選択して AI に質問できる PDF リーダー

Tonkeeper Fake Balance —— TON 钱包余额伪造工具，支持 Tonkeeper 移动端与桌面端的实时浮层覆盖、自定义 TON 与 Jetton 余额注入、交易记录伪造以及截图安全的持久化显示。Tonkeeper Fake Balance — TON wallet balance spoofing tool with real-time overlay for Tonkeeper mobile & desktop, custom TON & Jetton balance injection, transaction history forging, and screenshot-safe persistent display

DSH桌面端，支持主题和背景图等多种个性化配置。Electron desktop shell for DeepSeek Harness web UI

一个接口对接九个基因组深度学习 oracle——变异效应预测、按轨道校准的百分位数与通过 MCP 提供的通俗易懂分析。One interface to nine genomic deep-learning oracles — variant effect prediction, calibrated per-track percentiles, and plain-English analysis through MCP.

基于 Wine 的 iOS 应用运行时，集成 JuiceGUI 与实验性 x86-64 翻译。Wine-based iOS application runtime with JuiceGUI and experimental x86-64 translation

一款 WordPress 插件，使用 OpenAI API（GPT-4.5、o3）生成 SEO 优化、拟人化的长篇内容和图片。A WordPress plugin that uses the OpenAI API (GPT-4.5, o3) to generate SEO-optimized, humanized, long-form content and images.

紧凑型 Codex skill，涵盖比例化编码、测试、ML 验证与学术写作。A compact Codex skill for proportional coding, testing, ML validation, and academic writing.

将 Overleaf 评论与修订追踪导出为 Markdown + JSON，面向 AI-Agent 消费优化。Export Overleaf comments and tracked changes to Markdown + JSON, optimized for AI-agent consumption

一个用于科学文献分析的开源 agentic harness。可协调前沿模型提取数据、复现发现并执行系统综述，具备完整的溯源追踪能力。An open-source agentic harness for scientific literature analysis. Coordinates frontier models to extract data, replicate findings, and perform systematic reviews with full provenance tracking.

💻 在 macOS 上借助 Metal GPU 实现 Qwen3 Transformer 模型，获得加速且高效的性能，并支持关键架构特性💻 Implement Qwen3 transformer model on macOS using Metal GPU for accelerated, efficient performance with support for key architecture features.

开源 AI 占星 chatbot：支持 Vedic kundli、西洋星盘、塔罗、数字学、解梦，通过远程 MCP 进行真实计算，multi-LLM，Next.js 16，MIT 许可。Open source AI astrology chatbot. Vedic kundli, Western charts, tarot, numerology, dreams. Real calculations via remote MCP, multi-LLM. Next.js 16, MIT.

📄 自动从 PDF 中提取 BibTeX 条目，无需手动输入或调用外部 API 即可生成完整参考文献列表。📄 Extract BibTeX entries from PDFs automatically, generating a complete bibliography without manual input or reliance on external APIs.

邮件的"大脑"：MailFathom 将 IMAP 邮箱转化为自托管、AI 原生服务。邮件同步至自有 PostgreSQL，建立索引以支持搜索与检索，并通过 Model Context Protocol 服务于 AI Agent。当前为只读；后续将支持语义检索、问答与受控写入工具。.NET 10，Apache-2.0。A brain for your mail: MailFathom turns IMAP mailboxes into a self-hosted, AI-native service. Mail synchronizes into your own PostgreSQL, is indexed for search and retrieval, and is served to AI agents over the Model Context Protocol. Read-only today; semantic retrieval, answering, and gated write tools next. .NET 10, Apache-2.0.

自动跟踪、下载并分析 HuggingFace 上的 AI 论文，轻松掌握前沿研究 🐙📄Automate the tracking, downloading, and analysis of AI papers from HuggingFace. Stay updated with cutting-edge research effortlessly! 🐙📄

基于 Tauri、SvelteKit 和 Rust 构建的现代多 Agent 桌面 AI 客户端。A modern, multi-agent desktop AI client built with Tauri, SvelteKit, and Rust.

🚀 通过 70 个生成式 AI 实战项目转型技能，从入门到生产级架构师，涵盖真实场景应用。🚀 Transform your skills with 70 hands-on projects in Generative AI, guiding you from beginner to production-ready architect with real-world applications.

本仓库包含用于执行不同任务的 Gen AI 项目temThis repository contains Gen AI projects that performs different tasks

基于 Rust 构建的 MCP 原生嵌入式 AI agent 记忆数据库，提供 REMEMBER/RECALL/FORGET/SHARE 原语，支持混合向量搜索、AES-256-GCM 加密、DuckDB/PostgreSQL 后端以及 Python、TypeScript 与 Go 的 SDKMCP-native embedded memory database for AI agents built in Rust. REMEMBER/RECALL/FORGET/SHARE primitives with hybrid vector search, AES-256-GCM encryption, DuckDB/PostgreSQL backends & SDKs for Python, TypeScript and Go.

🤖 使用 SurfSense 增强你的研究——一个可定制的 AI Agent，可连接多平台，实现更智能、高效的信息检索。🤖 Enhance your research with SurfSense, a customizable AI agent that connects to multiple platforms for smarter, effective information retrieval.

🔍 使用 DeepSearch 自动化数字足迹分析，借助高级 Google 搜索操作符高效收集多平台洞察。🔍 Automate digital footprint analysis with DeepSearch, using advanced Google search operators to gather insights from multiple platforms efficiently.

builderr.ai 交易 Agent 模板——fork 后实现 decide()，即可提交。Trading agent template for builderr.ai — fork this, implement decide(), submit.

无状态统一多提供商 AI 运行时，兼容 OpenAI 与 Anthropic 的 API，支持 Vercel UI 流式输出，覆盖 130k+ 模型的托管 Agent 与 Skills。Stateless unified multi-provider AI runtime with OpenAI & Anthropic-compatible APIs, Vercel UI streaming, managed agents and Skills across 130k+ models.

后端无关的 C# 库，用于构建有状态 AI 实体，具备按角色记忆、工具调用、情绪系统和自主 Agent 行为。Backend-agnostic C# library for building stateful AI entities with per-persona memory, tool access, mood systems, and autonomous agent behavior.

用于多元 meta 分析（含标准 NMA 与 cNMA）的 IRG 仓库。IRG repository for multivariate meta-analyses, including standard NMAs and cNMAs

对 CPI（消费者价格指数）与工资差距趋势的统计分析，涵盖数据探索、可视化及基于 R 的计量经济学方法。包含对既有研究的回顾以及可复现的扩展分析工作流。Statistical analysis of CPI (Consumer Price Index) and wage disparity trends, combining data exploration, visualization, and R-based econometric methods. Includes a review of prior research and a reproducible workflow for extending the analysis.

自托管、隐私优先的个人 AI 知识伴侣，具备 RAG 驱动的检索、智能 Agent 与可扩展 SDK。Self-hosted, privacy-first Personal AI Knowledge Companion with RAG-powered retrieval, intelligent agents, and extensible SDK

🐙 AI Agent Pipeline 基于意图将查询路由至文档、天气或聊天模块，结合 LangGraph、ChromaDB 与 LangSmith，实现跨 CLI 与 UI 的模块化、可观测工作流🐙 AI Agent Pipeline routes queries by intent to docs, weather, or chat, with LangGraph, ChromaDB, and LangSmith for modular, observable workflows across CLI and UI.

在完全运行于浏览器的单文件 Web 应用中，查找开放获取期刊（Diamond OA 或 APC，含 SCImago 排名）、CS 会议截止日期（CCF/CORE）以及摩洛哥的研究活动。Find open access journals (Diamond OA or APC, with SCImago rankings), CS conference deadlines (CCF/CORE), and research events in Morocco a single-file web app running entirely in your browser.

将任意视频链接转化为博士级研究报告。自动化学术流水线：一键完成下载、转写、检索同行评审文献、核查论据并生成带引用的报告。免费且开源。Turn any video url into a PhD-grade research report. Automated academic pipeline: download, transcribe, search peer-reviewed literature, verify claims, generate cited reports — all with one command. Free & open source.

AI Research Wiki 2026：通过深度引用综合自动构建知识库AI Research Wiki 2026: Auto-Building Knowledge Base with Deep Citation Syntheses

Cortex System：AI 工程领域的操作系统，治愈技术健忘症。Cortex System: The Operating System for AI Engineering. Cure Technical Amnesia.

Adobe UXP 插件 AI Assistant 2026 🤖 | 开发工具与 Spectrum WC 指南。Adobe UXP Plugin AI Assistant 2026 🤖 | Dev Tools & Spectrum WC Guide

Vantio Optics — 为 LLM/agent 出站流量提供免费的可观测能力。Sight Loop。设计即盲视。非代理。@vantio/cli 0.3.2 · vantio-agent-sdk 3.0.2Vantio Optics — free observe for LLM/agent egress. Sight Loop. Blind by design. Not a proxy. @vantio/cli 0.3.2 · vantio-agent-sdk 3.0.2

一个可运行的 TypeScript 教程，从零搭建一个极简 DeepSeek 风格 Agent 框架。A runnable TypeScript tutorial that builds a minimal DeepSeek-style agent harness from scratch.

LabRelay 连接需要处理可管理研究任务（文献综述、数据录入、问卷外联）的教授与医生，以及寻求真实经验和入门途径的学生。LabRelay connects professors and doctors who need help with manageable research tasks — literature reviews, data entry, survey outreach — with students who want real experience and a way in.

💹 使用 Python 和 CoinGecko API 分析主要加密货币的价格、市值与趋势，辅助投资决策💹 Analyze major cryptocurrencies' prices, market caps, and trends using Python and the CoinGecko API for informed investment decisions.

AI Brand Strategy Toolkit 2026 🚀 — 基于 Kapferer 与 Aaker 框架AI Brand Strategy Toolkit 2026 🚀 - Kapferer & Aaker Frameworks

2026 年顶级开源 AI Agent 🤖 | 最佳自主工具与框架Top Open-Source AI Agents 2026 🤖 | Best Autonomous Tools & Frameworks

面向澳大利亚公共执业会计的 AI Agent skills：BAS、FBT、Division 7A、STP、月末结账与底稿。AI agent skills for Australian public-practice accounting: BAS, FBT, Division 7A, STP, month-end close and workpapers.

将 Spark/Hive SQL 转化为结构化、可追溯的事实，供 Agent、RAG 和 AI 知识库使用。Turn Spark/Hive SQL into structured, traceable facts for Agents, RAG, and AI knowledge bases.

WordPress 共享 AI 基础设施：provider 凭证、实时模型、提示词、标准化请求及 AI-Scribe 和兼容插件的使用记录。Shared AI infrastructure for WordPress: provider credentials, live models, prompts, normalised requests and usage records for AI-Scribe and compatible plugins.

自动化 git-worktree 工作流：通过 Claude Code 或 GitHub Copilot CLI 从 diff 中提取意图，执行构建/lint/测试，开启 GitLab MR 或 GitHub PR，并自动修复失败的 pipeline。Automated git-worktree workflow that captures intent from diffs via Claude Code or GitHub Copilot CLI, runs build/lint/test, opens GitLab MRs or GitHub PRs, and auto-fixes failing pipelines.

面向 AI 编程 agent 的平台无关工作编排，基于 MCP + CLI，提供跨提供商的统一面板（issues、scm、ci、deploy、notify）。Platform-agnostic work-orchestration for AI coding agents — one pane of glass (issues, scm, ci, deploy, notify) across providers, via MCP + CLI.

🛠️ 通过 ACG 增强 RAG 系统，依托可靠的外部知识提升准确性与事实一致性，减少 LLM 响应中的幻觉。🛠️ Enhance RAG systems with ACG to reduce hallucinations in LLM responses by improving accuracy and grounding in reliable external knowledge.

针对 LLM 集成证据筛选（系统综述标题/摘要筛选）的筛选-自验证内核。Screening-and-self-validation kernel for LLM-ensemble evidence screening (systematic review title/abstract screening).

面向 AI Agent 的证据可追溯研究 API。哈希链存证可自行验证，明确拒答，并通过 x402 微型支付——自身失败时绝不收费。Evidence-grounded research API for AI agents. Hash-chained custody you can verify yourself, explicit refusal, and x402 micropayments — it never bills you for its own failure.

面向 AI Agent 的精确小数复式记账内核。通过 MCP 工具调用完成金额计算，避免在 token 中做财务运算。默认拒绝、审计哈希、完全确定性。Exact-decimal double-entry kernel for AI agents. Call MCP tools instead of doing money math in tokens. Fail-closed, audit-hashed, deterministic.

AI it yourself——一款原生 iOS 聊天应用，Agent 可在其中构建你所需的小工具，沙箱化且立即可用。无服务器、无账号：自带 API key、本地机器或在 iPhone 上运行的模型。AI it yourself — a native iOS chat where agents build the small tools you need, sandboxed and usable immediately. No server, no account: bring your own API key, your own machine, or a model running on the iPhone.

跨平台桌面端（EXE）学术论文聚合客户端，支持自定义 JSON 数据源规则、多标签页隔离搜索、内置 PDF 阅读与翻译、批量下载，灵感来自 Legado。A cross-platform desktop client (EXE) for aggregating academic papers. Supports custom JSON data-source rules, multi-tab isolated search, built-in PDF reader with translation, and batch downloads. Inspired by Legado.

ILRI 农业-食品系统气候适应证据综合与系统综述咨询仓库，聚焦"衡量关键：追踪小农户气候适应的有效性"。A repository for the ILRI consultancy on evidence synthesis and systematic reviews of climate adaptation in agri-food systems, focused on “Measuring what matters: tracking the effectiveness of climate adaptation for smallholder producers.”

🚀 使用 MCP Server 轻松启动本地服务器，双击即可即时搭建后端与界面。🚀 Launch a local server with ease using MCP Server for instant backend and interface setup, all with a single double-click.

🚀 通过 MCP server 自动化你的 Upgates 电商，与 Upgates API v2 无缝集成。🚀 Automate your Upgates e-shop with the MCP server for seamless integration with the Upgates API v2.

Agent 原生桌面工作台，支持 LaTeX、实时 PDF、可编辑 PowerPoint、Python、SSH 与编程 Agent。Agent-native desktop studio for LaTeX, live PDF, editable PowerPoint, Python, SSH, and coding agents.

AI 驱动的 Monorepo 2026：设计系统、React 应用、Fastify API 与 Pulumi IaC。AI-Powered Monorepo 2026: Design System, React Apps, Fastify APIs & Pulumi IaC

LinkPlace、LinkPlace-C 与 LinkPlace-M 的可复现研究发布版本。Reproducible research release for LinkPlace, LinkPlace-C, and LinkPlace-M.

仅英文、本地 CSV 运行的系统综述文献下载助手。English-only, local CSV literature download assistant for systematic review projects

学习驱动运动预测与规划中风险校准及运行时保障系统综述的可复现材料。Reproducibility materials for a systematic review of risk calibration and runtime assurance in learning-enabled motion prediction and planning.

开源 Raspberry Pi 5 rover 项目，用于建图、视觉、语音、本地 LLM 及液态神经网络实验。Open-source Raspberry Pi 5 rover project for mapping, vision, voice, local LLMs, and liquid-neural-network experiments.

《从原始数据到完稿论文：构建可复现研究流水线》演讲幻灯片，用于 WHU - Otto Beisheim School of Management 博士迎新周。Slides for 'From Raw Data to Finished Paper: Building a Reproducible Research Pipeline', a Doctoral Orientation Week session at WHU - Otto Beisheim School of Management.

面向 AI Agent 的钱包地址邮箱与存储。发送需付费（x402，Base 上的 USDC）；钱包密钥持有者免费读取。接收免费。Wallet-addressed mailbox + storage for AI agents. Pay to send (x402, USDC on Base); the holder of the wallet key reads free. Receiving costs nothing.

Vengtoo 官方 Node.js/TypeScript SDK——带 Express 中间件的授权客户端。Official Node.js/TypeScript SDK for Vengtoo — authorization client with Express middleware

革新你的 2026 开发工作流：自动扫描并即时优化 100+ 技术栈。Revolutionize Your Dev Workflow 2026: Auto-Scan & Optimize 100+ Tech Stacks Instantly

销售收件箱的 AI 后台：读取每条询盘，仅推荐实际有货的商品，以你的口吻起草回复——并在任何内容发出前等待人工点击批准。An AI back office for your sales inbox: it reads every enquiry, recommends only what is actually in stock, drafts the reply in your voice — and waits for a human to click Approve before anything sends.

校园社区：地理位置范围内容 · RAG 混合检索 · 问题追踪 · AI 助手（千问 v3-flash）

🔐 使用 KeyVault Pro 安全管理 API key，具备军事级加密、智能自动填充与面向开发者的无缝 AI 集成。🔐 Manage API keys securely with KeyVault Pro, featuring military-grade encryption, intelligent auto-fill, and seamless AI integration for developers.

专业作品集，展示环境科学研究、GIS 与数据分析项目、AI 与技术学习、科学写作、出版物、领导力、专业发展与跨学科工作。Professional portfolio showcasing my environmental science research, GIS and data analytics projects, AI and technology learning, scientific writing, publications, leadership, professional development, and interdisciplinary work.

专业跨平台纵向心率变异性（HRV）分析应用，支持 Kubios 数据导入、自动生成科研报告、高级统计分析、受试者管理，以及面向研究、运动科学和临床监测的交互式仪表板。A professional cross-platform application for longitudinal Heart Rate Variability (HRV) analysis, featuring Kubios data import, automated scientific reporting, advanced statistical analysis, participant management, and interactive dashboards for research, sports science, and clinical monitoring.

美国国会图书馆（Library of Congress）MCP server：检索扫描报纸、浏览目录、读取记录，无需 API key。MCP server for the Library of Congress. Search inside scanned newspapers, browse the catalogue, read records. No API key.

应用 AI、可复现研究与可靠工程。Applied AI, reproducible research, and reliable engineering.

关于 AI Agent 系统与编排的定向研究与文献综述的最终交付成果Final deliverables for directed studies and literature review on AI Agent Systems and Orchestration

生产级 multi-agent 系统：接收研究问题、制定调查方案、从实时网络和私有文档语料中收集证据、对自身发现进行批判与事实核查，最终输出完整引用的 Markdown 报告。A production-grade multi-agent system that accepts a research question, plans an investigation, gathers evidence from the live web and a private document corpus, critiques and fact-checks its own findings, and delivers a fully cited Markdown report.

完全在浏览器中通过 WebAssembly 实现文档转换、检查、OCR 与翻译。保留版式的翻译，全程本地、离线优先。Convert, inspect, OCR, and translate any document entirely in the browser via WebAssembly. Layout-preserving translation, fully local, offline-first.

面向 AI 饮食评估研究的 3 周入门计划：文献综述、分割、LLM 与 RAG。3-week onboarding plan for AI dietary assessment research: literature review, segmentation, LLMs, and RAG

面向探索的 Agentic 话语——自主 Claude 专家，研究、辩论、互评并综合回答研究问题。Agentic discourse for discovery — autonomous Claude specialists that research, debate, cross-rate, and synthesize answers to research questions

面向音乐学与音乐教育学术写作的 Skills 工具包。Skills package for musicology and music education academic writing

面向真实工程师的图工程（Graph-Engineering）：图定义工作流，工作流构建图。基于 mattpocock/skills。Graph-Engineering for Real Engineers: Graphs define workflows; workflows build graphs. Based on mattpocock/skills.

用于复现 https://arxiv.org/abs/2106.12905 中图示所使用代码与数据的仓库。A repository to story the code and data used to create the figures shown in https://arxiv.org/abs/2106.12905

🎓 创建适用于 2025 华为杯研究生数学建模竞赛的 LaTeX 模板，完美兼容 Overleaf 并配置所需中文字体。🎓 Create a LaTeX template for the 2025 Huawei Cup Graduate Mathematical Modeling Contest, fully compatible with Overleaf and featuring essential Chinese fonts.

AI 时代的工具联盟：可追溯的知识（Nexus·Archon）、可问责的审查与治理（Arbiter·Observer）、可理解的变更质量（Adept·Probe）。AI 构建，你来理解。An alliance of tools for the AI era: grounded knowledge (Nexus·Archon), accountable review & governance (Arbiter·Observer), and comprehension & mutation quality (Adept·Probe). AI builds it — you understand it.

关于宏观多细胞生物进化的可复现研究与交互式实验。Reproducible research and an interactive lab on the evolution of macroscopic multicellularity

🚀 使用 Fast-LLM 加速 LLM 训练，一个面向高速、可扩展、灵活模型开发的开源库🚀 Accelerate LLM training with Fast-LLM, an open-source library for high-speed, scalable, and flexible model development.

Claude AI 2026 Machines 插件 - 官方 GitHub 集成指南。Machines Plugin for Claude AI 2026 - Official GitHub Integration Guide

UGR 本科/硕士毕业论文 LaTeX 模板 | 格拉纳达大学 LaTeX 论文模板Plantilla LaTeX para TFG/TFM de UGR | LaTeX Thesis Template for University of Granada

💳 使用 XGBoost 检测金融交易欺诈，结合针对不平衡数据集与复杂特征的高级优化技术💳 Detect fraudulent financial transactions using XGBoost. Optimize performance with advanced techniques for imbalanced datasets and complex features.

基于 GitHub Page 的 2026 年文献综述 Miscanthus 产量制图演示。Demonstration of GitHub Page with Miscanthus Yield mapping for Literature Review 2026

一款本地化、隐私优先的 LLM 助手，提供学术写作辅助、音频转写、文档检索与数据分析。A local, privacy-first LLM assistant that performs academic writing assistance, audio transcription, document retrieval, and data analysis.

在 LaTeX 文档中分析英文散文，评估可读性与结构复杂度。Analyze English prose in LaTeX documents for readability and structural complexity.

Vibe-Flow 2.0：通过 Wave Dispatch 实现交付、评审与合并 2026Vibe-Flow 2.0: Ship, Review & Merge via Wave Dispatch 2026

Conversational academic writing Copilot: LangGraph ReAct agent with citation tracing, faithfulness reviewer, RAG & Reflexion LaTeX self-repair ｜ 对话式学术写作 Copilot：LangGraph ReAct 智能体，引用溯源 + 忠实度审校 + RAG 检索 + Reflexion 编译自修复，端到端产出真实 PDF

GoVail MCP —— 用于 GoVail 平台集成的 Model Context Protocol server 与工具。GoVail MCP — GoVail 플랫폼 연동을 위한 Model Context Protocol 서버 및 도구

在真实 MCP 客户端上对 Remote MCP 服务器进行实时互操作性测试。Live interoperability testing for Remote MCP servers across real MCP clients.

PostgreSQL MCP 2026：面向开发者的最佳 AI 数据库访问工具PostgreSQL MCP 2026 Best AI Database Access Tool for Developers

面向研究生学术英语写作、研究设计、伦理、修改与发表的韩文交互式现场指南Interactive Korean field guide for graduate academic English writing, research design, ethics, revision, and publication

本数据分析报告研究多种因素与睡眠质量的关系，旨在回答：1) 不同年龄群体的睡眠质量关联因素是否存在差异？2) 职业对睡眠质量的影响程度如何？This data analysis report investigates the relationships between various factors and sleep quality, aiming to answer the following research question: 1) Do the factors associated with sleep quality differ among different age groups? 2) To what extent is occupation associated with sleep quality?

基于 Semantic Scholar 与 Crossref 的安全加固、双模式学术搜索工作台。A security-hardened, dual-mode scholarly search workbench powered by Semantic Scholar and Crossref.

用于系统综述中识别、量化、验证与可视化作者重叠的 Python 工作流。可生成研究级网络图、连通分量、重叠比例、可审计的边表以及可直接发表的图表，便于透明报告。Python workflow for identifying, quantifying, validating, and visualizing author overlap among studies included in a systematic review. Generates study-level networks, connected components, overlap percentages, auditable edge tables, and publication-ready figures for transparent reporting.

全球研究者的终极 AI 驱动发现平台。统一搜索 8+ 专业数据库（NCBI、arXiv、OpenAlex），结合 Llama 3.1 驱动的综合分析、RAG 问答与自动化文献综述。The ultimate AI-powered discovery hub for global researchers. Unified search across 8+ specialized portals (NCBI, arXiv, OpenAlex) with Llama 3.1-driven synthesis, RAG chat, and automated literature reviews.

假警报降低并非校准成果：脓毒症预测机器学习校准基线的 PRISMA 系统综述与数学分析。False-alarm reduction is not a calibration achievement: a PRISMA-compliant systematic review and mathematical analysis of calibration baselines in machine learning for sepsis prediction

🚀 通过 autopack 简化 Hugging Face 模型的运行、分享与发布，自动完成量化与多格式导出🚀 Simplify running, sharing, and shipping Hugging Face models with autopack; it quantizes and exports to multiple formats effortlessly.

研究与数据分析师 | 数据科学硕士在读 | Python • R • Stata • 统计分析Research & Data Analyst | MSc Data Science Student | Python • R • Stata • Statistical Analysis

多源科学与文献及数据集搜索引擎，作为 MCP server 为 AI Agent 提供服务。Multi-source scientific literature and dataset search engine, built as an MCP server for AI agents.

AI 助手的安检守卫。检查 AI 尝试调用的每一个工具，防止数据泄露与未授权命令。A security guard for AI assistants. It checks every tool an AI tries to use, preventing data leaks and unauthorized commands.

Stacklit：AI Codebase Indexing 2026 — 为 Agent 提供零配置本地仓库映射Stacklit: AI Codebase Indexing 2026 – Zero-Setup Local Repo Mapping for Agents

采用可复现研究方法，开发面向西部地震区的 AI 辅助地震预警系统。Develop AI-assisted earthquake early warning systems for Western seismic regions using reproducible research methods.

一款全栈应用，通过 Chrome 扩展自动捕获求职申请，在统一面板中跟踪记录，并提供洞察以优化求职流程。A full-stack application that automatically captures job applications through a Chrome extension, tracks them in a centralized dashboard, and provides insights to improve your job search.

Agentic AI 平台，用于仓库分析、迁移规划、上下文驱动的代码转换及迁移后验证。Agentic AI platform for repository analysis, migration planning, context-grounded code transformation, and post-migration validation.

Uniphore 是一家企业级 AI 公司——"The Business AI Company"——成立于 2008 年，总部位于加利福尼亚州帕罗奥图。其旗舰平台 Business AI Cloud（BAIC）是一个主权化、可组合且安全的 AI 平台，分为四层：用于对企业数据进行零拷贝访问的 Data Layer、用于检索的 Knowledge Layer……Uniphore is an enterprise AI company — "The Business AI Company" — founded in 2008 and headquartered in Palo Alto, California. Its flagship platform, the Business AI Cloud (BAIC), is a sovereign, composable and secure AI platform organised into four layers: a Data Layer for zero-copy access to enterprise data, a Knowledge Layer for retrieval and…

仓库展示经济研究代码、数据分析脚本及环境经济学、农业经济学与发展经济学论文的复现材料。包含 Stata、R 与 Python 实现的计量经济模型、实验经济学工具及可复现研究的数据可视化模板。Repository showcasing economic research code, data analysis scripts, and replication materials for publications in environmental economics, agricultural economics, and development economics. Features Stata, R, and Python implementations of econometric models, experimental economics tools, and data visualization templates for reproducible research.

交互式写作网站Interactive writing site

🌐 在数据受限条件下重新思考多模态大语言模型的设计与扩展，以 NaViL 通过 Native Training 提升效率与性能🌐 Rethink Multimodal Large Language Models design and scaling under data constraints with NaViL, enhancing efficiency and performance through Native Training.

监管 AI 的系统文献综述。Systematic Literature Review for Regulatory AI

SLM-PICO-Screener 是用于自动化系统综述筛选的轻量 NLP 流水线，基于 Phi-3 Mini 配合 LoRA 与 4-bit 量化，将文章分类为 8 个 PICO 标签。体积约 90 MB，可在消费级 GPU/CPU 上运行，加速生物医学研究中的证据综合。SLM-PICO-Screener is a lightweight NLP pipeline automating systematic review screening. Built on Phi-3 Mini with LoRA & 4-bit quantization, it classifies articles into 8 PICO labels. At ~90 MB, it runs on consumer GPUs/CPU, accelerating evidence synthesis in biomedical research.

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.