趋势榜

dsh-routing-suite——注入器 + 路由标准套件：先安装运行时注入器，再安装任务感知的推理模式路由预设（已实测 P1-P23）。dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).

DeepSeek Harness 内置的插件市场——浏览、搜索、一键安装 · DSH 可视化插件市场。The plugin market inside DeepSeek Harness — browse, search, one-click install · DSH 可视化插件市场

日历同步工具与通用日历 MCP server。可在 Google、Outlook、Office 365、iCloud、CalDAV 或 ICS 上聚合、同步和管理日历。Calendar sync tool & universal calendar MCP server. Aggregate, sync and control calendars on Google, Outlook, Office 365, iCloud, CalDAV or ICS.

为纯文本 DeepSeek Harness Agent 装上眼睛：内置免费视觉链路（无需 key）+ 像素级视觉工具（问答、定位、裁剪、像素 diff、取色、OCR、SVG 矢量化、抠图、截图）。一条命令安装，无需 Python，图像回合与普通工具调用回合一致。Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

Second Brain 是一个 Agentic 框架，作为操作系统运行，利用本地文件智能、工作流自动化和 LLM 来完成任务，并通过多种模态和消息平台进行通信。Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos.

一门实战课程，用 PyTorch 从零构建现代 LLM，包含 26 个可运行的 Jupyter Notebook，涵盖 tokenizer、attention、MoE、RLHF、推理、评估和蒸馏。A hands-on course for building modern LLMs from scratch in PyTorch, with 26 runnable Jupyter Notebooks covering tokenizers, attention, MoE, RLHF, inference, evaluation, and distillation.

用 30 秒找到适合你的 DeepSeek Harness 插件。 不只是仓库列表：这里告诉你插件解决什么问题、适合谁，以及从哪里开始。

cruby 的全能 AI runtime。cruby's capable AI runtime

精选的 DeepSeek Harness (DSH) 插件、扩展、工具、skills、客户端、运行时、集成与已验证参考——英文与中文双版本。Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

DeepSeek Harness 的任务感知推理模式路由器：三个已实测的行为带（spec/mixed/react），附带相变证据，persona + 首轮工具注入，agent 可见的可调参数。包含双吸引子策略论文。Task-aware reasoning-mode router for DeepSeek Harness: three measured behavior bands (spec/mixed/react) with phase-transition evidence, persona + first-turn tool injection, agent-visible tuning. Dual-attractor policy paper included.

DSH插件市场 / DSH Plugin Marketplace: 在 DeepSeek Harness Web GUI 中一键浏览、安装与更新 GitHub topic:dsh-plugin 的全部插件 | browse, install & update all GitHub dsh-plugin plugins in the DSH Web GUI

面向 Pi 的可编程工具与 agent 运行时。A programmable tool and agent runtime for Pi

开源核心的 AI 工作台——覆盖任何模型的 notebooks、Agent、RAG、语音和图像：OpenAI、Anthropic、Google、xAI，或通过 Ollama/vLLM 的本地模型。BSL 1.1，两年后自动转换为 Apache-2.0。当别人的 AI 停止运行时，你的 AI 仍在运行。The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.

面向机器人的开源操作系统。The open-source operating system for robots

面向持续论证技巧的学术写作助手Academic Writing Assistant for Continuous Argumentation Technique

双模式 AI 研究工作空间：DeepSearch 在约 2 分钟内将查询转化为带引用的网络报告；Research Mode 运行 25 个 Agent 的流水线，撰写完整学术论文（含 PRISMA 流程图、经核验的引用，导出 PDF/DOCX）；设有 4 个人机协同检查点；基于 LangGraph、FastAPI 与任意 OpenAI 兼容 LLM 构建AI research workspace with two modes — DeepSearch turns a query into a cited web report in ~2 min; Research Mode runs a 25-agent pipeline that writes a full academic paper (PRISMA diagram, verified citations, PDF/DOCX export). 4 human-in-the-loop checkpoints. Built with LangGraph, FastAPI, and any OpenAI-compatible LLM.

用于哲学领域的高准确度、覆盖全面的文献综述多 Agent 工作流Multi-agent workflow for accurate and comprehensive literature reviews in philosophy

面向终端的通用 AI 助手，让 Agent 之间共享可检索、可追溯且允许分歧的知识。让下一次判断，带着来源出发。

一个 170k token 的复杂业务系统。ObjectStack 将整个应用——数据模型、UI、工作流、权限——压缩为带类型的元数据，使 AI Agent 能在上下文中完整掌握、推理并重构。A complex business system in 170k tokens. ObjectStack compresses an entire app — data model, UI, workflows, permissions — into typed metadata, an AI agent can hold in context, reason about, and refactor whole.

生产级多 Agent 平台，提供编排、会话治理和审计能力。技术栈：Go/Python/Rust 微服务、多类型数据存储、Next.js 管理后台 UI、自动化 CI/CD 流水线、通过 PR 评论提及触发的 AI 代码审查。Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservices, multi-type data storage, Next.js admin UI, automated CI/CD pipelines, AI code review triggered via PR comment mentions.

DeepSeek Harness (DSH) 论文写作护栏——AI 写作风格检测、证据保留、期刊匹配校准、手稿校对、writing_audit 与自动检查。本地运行，零网络，零 LLM。DeepSeek Harness (DSH) academic writing guard for papers — 论文去AI味 / AI-writing style detection, evidence preservation, journal-fit calibration, manuscript proofreading, writing_audit & automatic checks. Local, zero network, zero LLM.

自动更新的开源知识库，面向 AI Agent、RAG 系统、MCP server、prompt、tool、模板以及新一代 Web 开发。An auto-updating open-source vault for AI agents, RAG systems, MCP servers, prompts, tools, templates, and next-generation web development.

Token 高效的 Claude Code 工作空间，支持并行 Agent 与持久记忆，集成 Research → Plan → Implement → Validate 工作流。Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.

经过调优、功能完备的 MCP，以 LLM 优化的方式操作文件系统。Tuned and fully-featured MCP to work with the filesystem in LLM optimized way

SharpAI 是基于 llama.cpp（通过 LlamaSharp）构建的可嵌入 Embedding、补全与模型管理平台，内置 Ollama 兼容的 Web 服务。SharpAI is an embeddable embeddings, completions, and model management platform using llama.cpp via LlamaSharp, with a built-in Ollama-compatible webserver.

AI Employee - Platinum Tier | 一个 7×24 管理业务运营的 Digital FTE | 邮件、社交媒体、发票、WhatsApp — 全部通过 human-in-the-loop 审批自动化AI Employee - Platinum Tier | A Digital FTE that manages business operations 24/7 | Email, Social Media, Invoicing, WhatsApp - all automated with human-in-the-loop approval

面向巴西央行 (BCB) 数据的 MCP server——为 AI agent 提供 Selic、IPCA、汇率与 GDP。MCP server for Brazil Central Bank (BCB) data — Selic, IPCA, exchange rates, GDP for AI agents

自动检查 BibTeX .bib 文件的样式规范性（借助 CTAN 的 bibcop）Automated checking of BibTeX .bib files for style correctness (with the help of bibcop from CTAN)

基于 DNS、证书透明日志与未认证身份发现的公开元数据域情报。本地 Python CLI、版本化 JSON 与 stdio MCP server，无需凭证或主动扫描。Public-metadata domain intelligence from DNS, certificate transparency, and unauthenticated identity discovery. Local Python CLI, versioned JSON, and stdio MCP server. No credentials or active scanning.

Local-first、确定性的验证层，用于 AI 声明、记忆写入和风险操作。Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.

多模型协作与智能辩论平台 — Multi-Agent 并行工作流 + RAG + 知识图谱，让多个 AI 像专家团队一样辩论、推理、共创

SOAT 是一个开源框架，旨在为自主 AI Agent 提供持久记忆能力。SOAT is an open-source framework designed to provide persistent memory capabilities for autonomous AI agents.

🛠️ 使用 Sherlock AI Plugin 将研究论文转化为可执行代码，是你高效进行文献综述与实现工作的必备工具。🛠️ Transform research papers into executable code with Sherlock AI Plugin, your essential tool for efficient literature review and implementation.

实时更新的向量数据库项目、集成和基准评测全景图——每……刷新。Live-updating landscape of vector database projects, integrations, and benchmarks — refreshed every

通过 MCP 让任意 AI agent 在你真实已登录的 Chrome 中拥有"眼睛"和"双手"。零依赖。Give any AI agent eyes and hands in your real, logged-in Chrome — via MCP. Zero dependencies.

🤖 Hermes Agent 2026：可学习、可自适应的开源 AI 助手 🚀。🤖 Hermes Agent 2026: AI Assistant That Learns & Adapts 🚀 | Open Source

面向商业智能 Agent 的 MCP server——基于真实 KPI 分析提供 6 个 tools / 6 个 resources / 1 个 prompt；兼容 Claude Desktop、LangGraph、CrewAI、DSPy。基于 FastMCP。MCP server for business-intelligence agents — 6 tools / 6 resources / 1 prompt over real KPI analytics; works from Claude Desktop, LangGraph, CrewAI, DSPy. FastMCP.

面向会议的对话智能：将转录文本转化为摘要、决策、行动项、风险与机会，支持多租户自托管。FIAP NEXT Challenge 2026。Conversation intelligence for meetings: turns transcripts into summaries, decisions, action items, risks and opportunities. Multi-tenant, self-hosted. FIAP NEXT Challenge 2026.

面向 Kubernetes 环境的 air-gapped RAG pipeline。在 LibreChat/LiteLLM/Keycloak/vLLM 之上增加文档摄取、强制的分类/可发布性标签、策展人审核与基于声明的访问控制检索，并以自定义 MCP 工具的形式对外暴露。Air-gapped RAG pipeline for Kubernetes environments. Adds document ingestion, mandatory classification/releasability tagging, curator review, and claims-based access-controlled retrieval on top of LibreChat/LiteLLM/Keycloak/vLLM — exposed as a custom MCP tool.

一个多 Agent 命令行工具，面向科研人员从 arXiv 和 Semantic Scholar 发现、总结并可视化最新量子科学论文。Multi-agent CLI tool that discovers, summarizes, and visualizes the latest quantum science papers from arXiv and Semantic Scholar for researchers.

中国地质大学（武汉）报告与答辩模板合集

THIS PAPER IS FOR ENTERTAINMENT PURPOSES ONLY.この小説はフィクションであり、実在する団体または個人とは関係ありません。

AI 工程路线图 2026 🚀 | 从零构建并部署 AI 应用。AI Engineering Roadmap 2026 🚀 | Build & Deploy AI Apps from Scratch

BuyWhere agent-native 商品目录 APIBuyWhere agent-native product catalog API

Amadeus（来自《Steins;Gate 0》的 AI 助手）适配 DeepSeek Harness。Amadeus (AI assistant from Steins;Gate 0) for DeepSeek Harness

AgentServices — AI Agents 的 Premium APIs。加密数据、营销情报、争议解决。基于 Base 的 x402 micropayments。AgentServices — Premium APIs for AI Agents. Crypto data, marketing intelligence, dispute resolution. x402 micropayments on Base.

🧠 Ultimate AI Coding Agent 2026：全面提速开发流程，写出更快、更干净的代码。🧠 Ultimate AI Coding Agent 2026: Supercharge Your Dev Workflow for Faster, Cleaner Code

讀論文時把疑問就地註記回原文，累積成可複習的筆記與單頁 HTML — a Claude Code plugin for annotating papers with your own questions.

E-Code——借助 AI Agent 构建、发布并扩展全栈应用。E-Code — build, ship and scale full-stack apps with AI agents

面向 B5G/6G NOMA RIS/STARS 无线通信研究的 IEEE 规范学术写作、润色与评审 Agent Skills。IEEE-compliant academic writing, polishing, and reviewing Agent Skills — tailored for B5G/6G NOMA RIS/STARS wireless communications research.

部署一支完整的 AI 工程团队 2026——带自动化质量 Hook 的 Claude 12-Agent 系统。Deploy a Full AI Engineering Team 2026 - Claude 12-Agent System with Automated Quality Hooks

一个只读 MCP 服务器，根据研究问题或参考图像，为 Claude 和 Codex 推荐真实可复现的 R/Python 科学图表案例。Read-only MCP server that recommends real, reproducible R/Python scientific figure cases to Claude and Codex — by research question or reference image.

本地优先、由 LLM 驱动的系统文献综述 (SLRs) 平台，以人机协同方式自动完成筛选与提取Local-first, LLM-powered platform for Systematic Literature Reviews (SLRs)—automating screening and extraction with human-in-the-loop precision.

codegraph 是一个 local-first 的代码上下文引擎和面向代码仓库的 MCP server。它将源代码增量索引到轻量级 SQLite 图中，然后提供高信噪比的 tools，支持符号查找、调用图遍历、影响分析、相关测试发现和语义搜索。使用 Go 构建，单二进制工作流，专为……而设计。codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work

Claude Code 学术写作框架：通过模式门控的 Agent 工作流，确保全文引用可核验、改写忠于原意、并保持作者风格Claude Code framework for academic writing: verified full-text citations, scope-faithful paraphrase, and voice preservation, enforced by a mode-gated agent workflow

"生物信息学分析揭示 COVID-19 mRNA 疫苗与自然 SARS-CoV-2 变异株之间的人工密码子偏好变化"。SARS-CoV-2、COVID-19、vaccine、codon-optimization、bioinformatics、sequence-analysis、mRNA-vaccine、origin-analysis、reproducible-research。"Bioinformatics analysis revealing artificial codon preference changes in COVID-19 mRNA vaccines vs natural SARS-CoV-2 variants" SARS-CoV-2, COVID-19, vaccine, codon-optimization, bioinformatics, sequence-analysis, mRNA-vaccine, origin-analysis, reproducible-research

面向 Festo/CODESYS PLC 工程的 MCP server——生成 IEC 61131-3 Structured Text 与经过校验的 PLCopen XML，内置知识库（27 个主题、19 份手册、BM25 检索）以及一个 38 个块的 ST 库。MCP server for Festo/CODESYS PLC engineering — generates IEC 61131-3 Structured Text and validated PLCopen XML, with an embedded knowledge base (27 topics, 19 manuals, BM25 search) and a 38-block ST library.

面向 Butterfly Labs BF0005G Jalapeno SHA-256 ASIC 的工具包——包含协议层、统计分析、NIST SP 800-22 随机性测试与迭代哈希动力学；将退役矿机改造为硬件密码学研究平台，同时也可用作酸面种发酵加热器Toolkit for the Butterfly Labs BF0005G Jalapeno SHA-256 ASIC — protocol layer, statistical analysis, NIST SP 800-22 randomness tests, and iterated-hash dynamics. Repurposes a retired miner as a hardware cryptographic research platform, and sourdough starter warmer.

Webasyst MCP Server 2026：面向应用、插件与主题的 AI 工具。Webasyst MCP Server 2026: AI Tools for Apps, Plugins & Themes

AI 驱动的学术与职业助手，帮助留学生优化简历、学术写作与研究申请An AI-powered academic and career assistant designed to help international students improve resumes, academic writing, and research applications.

Cold email MCP server + agent-native 发送基础设施 — 完全由你的 coding agent（Claude Code / Codex / Cursor）运行。一个 token，17 个 MCP tools + CLI：品牌域名、邮箱、预热、序列、回复。内测中。Cold email MCP server + agent-native sending infrastructure — run entirely by your coding agent (Claude Code / Codex / Cursor). One token, 17 MCP tools + CLI: branded domains, mailboxes, warmup, sequences, replies. Early access.

基于 ESP32-P4（SeedSigner 生态）的无状态安全引导加载器分阶段开发，从文献综述起步，依次完成安全启动、SD 卡载荷加载、Specter bundle 验证以及反钓鱼加固。Phase-by-phase development of a stateless secure bootloader for ESP32-P4 (SeedSigner ecosystem) from literature review to secure boot, SD card payload loading, Specter bundle verification, and anti-phishing hardening

本仓库用于存放系统综述 "Colour, Congruence, and Customisation: A Systematic Review of Purchase Intention in Online Fashion Retail" 的全部补充材料This repository is responsible for holding all the additional materials related to the systematic literature review titled: "Colour, Congruence, and Customisation: A Systematic Review of Purchase Intention in Online Fashion Retail"

在你信任它们的静默之前，先证明它们仍然看得见的 hook。为你的编码 Agent 编写的检测器提供配对的正/负对照。Hooks that prove they can still see before you trust their silence. Paired positive/negative controls for the detectors your coding agent writes.

这是一个个人日志/日记/知识库，集成本地部署的聊天机器人，统一追踪我想要追踪的任何内容。This is a personal journal / diary / knowledge base integrating a locally served chatbot to cohesively track whatever I want it to track.

项目一：竞赛团队——面向异质性乳腺癌的逻辑门控药物递送，竞赛撰稿进行中。项目二：两种蛋白之间的通用 RNA Linker，融合蛋白质粒进入第二轮设计迭代。项目三：基于 RNA 核糖开关的金属检测，启动全细胞生物传感的文献综述。Project 1: Competition Team - Logic-gated Drug Delivery for Heterogeneous Breast Cancer Competition Writeups underway Project 2: Generic RNA Linker between two proteins Plasmids for fusion proteins are in second round of design iterations Project 3: Metal Detection using RNA Riboswitch Beginning Literature Review for whole cell bio-sensing

文献引用管理器，作为学士学位论文的一部分开发Bibliographic citation manager, that was created as a part of a Bachelor's thesis

面向自由职业学术写作/编辑服务的市场与客户接入站点，集成 Zod 校验的联系表单。Marketing and client-intake site for freelance academic writing/editing services, with a Zod-validated contact form.

DHBW 论文模板。Template for DHBW thesis

一款 agentic 的链上行为分析应用，帮助加密货币交易者理解其最大亏损究竟是来自判断错误，还是来自未能长期坚持正确判断。An agentic on-chain behavioral analysis app that helps crypto traders understand whether their biggest losses came from being wrong — or from not staying right long enough.

自托管 YouTube MCP server：搜索、字幕、帧、评论，以及本地语义语料库。Self-hosted YouTube MCP server: search, transcripts, frames, comments, and local semantic corpora.

对 5 项真实新冠疫苗三期临床试验（Pfizer、Moderna、AstraZeneca、J&J、Novavax）进行统计分析，基于公开病例数据计算疫苗有效率与置信区间，与同行评审结果交叉验证，并附带 meta 分析与交互式仪表盘Statistical analysis of 5 real COVID-19 vaccine phase 3 trials (Pfizer, Moderna, AstraZeneca, J&J, Novavax) - computes vaccine efficacy and confidence intervals from published case data, validated against peer-reviewed results, with a meta-analysis and interactive dashboard.

AI 驱动的研究助手，自动检索、分析、总结、评审并格式化学术论文，生成带 APA 引用与 PDF 输出的结构化系统文献综述AI-powered research assistant that automatically searches, analyzes, summarizes, reviews, and formats academic research papers into structured systematic literature reviews with APA citations and PDF output.

用于系统综述检索的交互式工具：PICO 构建器、数据库语法转换器与邻近算子构建器。Interactive tools for systematic review searching: PICO builder, database syntax converter, and proximity-operator builder.

面向开源库的机器可读错误知识库——MCP server、REST API 与静态数据集，将每条错误消息映射到抛出该错误的源代码行。Machine-consumable error knowledge base for open-source libraries — MCP server, REST API, and static dataset mapping every error message to the source line that raised it

2026 年 21-Agent 病毒式发布流水线——从 AI 研究到多渠道分发。21-Agent Viral Launch Pipeline 2026 – AI Research to Multi-Channel Delivery

受治理的、与 provider 无关的运行时，面向证据驱动的自主软件工程、研究和数据分析工作流。Governed, provider-neutral runtime for evidence-driven autonomous software engineering, research, and data-analysis workflows.

面向研究的 Skill 定义精选集合，覆盖文献综述、证据综合与研究空白分析；汇总多个社区驱动的 Skill，便于在 Codex 或 Copilot 工作流中对比、审阅与按需安装A curated collection of research-focused skill definitions for literature review, evidence synthesis, and research-gap analysis. It brings together multiple community-driven skills so they can be compared, reviewed, and selectively installed for use in Codex or Copilot workflows.

使用 OpenAI Python SDK 嵌入开发者工具文档并对查询匹配进行排序。Embed developer-tool documents and rank query matches with the OpenAI Python SDK.

整合 Web 上的免费金融数据。Unifies free financial data of the web

完整的 S&P 500 质量评分项目：数据采集与剖析、修正板块/子行业错配、清洗异常值与缺失值、将 5 项指标归一化为综合得分、回答全部 4 个研究问题，并搭建交互式 Power BI 仪表盘Complete S&P 500 Quality Score project: sourced and profiled data, fixed the sector/sub-industry mismatch, cleaned outliers and missing values, normalized 5 metrics into a composite score, answered all 4 research questions, and built an interactive Power BI dashboard.

不要再重复解决同一段代码——一个本地优先的分布式推理缓存：来自真实环境的匿名兼容性证据，加上面向编码 LLM 的已验证最小示例。Stop solving the same code twice — a local-first distributed reasoning cache: anonymous compatibility evidence from real environments plus verified minimal samples for coding LLMs.

一个由 AI 驱动的科研情报平台，利用 LLM 和现代 NLP 技术，实现语义搜索、基于 RAG 的问答、文献综述生成、研究空白检测、知识图谱构建、引文管理以及科研写作辅助。An AI-powered Research Intelligence Platform that enables semantic search, RAG-based question answering, literature review generation, research gap detection, knowledge graph construction, citation management, and scientific writing assistance using LLMs and modern NLP techniques.

AI Coding Memory MCP 2026：用于持久化 Sprint 与决策管理的 20 个工具。AI Coding Memory MCP 2026: 20 Tools for Persistent Sprint & Decision Management

多 Agent AI 研究助手——由多个专门化 Agent 协作，自动检索论文、总结发现、对比方法、生成文献综述并产出可演示的内容Multi-Agent AI Research Assistant — An AI-powered research automation system where multiple specialized agents collaborate to search research papers, summarize findings, compare methodologies, generate literature reviews, and create presentation-ready content.

Subconscious Memory 2026：基于混合语义搜索与 MCP 的 AI 编码上下文引擎。Subconscious Memory 2026: AI Coding Context Engine with Hybrid Semantic Search & MCP

Quarto 文档模板：符合英国文档标准的简洁专业 PDF 与 HTML 输出Quarto document template: clean professional PDF and HTML output per UK document standards

Markdown 学术写作工作流：一篇以 Markdown 纯文本示例论文阐述写作流程，同时作为学习与脚手架项目。Markdown Academic Writing Workflow, an example paper talking about the writing workflow with Markdown plain text file, served as a learning and a scaffolding project at the same time.

使用纯 C 从零构建 LLM 推理引擎，不依赖任何框架。Build an LLM inference engine from scratch in pure C with no frameworks.

对 LLM 文献筛选方法的受控双研究对比——RAG 与 zero-shot、自适应与被动选文——并以真实系统综述的真值标注进行评估。Controlled two-study comparison of LLM-based literature screening methods — RAG vs. zero-shot, and adaptive vs. passive paper selection — evaluated against real systematic review ground truth.

一个用于自动化文献综述、论文摘要和引文映射的多 Agent AI 系统。A multi-agent AI system for automated literature review ,paper summarization, and citation mapping.

涵盖 RAG、AI Agent、评估与商业智能的实战 AI 应用项目集。Practical AI application projects across RAG, AI agents, evaluation, and business intelligence.

40 项检查的设计契约验证引擎 — 为任意 URL 评分，把控 CI，强制执行 DTCG 2025.10 tokens。MCP server + GitHub Action + stylelint plugin + CLI。40-check design contract verification engine — score any URL, gate your CI, enforce DTCG 2025.10 tokens. MCP server + GitHub Action + stylelint plugin + CLI.

Measured by Nova：本地空间重建 MCP server，用于构建物理上精确的 Blender 模型。Measured by Nova: local spatial reconstruction MCP server for physically accurate Blender models.

适用于 macOS 的 local-first 语音+手势 AI 存在。唤醒词 → Whisper → 三层路由 → Claude Agent SDK + MCP，带有 kill switch、设备级 allowlist、声纹门控确认和完整的操作日志。Local-first voice + gesture AI presence for macOS. Wake word → Whisper → three-tier router → Claude Agent SDK + MCP, behind a kill switch, device-scoped allowlist, voiceprint-gated confirmation and a full action log.

Thesis Helper：面向学术研究的自动化统计分析 Web 应用。上传数据集即可即时生成描述性统计、相关性分析、回归和 t 检验，无需编写代码。Thesis Helper: An automated statistical analysis web app for academic research. Upload your dataset and instantly generate descriptive stats, correlations, regressions, and t-tests without coding.

使用部署在 streamlit 上的 MCP server 构建的旅行 Agent。A Travel Agent Built using a MCP server which is deployed in streamlit

立场论文：编码 Agent 需要对代码库决策的显式建模，而不仅仅是结构建模。Position paper: coding agents need an explicit model of codebase decisions, not just structure"

Local-first 可视化任务图，使人类与 AI Agent 在目标、进度、推理与下一步行动上保持对齐。Local-first visual task graph that keeps humans and AI agents aligned on goals, progress, reasoning, and the next action.

Zhixin Li 的学术主页：超声医学、医学影像 AI、多模态学习与可复现研究。Academic homepage of Zhixin Li: ultrasound medicine, medical imaging AI, multimodal learning, and reproducible research.

Fiberarticle 是一个 Agentic AI，可自主开展研究、执行文献综述并撰写可发表级的论文Fiberarticle is an Agentic AI that researches, performs literature reviews, and writes publication-ready article papers.

本项目根据用户检索与数据集中已有论文进行论文推荐This project recommends paper based upon your search and available papers inside the dataset

基于 LangGraph、Ollama 与 RAG 的可追溯多智能体医疗辅助分诊系统

2026 年面向 AI 代码生成的 PostgreSQL 优化终极指南。The Ultimate guide to PostgreSQL Optimization for AI Code Generation in 2026

一组科学与医学写作样例集合，包括通俗摘要、论文风格写作和临床摘要。A portfolio of scientific and medical writing samples, including lay summaries, manuscript-style writing, and clinical summaries.

用自然英语描述一个零件，即可获得完全可编辑的参数化 Fusion 360 模型。LLM 针对 28 个类型化 CAD 端点生成经过校验的 JSON feature 方案，通过 MCP server 与 Fusion 360 插件执行。附带 mock 后端，无需安装 CAD 即可运行。Describe a part in plain English, get a fully editable parametric Fusion 360 model. An LLM emits a validated JSON feature plan against 28 typed CAD endpoints, executed through an MCP server and a Fusion 360 add-in. Ships a mock backend so it runs with no CAD install.

基于 MCP 的实时来源声明与引用验证，支持 FIGI 解析与签名投递回执。Live-source claim and citation verification over MCP, with FIGI resolution and signed delivery receipts.

专注于通过统计分析与机器学习模型检测金融欺诈的数据科学研究项目。Data science research project focused on detecting financial fraud through statistical analysis and machine learning models.

基于 n8n 构建的多 Agent AI 研究助手——输入主题后自动规划研究问题、检索网络并生成完整报告；由 Groq (Llama 3.3) + Tavily 驱动Multi-agent AI research assistant built with n8n — takes a topic, plans research questions, searches the web and generates a full report automatically. Powered by Groq (Llama 3.3) + Tavily.

面向 CLI 编码 Agent 的桌面工作空间。可并行运行 Claude Code、Codex、OpenCode 和 Gemini CLI——每个任务使用独立的 git worktree。MIT 协议，local-first，无遥测。A desktop workspace for CLI coding agents. Run Claude Code, Codex, OpenCode and Gemini CLI side by side — each task in its own git worktree. MIT, local-first, no telemetry.

用于 in-loop 设计审查的远程 MCP server，以及 OAuth 2.1 鉴权、SSRF 安全的 URL 处理、通过 MCP 执行长时任务的实践参考。A remote MCP server for in-loop design review, and a worked reference for OAuth 2.1 auth, SSRF-safe URL handling, and long-running jobs over MCP.

AI 驱动的加密情绪日记——基于 RAG 的 LLM 反馈（TAIDE + ChromaDB）结合 Random Forest 情绪预测。Live demo：heartbox.tw（test1/test1）。AI-powered encrypted mood journal — RAG-grounded LLM feedback (TAIDE + ChromaDB) and Random Forest emotion forecasting. Live demo: heartbox.tw (test1/test1)

将任意代码库转化为学术论文（Typst、LaTeX、PDF 与 WebPaper HTML）。提供标准库 Python CLI + Claude Agent Skill。Turn any codebase into an academic paper (Typst, LaTeX, PDF & WebPaper HTML). Stdlib Python CLI + Claude Agent Skill.

系统综述与验证的质量模板——扩展 Consultant 角色原型。Quality template for systematic review and validation - Extends Consultant archetype