趋势榜

DeepSeek Harness (dsh) 插件精选列表 · DeepSeek Harness 插件精选列表。A curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表

DeepSeek Harness (DSH) Web UI 的插件与皮肤合集——任务板、git graph、右侧面板、远程移动端 UI、宠物、实时 token 统计与皮肤中心。Plugin and skin collection for DeepSeek Harness (DSH) Web UI - task board, git graph, right-side panel, remote mobile UI, pet, live token stats, and skin center.

开源 AI 研究工作台，搭载 scientific agents，专注于可复现的研究与发现。Open-Source AI research workbench with scientific agents for reproducible research and discovery.

DSH 官方公众号收录的 TUI 补位插件：Claude Code 风，鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plugin — Claude Code style: whale bar, live status, streaming thoughts, double-Esc rollback, context bar + TPS. npm one-click.

Grok Bot 的开源替代方案，提供 bot 可调用的虚拟机。Open Source Alternative to Grok Bot with a virtual machine that bots can use

基于 Next.js、LangChain、PostgreSQL + pgvector 构建的 AI 驱动的初创企业加速引擎。可上传、组织并与文档对话。包含预测性缺失文档检测、基于角色的工作流以及页面级洞察提取。AI-powered StartUp Accelerator Engine built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workflows, and page-level insight extraction.

DeepSeek Harness (DSH) 生态：来自 dsh-external/hub 与公开 dsh-plugin 主题的精选插件、工具与基础设施。DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.

Athena 是一个本地优先的 agentic PKM，借助你自己的上下文帮助你做出更优决策——持久记忆、结构化推理，以及跨任意 LLM 工作的受治理 AI agent。拥有状态，租用智能。Athena is a local-first agentic PKM that helps you make better decisions with your own context — persistent memory, structured reasoning, and governed AI agents that work across any LLM. Own the state. Rent the intelligence.

开源 Agent 记忆。Opensource Memory for Agents

DeepSeek Harness (dsh) 从 0 到 1 深度手册：安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比（中文 + 英文 PDF）

DeepSeek Harness 的桌面应用Desktop app for DeepSeek Harness

DSH 官方尚无终端 TUI 的补位之作：Claude Code 风格全屏交互终端插件——像素鲸鱼顶栏、实时工作状态行、思考流式展开、双击 Esc 回滚、上下文进度条 + TPS 仪表。npm 一键安装。

本地优先、自托管的媒体下载器，基于 yt-dlp、Flask、Docker 和 ffmpeg。Local-first, self-hosted media downloader powered by yt-dlp, Flask, Docker, and ffmpeg.

面向 AI 网页聊天 [Claude|ChatGPT|Grok...] 的自定义 MCP [Connector]，直接在电脑上使用文件和 ShellCustom MCP [Connector] for AI chat web [Claude|ChatGPT|Grok...] use Files/Shell on your computer directly

SillyTavern 迁移与面向 DSH 的下一代 Agent RP。SillyTavern migration and next-generation Agent RP for DSH

通过 AuthSwap 实现 Windows Codex Desktop 多账号。共享工作区，独立的 ChatGPT 登录。Windows Codex Desktop multi-account via AuthSwap. Shared workspace, separate ChatGPT logins.

🪢 Langfuse API 的自动生成 Java 客户端。🪢 Auto-generated Java Client for Langfuse API

一个轻量级把HTML静态文件（含SPA项目build的产物）打包成exe可执行文件的项目，打包机无需安装cli脚手架，也无需安装rust、tauri等框架。

一个 LLM 相关论文、学位论文、工具、数据集、课程与基准的合集。A collection of LLM related papers, thesis, tools, datasets, courses, benchmarks

repo-map 生成由 LLM 增强的软件仓库摘要与分析，为开发者提供关于项目结构、文件用途以及跨编程语言潜在考量的洞察。repo-map generates LLM-enhanced summaries and analysis of software repositories, providing developers with valuable insights into project structures, file purposes, and potential considerations across various programming languages.

ICLR 2026 Oral 论文 "Q-RAG: Long Context Multi-Step Retrieval via Value-Based Embedder Training" 的官方仓库。Official repository for the ICLR 2026 Oral Paper🔥 “Q-RAG: Long Context Multi-Step Retrieval via Value-Based Embedder Training”

一站式 DeepSeek Harness 社区发行版：TUI、桌面端与 Web UI 三种形态统一体验，支持分层安装、一步到位，免去手工整合打包。

MatlowAI 的 MiniMax-H3 ComfyUI 节点：Contact-Sheet diffusion + Motion Lab（针对快速运动的 test-time 去绳状畸变）MatlowAI's MiniMax-H3 ComfyUI nodes: Contact-Sheet diffusion + Motion Lab (test-time de-roping of fast motion)

通过自然语言接口提供空间转录组学分析的 MCP server。MCP server for spatial transcriptomics analysis through natural language interfaces.

开源 AI Workforce OS：将 AI Agent 转化为执行业务职能、以结果衡量的自主劳动力。Claude Tag 的开源替代方案。The Open-Source AI Workforce OS. Turn AI agents into autonomous labor that performs business functions and is measured by outcomes. Claude Tag open source alternative

面向 agent 的纯数学工具：搜索实例与反例，进行精确计算，并独立验证结论所证内容。Pure mathematics for agents: search for examples and counterexamples, compute exactly, and independently check what a result proves.

自托管的开发机 OS——通过 Tailscale 在单一面板上提供应用管理、AI agent 编排、数字孪生、第二大脑与创意流水线。Self-hosted dev machine OS — app management, AI agent orchestration, digital twin, second brain, and creative pipeline from a single dashboard over Tailscale

可自托管的 Agentic OS：通过签名插件构建、运行与审计多 Agent AI 团队。自带 LLM key，数据完全自有，符合 EU/GDPR 要求。Self-hostable agentic OS. Build, run & audit multi-agent AI teams from signed plugins. Bring your own LLM key, own all your data, EU/GDPR-ready.

欧洲议会 MCP Server——为 AI agent 提供政治情报。European Parliament MCP Server - Political intelligence for AI agents

用于评估 Agentic AI 应用的 AI 红队工具与 LLM 安全框架，测试 prompt injection，支持漏洞评估、SBOM 生成与静态分析。AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

别再同时处理太多事，开始真正把事做完。GSD Task Manager 让你可以轻松把待办按"紧急"和"重要"分类，从而在不至于精疲力竭的情况下把事情搞定。简单直观、完全离线运行。Stop juggling, start finishing. GSD Task Manager makes it easy to sort your to-dos into what’s urgent and what’s important, so you can finally get stuff done without burning out. It’s simple, visual, and works entirely offline.

可复现研究仓库的 GitHub 模板 —— 两层 Python 3.10+/uv monorepo，将通用基础设施与项目级代码分离，配有 pytest 覆盖率门禁（基础设施 60%、项目 90%）、16 阶段构建流水线、通过 pandoc/LaTeX 实现的 Markdown 转 PDF 渲染，以及 25 个标准示例。GitHub template for reproducible research repos — two-layer Python 3.10+/uv monorepo splitting generic infrastructure from per-project code, with pytest coverage gates (60% infra, 90% projects), a 16-stage build pipeline, markdown-to-PDF rendering via pandoc/LaTeX, and 25 canonical exemplars.

Brilliant Directories 官方 MCP 服务器 —— 可从任何 AI Agent 管理会员、帖子、线索、评论、页面等。附带 OpenAPI 3.1 规范。Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, pages, and more from any AI agent. OpenAPI 3.1 spec included.

面向 AI agent 的基于证据的评估——将每条断言与 agent 真实工具输出进行核对（受约束、基于证据的模型判断，而非整体式 LLM 评判的猜测），并附带置信区间。Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model judgment, not holistic LLM-judge guesswork), with confidence intervals.

FlexEval 是一个面向实际量化分析的 LLM 评估工具。FlexEval is an LLM evaluation tool designed for practical quantitative analysis.

连接 Suunto 手表数据到 Claude 及其他 AI 助手的 MCP server。MCP server that connects your Suunto watch data to Claude and other AI assistants

一个强大且高效的浏览器 agent，可自动化完成网页上的任何任务。A powerful & efficient browser agent that automates any task on the web

内容后端，具备类型化生命周期强制、MCP-native API 和零运行时依赖。自托管、开源。Content backend with typed lifecycle enforcement, MCP-native API, and zero runtime dependencies. Self-hosted. Open source.

一个单文件引导程序，帮助编程 agent 跨会话与上下文窗口执行长周期任务。A one-file bootloader that helps coding agents execute long-horizon projects across sessions and context windows.

墨西哥开放法律情报：覆盖联邦、州、市三级来源的 3 万+ 部法律 · 350 万+ 可检索条文 · 三语界面（西班牙语 · 英语 · 古典纳瓦特尔语）· 一方 RAG 聊天 · OpenAPI + SDK · 为市民、会计师、律师与 AI Agent 像代码一样导航墨西哥法律。Open legal intelligence for Mexico. 30,000+ laws across federal, state, and municipal sources · 3.5M+ searchable articles · trilingual UI (Spanish · English · Classical Nahuatl) · first-party RAG chat · OpenAPI + SDKs · built so citizens, accountants, lawyers, and AI agents can navigate Mexican law as code.

2026 年 5 款最佳免费 OpenClaw Android AI Agents——免 Root 全 Linux。5 Best Free OpenClaw Android AI Agents 2026 – No Root Full Linux

论文 PDF 知识提取与学术写作 — Claude Code PluginPaper PDF Knowledge Extraction and Academic Writing – Claude Code Plugin

Codex 的主题画廊、预览器、构建器与社区。The theme gallery, previewer, builder, and community for Codex.

Spring AI 的隐私护栏：跨模型/工具调用的请求作用域 PII 令牌化与最小特权披露，基于 Presidio 与 JVM 本地 OpenNLP。Privacy guardrails for Spring AI: request-scoped PII tokenization and least-privilege disclosure across model/tool calls, with Presidio and JVM-local OpenNLP.

C++ AI Agent like langgraph. 支持嵌入普通 app 中辅助实现ai功能

本地优先、可审计的技术文档与源代码知识编译器。Local-first, auditable knowledge compiler for technical docs and source code

独立 Go 守护进程，将 Homematic / HomeMatic IP CCU 桥接到 MQTT（支持 Home Assistant Discovery），提供 REST + WebSocket API、MCP 服务器、Svelte 配置 UI 以及原生 Matter 桥接 —— 多 CCU、单一静态二进制。Standalone Go daemon bridging Homematic / HomeMatic IP CCUs to MQTT (with Home Assistant Discovery), a REST + WebSocket API, an MCP server, a Svelte config UI, and a native Matter bridge — multi-CCU, single static binary.

遵循中文学术写作规范的学术 humanizer。Fork 自 AIScientists-Dev/academic-humanizer。Academic humanizer with Chinese academic writing rules. Fork of AIScientists-Dev/academic-humanizer.

系统综述与论文清单：探索面向代码的 LLM 中数据与代码质量问题的映射、检测与治理。Systematic review and paper list exploring the mapping, detection, and governance of data and code quality issues in Large Language Models for Code.

自托管 AI 知识 Agent —— TypeScript、Bun、MCP。掌控你的数据，运行你自己的大脑。Self-hosted AI knowledge agent — TypeScript, Bun, MCP. Own your data, run your own brain.

面向 AI 编码 Agent 的 IDE 智能，集成 LSP 语义、tree-sitter 索引、项目记忆和并发安全编辑。IDE intelligence for AI coding agents, with LSP semantics, tree-sitter indexing, project memory, and concurrency-safe edits.

面向 AI Agent 与软件服务的去中心化自主 Agent 商务中枢。Decentralized Autonomous Agent Commerce Hub for AI agents and software services.

精选实用 Agent Skill 列表，覆盖 Claude Code、Codex、Gemini CLI、OpenClaw、Hermes 等 AI Coding Agent。A curated list of useful Agent Skills for Claude Code, Codex, Gemini CLI, OpenClaw, Hermes, and other AI coding agents.

硕士论文（UiB，计算语言学，2023）及扩展工作。针对系统综述筛选的文本分类。原始 11 工作流分析结合 NEO ontology 集成，以及 Cohen 等人（2006）药物类别基准的扩展，比较 BoW 与 BiomedBERT。Master's thesis (UiB, Computational Linguistics, 2023) and extension work. Text classification for systematic review screening. Original 11-workflow analysis with NEO ontology integration plus Cohen et al. (2006) drug-class benchmark extension comparing BoW and BiomedBERT.

使用 ConsensusMind 这一自主 AI Agent 对区块链共识机制进行全面深入的研究，涵盖文献综述、模拟与学术写作。🤖 Conduct thorough research on blockchain consensus mechanisms with ConsensusMind, an autonomous AI agent for literature review, simulations, and academic writing.

面向 Node 与浏览器的 AI 数据库对话：用自然语言提问、审视查询、获取答案。支持 Postgres、MySQL、SQLite、DuckDB、Oracle、MongoDB。具备只读 AST 守卫、React UI、MCP server、VS Code 与 JetBrains 集成。AI database chat for Node and the browser: ask in plain language, review the query, get answers. Postgres, MySQL, SQLite, DuckDB, Oracle, MongoDB. Read-only AST guard, React UI, MCP server, VS Code & JetBrains.

用知识图谱刻画 AI/ML 模型从创建到部署的完整生命周期。Knowledge Graph to capture AI/ML model lifecycle from creation through deployments.

基于 LlamaIndex、Redis 与 PII 脱敏的 RAG 搜索引擎。RAG search engine using LlamaIndex, Redis, and PII masking.

EveryAPI CLI：Claude Code / Codex / Gemini CLI 集成 + MCP server。EveryAPI CLI: Claude Code / Codex / Gemini CLI integration + MCP server

一个面向 PDF 文档问答的全栈 RAG 应用：上传 PDF，将其索引到本地向量库，然后基于页面级答案进行对话，并在内置阅读器中通过可点击引用跳转到对应页面。A full-stack retrieval-augmented generation (RAG) application for question answering over PDF documents. Upload a PDF, index it into a local vector store, then chat with page-grounded answers and clickable citations that jump to the right page in the built-in viewer.

每日论文推荐。daily paper recommendation

自托管、100% 本地的 AI 平台——在一个 Docker 栈中集成 LLM 推理、RAG 与知识图谱。无需 API key。Self-hosted, 100% local AI platform — LLM inference, RAG, and knowledge graphs in one Docker stack. No API keys.

面向 Canvas LMS 的 AI 辅助课程设计工具链 —— Curriculum Intelligence、Canvas Design Studio 和 Command & Control MCP 服务器，附带原生安装器和插件模块架构。AI-assisted course design toolchain for Canvas LMS - Curriculum Intelligence, Canvas Design Studio, and Command & Control MCP servers, with a native installer and plug-in module architecture.

语义优先的 Codex skill，用于可审计的 BERTopic 调参、主题解释、模型比较与可复现研究交付。Semantic-first Codex skill for auditable BERTopic tuning, topic interpretation, model comparison, and reproducible research delivery.

面向 Claude Code 的跨源学术文献扫描 skill：并行检索 OpenAlex / Semantic Scholar / arXiv / Perplexity，进行确定性去重，并整合为一份带引用的共识报告。Cross-source academic literature scan skill for Claude Code: fans out to OpenAlex / Semantic Scholar / arXiv / Perplexity, dedupes deterministically, reconciles into one cited consensus report.

一本关于生产级 RAG 与 agentic 系统的实用第一性原理手册，支持 RU/EN/SK，基于 Docusaurus 构建。A practical, first-principles handbook on production RAG & agentic systems — RU/EN/SK, built with Docusaurus.

由一名高中应届毕业生借助 AI 开发的、可定制个人知识库的 AI Agent。An AI agent that customizes your knowledge base, created by a graduated high school student using AI

为 MI Tech Arsenal 定制的基于 RAG 的 AI 助手，具备自动化 sitemap 索引、通过 ChromaDB 进行神经搜索，以及 Streamlit 到 Blogger 的无缝集成。A custom RAG-based AI assistant for MI Tech Arsenal. Features automated sitemap indexing, neural search via ChromaDB, and a seamless Streamlit-to-Blogger integration.

Logic Writing：面向 Codex 的证据驱动调查与学术写作编排。Logic Writing: evidence-first investigation and academic writing orchestration for Codex

开源的全流程演示文稿平台——构建、演示、发布与协作。自托管、原生支持 MCP、完全可定制主题。The open-source, end-to-end presentation platform - build, present, publish, and collaborate. Self-hosted, MCP-native, fully themeable.

bibsync 从 LaTeX 源文件中的引用键同步 BibTeX 文件。灵感来自 adstex，支持 NASA ADS 和 InspireHEP 作为数据源。bibsync synchronizes BibTeX files from citation keys in LaTeX sources. It is inspired by adstex, with provider support for both NASA ADS and InspireHEP.

自托管 AI 新闻门户的 Agentic 控制层：一个标准库 Python CLI 加一个 MCP server（32 个工具），由 LLM agent 驱动，通过门控编辑流程撰写并发布 AI 人设文章，策展首页与作者，并完成部署。附带 prompt/skill 配方与 7×24 服务循环。Agentic control layer for the Censurado self-hosted AI news portal: a stdlib Python CLI plus an MCP server (32 tools) an LLM agent drives to write and publish AI-persona articles through a gated editorial walk, curate the front page and authors, and deploy. Ships the prompt/skill recipe and a 24/7 serve loop.

面向人文社科与 STEM 领域的领域感知学术写作、证据追踪、发布检查与 AI 使用披露。Domain-aware academic writing, evidence tracking, release checks, and AI-use disclosure for humanities, social sciences, and STEM.

一次扫描即可查看机器上所有与开发者和 AI 相关的内容 —— 一款原生 Tauri 应用，将开发 + AI 环境映射为可交互的架构图。See everything Developer- and AI-related on your machine in one scan — a native Tauri app that maps your dev + AI environment into an interactive architecture graph.

运行 UNITARES 的 Raspberry Pi —— 论文中引用的纵向测试平台。Raspberry Pi running UNITARES — longitudinal testbed cited in the papers.

证据门禁式 Coding Agent 编排器：冻结任务、独立验证、绑定摘要的评审、仅草稿可发布。Evidence-gated orchestration for coding agents: frozen tasks, independent verification, digest-bound review, draft-only publication. 证据门禁式 Coding Agent 编排器。

AI agent 沙箱的时间旅行调试——基于 Firecracker microVM，支持 record、snapshot、restore 与 diff，非容器方案。Time-travel debugging for AI agent sandboxes — Firecracker microVMs with record, snapshot, restore, and diff. Not containers.

硕士论文研究：使用 Terraform IaC、Atomic Red Team MITRE ATT&CK 模拟与 Python 统计分析，在 Microsoft Azure 中实证评估零信任架构（ZTA）与传统边界安全。Sheffield Hallam University 2026。MSc dissertation research: Empirical evaluation of Zero Trust Architecture (ZTA) vs conventional perimeter security in Microsoft Azure using Terraform IaC, Atomic Red Team MITRE ATT&CK simulations, and Python statistical analysis. Sheffield Hallam University 2026.

Researcher's Decision Pattern Matrix 仓库，一套用于辅助研究人员（硕士与博士）在选题、研究问题类型、研究设计与方法论方面做决策的文件集合。This is a repository an Researcher's Decision Pattern Matrix, a collection of files to assit researchers (MSc and PhD) in making decisions concerning topic selection, research question type, research design and methodology.

开源、自托管的 Claude Code 与 opencode 客户端。Agent 在你自己的 Linux 主机或 Mac 上的真实 tmux 中运行，可通过桌面、手机或浏览器经 HTTPS 远程操控。Open-source, self-hosted Claude Code and opencode client. Agents run in real > tmux on your own Linux box or Mac, and you drive them from desktop, phone or > browser over HTTPS.

关于 Riemann zeta 零点无条件低重数剖面的未经同行评审的研究，附精确证书，并清晰区分与 RH 相关的探索。不证明 RH。Unrefereed research on unconditional low-multiplicity profiles for Riemann zeta zeros, with exact certificates and clearly separated RH-adjacent explorations. Does not prove RH.

配套仓库：指数族模型主动感知文献综述Companion repository to a literature review on active sensing with exponential family models

为 https://pubmed.ncbi.nlm.nih.gov/ 创建第一阶段筛选表格的文献综述Create phase 1 screening spreadsheet literature review of https://pubmed.ncbi.nlm.nih.gov/

一个结合 Web 搜索与 API 增强的 Agent，用于构建研究论文知识图谱，突破文献综述瓶颈。An agent that combines web search and API enrichment to build a knowledge graph of research papers for literature review bottlenecks

面向 Voynich Manuscript 多尺度结构的可审计可复现研究。Audited reproducible research on multiscale structure in the Voynich Manuscript

为每一个 Coding Agent 提供统一的全局开发环境。One global environment for every coding agent.

本仓库记录了我通过对研究论文的结构化分析、文献综述以及对基因组学、转录组学、生物信息学和 AI 在生命科学中应用的笔记，对计算生物学的持续探索。This repository documents my ongoing exploration of computational biology through structured analyses of research papers, literature reviews, and notes on genomics, transcriptomics, bioinformatics, and AI applications in life sciences.

可复用的 Codex skills，涵盖文献综述、学术写作、数学推理、数值仿真以及可发表的图表。Reusable Codex skills for literature review, academic writing, mathematical reasoning, numerical simulation, and publication-ready figures.

Experimental Qwen3.5-derived 752M LLM：基于 Qwen3.5 的实验性 752M 参数 LLM，采用 CPT + SFT 两阶段流程，面向编码、技术推理与指令跟随。Experimental Qwen3.5-derived 752M LLM: a two-phase CPT + SFT pipeline for coding, technical reasoning, and instruction following.

项目名称：用于自动化文献综述与研究空白发现的自适应 AI 研究智能平台。Project Title: Adaptive AI Research Intelligence Platform for Automated Literature Review and Research Gap Discovery

有界研究 Agent：plan → retrieve → critique，具备步骤预算、执行轨迹、引用追溯与自由路径 UI，无需 API key。Bounded research agent: plan → retrieve → critique, step budgets, traces, citations, free-path UI. No API key.

Autonomous AI Algorithm Discovery Laboratory：一个有边界、可复现的研究平台，在固定算力预算下提出、实现、测试、拒绝、改进并报告 AI 系统的候选改进方案。Autonomous AI Algorithm Discovery Laboratory: a bounded, reproducible research platform that proposes, implements, tests, rejects, refines, and reports candidate improvements to AI systems under a fixed compute budget.

六个 Claude skills，覆盖写作、配图、润色、投稿与修改 Q1 期刊文章的全流程——其中一个可端到端运行 systematic review。适用任何领域、任何研究设计；采用拦截式 gate 而非堆砌式 checklist。Six Claude skills for writing, illustrating, polishing, submitting, and revising Q1 journal articles — including one that runs a systematic review end to end. Any field, any research design; gates that stop rather than checklists that sprawl.

一个研究问题，一套跨 BV-BRC、BRC Analytics、PDN、NIAID Data Ecosystem、NCBI 资源及其他参与仓库的协同计划。One research question, one coordinated plan spanning BV-BRC, BRC Analytics, PDN, the NIAID Data Ecosystem, NCBI resources, and other participating repositories.

推进并系统评估 BV-BRC Copilot，从研究问题和已发表方法生成、执行并复现生物信息学工作流。Advancing and systematically evaluating BV-BRC Copilot for generating, executing, and reproducing bioinformatics workflows from research questions and published methods.

基于 n8n、Groq（Llama 模型）、Node.js、React 和 PostgreSQL 构建的多 Agent AI 研究流水线。用户提交研究问题后，由规划 Agent 拆解，由专业的研究/技术/成本 Agent 并行调查，由事实核查 Agent 验证，最终合成为带来源的结构化报告。A multi-agent AI research pipeline built with n8n, Groq (Llama models), Node.js, React, and PostgreSQL. A user submits a research question, which is broken down by a planning agent, investigated in parallel by specialized research/technical/cost agents, verified by a fact-checking agent, and synthesized into a structured report with sources.

Persian IEEE LaTeX 文章模板，集成 GitHub Actions CI/CD。Persian IEEE LaTeX article template with GitHub Actions CI/CD.

基于机器学习的 Python 推荐系统。Machine Learning Based Recommendation System in Python

基于 IQ 信号、采用 STFT 频谱图、视觉模型、k-fold 训练与集成推理的多节点 RF 无人机识别可复现研究工具包。A reproducible research toolkit for multi-node RF drone identification from IQ signals using STFT spectrograms, vision models, k-fold training, and ensemble inference.

模块化的学术写作 skills 套件，面向 AI 辅助研究，覆盖摘要、引言、相关工作、方法、实验与结论，具备证据感知推理、引用核查、术语一致性以及 clean/audit 模式。A modular suite of academic writing skills for AI-assisted research, covering Abstract, Introduction, Related Work, Method, Experiments, and Conclusion with evidence-aware reasoning, citation checks, terminology consistency, and clean/audit modes.

本地 CLI，用于发现本地网络上的影子 MCP 服务器并审计认证状态。零遥测，纯本地。Local CLI to discover shadow MCP servers on your local network & audit authentication status. Zero telemetry, local-only.

一个使用 OpenAI function calling 和 DuckDuckGo 搜索的网络搜索与研究问题回答 AI Agent。An AI agent that searches the web and answers research questions using OpenAI's function calling and DuckDuckGo search.

适用于 preglobal 斯巴鲁车型带 EyeSight 的 ICBM（按键欺骗式 ACC 触发）— 已实车可用。全纵向控制仍是开放且未经证实的研究问题。ICBM (button-spoofed ACC actuation) for preglobal Subarus with EyeSight — live and working. Full longitudinal control is still an open, unproven research question.

🧪 实验性本地优先 RAG，附带桌面 GUI：将文档拖入文件夹即可对话聊天，内置 Ollama / fastembed / OCR / reranker。🧪 Experimental local-first RAG with desktop GUI — drop documents in a folder, chat with them. Ollama / fastembed / OCR / reranker built in.

可执行真实操作的 AI agent 层级——shell、GitHub、邮件、采购——以代码编写（非配置）的审批底线（Latch）作为门槛。零依赖。A hierarchy of AI agents that take real actions — shell, GitHub, email, purchases — behind an approval floor written in code, not configuration (Latch). Zero dependencies.

📚 用于采集开放获取学术期刊的 Python CLI（OpenAlex + Semantic Scholar + Crossref + Unpaywall）— 导出 Obsidian Markdown、CSV 并自动下载 PDF。为毕业论文文献综述而构建。📚 CLI Python untuk mengumpulkan jurnal akademik open-access (OpenAlex + Semantic Scholar + Crossref + Unpaywall) — export Markdown Obsidian, CSV, dan download PDF otomatis. Dibuat untuk literature review skripsi.

Semantic Search for Pi 2026：本地知识库与 AI 工具。Semantic Search for Pi 2026: Local Knowledge Base & AI Tool

全栈量化研究平台：因子分析、系统化策略回测、真实交易成本建模、滚动前推 ML 验证、投资组合风险分析与稳健性测试，基于美股日频数据。为可复现研究而构建——非实盘交易。Full-stack quantitative research platform for factor analysis, systematic strategy backtesting, realistic transaction-cost modeling, walk-forward ML validation, portfolio risk analytics, and robustness testing on daily U.S. equity data. Built for reproducible research—not live trading.

文献综述与参考文献。literature reviews and bibliographies

用于生物学研究问题的科学研究 Agent。Scientific Research Agent for biological research questions

ENGR 820 文献综述ENGR 820 literature review

一个真实场景下的多能力 AI Agent，可接收用户的研究问题，自主决策所需信息，调用工具/MCP，分析信息并产出结构化报告。A real world multi capability AI agent that can take a user's research question, decide what it needs, use tools/MCP, analyze information, and produce a structured report.

RISE Collective 是一个学术、研究、创新与专业咨询平台，支持学生、研究人员、学者和职业发展者。服务包括研究 & 发表、咨询 & 职业、项目 & 创新、学术写作、图书出版、留学支持与知识产权服务。RISE Collective is an academic, research, innovation, and professional advisory platform supporting students, researchers, academics, and aspiring professionals. Services include research & publication, consulting & careers, projects & innovation, academic writing, book publishing, study abroad support, and intellectual property services.

ZN 十年期国债期货与 6E 欧元外汇期货日内 VWAP 均值回归的系统研究，包括数据验证、统计分析、回测、Monte Carlo 模拟与实盘部署。Systematic research on intraday VWAP mean reversion in ZN Treasury and 6E Euro FX futures, including data validation, statistical analysis, backtesting, Monte Carlo simulation, and live deployment.

为将 MCP 服务器推向企业部署的团队提供的实用 MCP 就绪、安全与无状态迁移资源。Practical MCP readiness, security and stateless-migration resources for teams moving MCP servers toward enterprise deployment.

ABCD Study 屏幕媒介出版物的系统综述：检索、筛选与效应量审计。Systematic review of ABCD Study screen media publications: search, screening, and effect size audit

1C:EDT 内置的 MCP 服务器：为 AI Agent 提供对项目的语义访问 —— BSL 代码、元数据、校验和实时调试MCP-сервер внутри 1C:EDT: дает AI-агентам семантический доступ к проекту - код BSL, метаданные, валидация и живая отладка

Agentic RAG：回答前对每条引用与原文进行核对，证据不足时弃答。具备自纠正检索循环、确定性引用锚定以及 prompt injection 防御能力。Agentic RAG that verifies every citation against source text before answering, and abstains when the evidence does not hold. Self-correcting retrieval loop, deterministic citation grounding, prompt-injection defence.

Hirdaramani Apparel Ltd 关于工作-生活平衡与员工生产力的研究，使用 R 进行统计分析、回归与 ANOVA。Research study on work-life balance and employee productivity at Hirdaramani Apparel Ltd, using R for statistical analysis, regression, and ANOVA.

系统综述数据分析仓库：基于机器学习技术的自闭症谱系障碍儿童情绪识别Data analysis repository for systematic literature review on emotion recognition in childrens with Autism Spectrum Disorder using machine learning techniques

Download consensus ai，可在数秒内从科学论文中获取有证据支撑的答案。面向学生、临床工作者与好奇读者，Consensus 将复杂研究转化为清晰、带引用的洞察，是值得信赖的共识研究工具，助力更快文献综述与更明智决策。Download consensus ai to find evidence-backed answers from scientific papers in seconds. Built for students, clinicians, and curious readers, Consensus turns complex studies into clear insights with citations, making it a trusted consensus research tool for faster literature review and smarter decisions.

CUMCM 数学建模 AI skill 包：选题、模型选择、论文写作、陷阱清单。3 年竞赛经验CUMCM math modeling AI skill pack: problem selection, model choice, paper writing, trap list. 3 years of contest experience

ORR – 开放与可复现研究：实践与工具。ORR – Open and reproducible research: practices and tools

尽享我的平台！My Platform enjoy!

面向 LLM Agent 的确定性写入时记忆整合与预取召回：采用本地模型，召回路径与整合决策中均不含 LLM。Deterministic write-time memory consolidation and pre-fetch recall for LLM agents. Local models, no LLM in the recall path or the consolidation decision.

用于在 LLM 辅助工作中强制执行项目约定的 RETE 规则引擎。A RETE rules engine for durable enforcement of project conventions in LLM-assisted work.

AI-Core 2026：面向 OpenAI、Anthropic、Gemini 与 Grok API 管理的集中化 WordPress AI Provider 中枢。AI-Core 2026: Centralized WordPress AI Provider Hub for OpenAI, Anthropic, Gemini & Grok API Management

人工智能与软件开发公司；构建智能系统、自动化工具、定制软件及开源技术。شرکت هوش مصنوعی و توسعه نرم‌افزار؛ سازنده سیستم‌های هوشمند، ابزارهای اتوماسیون، نرم‌افزارهای سفارشی و فناوری‌های متن‌باز.

OncoRAG 是一个 RAG 系统，为临床医生和研究人员提供即时获取最新肿瘤学证据的能力——来源包括直接来自 PubMed 的随机对照试验、Meta 分析、系统综述和 III 期临床试验。提出临床问题，即可获得带引文的可靠答案。OncoRAG is a Retrieval-Augmented Generation system that gives clinicians and researchers instant access to the latest oncology evidence — drawing from Randomized Controlled Trials, Meta-Analyses, Systematic Reviews, and Phase III Clinical Trials sourced directly from PubMed. Ask a clinical question, get a grounded answer with citations.

Spec-FastGS 论文工作区：代码、已下载论文库 + 文献综述、分析与报告。Spec-FastGS thesis workspace: code, downloaded paper library + literature review, analysis, and report.