仓库/Skill 库

303 份 AI/LLM 中文讲义，支持在线阅读、PDF 下载和 LaTeX 源码查看 | Stanford CS336/CS224R/CS25 | Berkeley LLM Agents | Agent 工程实践

Obsidian.md 是一款专为学术写作打造的出色笔记应用。本仓库是"使用 AI 进行系统文献综述"研讨会活动的组成部分。Obsidian.md stands out as an exceptional note-taking application tailored specifically for academic writing. This repository is part of the activities for the Systematic Literature Review using AI workshop.

生产就绪的 FastAPI 平台，模块化组件，内置 control plane。A production-ready FastAPI platform with modular components and a built-in control plane.

面向 Overleaf 的 AI 驱动引用搜索与论文审阅 Chrome 扩展插件。类似 Google Scholar，但内置于 Overleaf 中。同时兼容 OpenAI Prism 和 Opera。AI-powered citation search & paper review for Overleaf — Chrome extension. Think Google Scholar but inside Overleaf. Also works with OpenAI Prism, & Opera.

本地 MCP server，用于有状态、fail-closed 的 Logic Pro 控制与项目实时回读。Local MCP server for stateful, fail-closed Logic Pro control and live project readback.

BibTeX 文献管理工具：自动将预印本更新为已发表版本，并筛选仅保留被引用的文献。Tools for managing BibTeX bibliographies: automatically update preprints to published versions and filter to only cited references.

统一 ACE-Step 1.5 与 YuE2-3B 的本地 AI 音乐工作室，集成于单一 Vue 界面——文本生成音乐、分轨分离、MIDI 转录与 LoRA 微调，并内置多轨 DAW。Local AI music studio unifying ACE-Step 1.5 and YuE2-3B in one Vue interface — text-to-music generation, stem separation, MIDI transcription, and LoRA fine-tuning, with a built-in multitrack DAW.

面向学术写作、数据分析、教学与科研交流的端到端技能。End-to-end skills for academic writing, data analysis, teaching, and research communication.

本课程涵盖从初始想法到正式学术写作的开发流程与实现要点。学生将学习如何转化与消化文献综述，从而凝练出拟定的研究题目。This course will cover the fundamental steps and implementation on developing the initial ideas to formal academic writing accordingly. Students will be given the mechanisms on how to transform and digest the literature reviews that leads to the proposed title.

mloda.ai - 面向 AI 与 ML 的开放数据访问。基于插件、可追溯、与框架无关。mloda.ai - Open Data Access for AI and ML. Plugin-based. Traceable. Framework-agnostic.

开源 multi-agent 研究助手：约 2 分钟生成带引用的网络报告，或由 25 个 agent 流水线配合人工检查点产出完整学术论文。欢迎贡献。Open-source multi-agent research assistant: cited web reports in ~2 min, or a full academic paper from a 25-agent pipeline with human checkpoints. Contributors welcome.

本仓库托管一个为开展系统文献综述（SLR）定制的 Obsidian vault，是"使用 AI 进行系统文献综述"研讨会活动的组成部分。This repository hosts an Obsidian vault tailored for conducting a Systematic Literature Review (SLR). This repository is part of the activities for the Systematic Literature Review using AI workshop.

基于 Google ADK 构建的生产级多 Agent 编排引擎：数据库驱动的 Agent 配置、支持 50+ LLM provider、MCP 协议、持久化记忆、Web 仪表盘与 RBAC。Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.

Zotero AI 插件：Zotero 10 的研究助手。可与文献库对话、执行联邦学术检索、RAG、OCR、系统综述，并管理云存储。包含独立的 MCP、Agent 能力与技能库。Zotero AI plugin Research assistant for Zotero 10. Chat with your library, run federated scholarly search, RAG, OCR, systematic reviews, and manage cloud storage. Includes standalone MCP, Agentic capabilities, and skills library.

收录经审核 Docker Compose 部署方案的自托管应用公开目录。Public catalog of self-hosted applications with reviewed Docker Compose recipes

结合向量检索与时序知识图谱的 AI 记忆系统，内置面向 Agent 的认知引擎，支持记忆衰减、矛盾检测与 MCP 集成。AI memory system combining vector search with temporal knowledge graph. Built-in cognitive engine for agents. Supports memory decay, contradiction detection, and MCP integration.

全栈开源 AI 协作套件与多 Agent 平台，具备 LLM 编排、自动化与虚拟助手能力，可从小规模部署平滑扩展至企业级环境。Complete open-source AI collaboration suite and multi-agent platform featuring LLM orchestration, automation, and virtual assistants. Scales seamlessly from small deployments to large enterprise environments.

将生产事故转化为结构化的 9 段式 LLM 响应（严重等级、根因、缓解措施、事后复盘）。附带 5 个场景的回归测试集 + LLM-as-judge 评估流水线。Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.

面向 Node.js、浏览器与 serverless 运行时的纯 TypeScript 低内存、零依赖图像编解码与处理库。具备有界解码/缩放管线，并提供深度 TIFF、科学栅格、GeoTIFF、OME-TIFF 与全切片成像支持。Low-memory, zero-dependency image codecs and processing in pure TypeScript for Node.js, browsers, and serverless runtimes. Bounded decode/resize pipelines plus deep TIFF, scientific raster, GeoTIFF, OME-TIFF, and whole-slide support.

用 Rust 编写的极速 ⚡️ (La)TeX 编译器 + IDE（HackCMU 2026 获奖项目）Blazing ⚡️ fast (La)TeX compiler + IDE written in Rust (HackCMU 2026 Winner)

类 GitHub 风格的 Jenkins CLI——在终端管理 context、构建运行、日志与管理员任务。GitHub-style CLI for Jenkins — manage contexts, runs, logs, and admin tasks from your terminal.

基于 Zotero Web API 的 JupyterLab 引用管理器Citation Manager for JupyterLab using Zotero Web API

文档驱动的文献综述流水线，包含反幻觉验证阶段（基于 OpenAlex/Crossref/Semantic Scholar 进行确认或剔除）。Document-driven literature-review pipeline with an anti-hallucination verification stage (confirm-or-drop against OpenAlex/Crossref/Semantic Scholar).

AI-ML Companion：一个通过"看 AI 运作"来学习 AI 与 ML 的交互式平台 — 28 条学习路径、400+ 模块、实时可视化 — 另有 20+ 端到端真实项目，覆盖经典 ML、深度学习、计算机视觉到生产级 LLM 与多 Agent 系统。AI-ML Companion: an interactive platform to learn AI & ML by watching it work - 28 tracks, 400+ modules, live visualizations - plus 20+ end-to-end real world projects from classical ML, DL, Computer Vision to production LLM & multi-agent systems.

开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversarial review.

🔥🔥 System One 模型与 Jev 背后的论文、开源复现与独立评测。🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

AI Max+ 395 加速：在 RTX 3060 上实测的异构 GPU PD 与异步融合层 pipeline 实验。AI Max+ 395 acceleration: measured heterogeneous GPU PD and asynchronous fused-layer pipeline experiments with RTX 3060.

⚡ Translate Markdown without breaking format — code blocks, LaTeX, links all preserved ｜ 翻译 Markdown 不破坏格式，代码块、LaTeX 公式、链接全保留

Jadense in Zotero — Zotero 的 AI 研究助手Jadense in Zotero — AI research assistant for Zotero

📚 只引用你能够核实的内容📚 Only Cite what you can verify

一切写作的单一应用the one app for everything you write

用于可复现 AI Agent 评测的确定性、可分叉、有状态 MCP 测试世界——不对生产环境产生副作用。Deterministic, forkable, stateful MCP test worlds for reproducible AI agent evaluation—without production side effects.

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

Paper Workbench — 论文写作审查全流程工作台 / End-to-end academic writing & review workbench

TexLite：轻量级自托管协作 LaTeX 编辑器，Overleaf 替代方案TexLite: Lightweight self-hosted collaborative LaTeX editor and Overleaf alternative

JabRef 用户文档。User documentation of JabRef