仓库/Skill 库

面向业务的 RAG | 要么有引用，要么不要 | 客服团队需要一份可核验的答案RAG for business | Citations or nothing | Support teams need an answer they can verify

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.

面向 AI agent 与 agentic workflow 的开源 MLflow 插件：涵盖 prompt、tool、skill、MCP server、RAG 知识库、评估、部署、可观测性以及 Aria copilot。Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

软件工程作品集 | Web 开发 | 桌面应用开发Software Engineering Portfolio | Web Development | Desktop App Development

面向印度尼西亚的环境工程 AI Agent（MCP Server），内置 330 个工具。Environmental Engineering AI Agent (MCP Server) untuk Indonesia dengan 330 tools.

Swift AI Command CenterSwift AI Command Center

可安装的私有 AI 指挥中心，跨 Windows、macOS 与 Linux，集成 OpenZero、ZSEC Shield 与 TalkToAI 工作区。Installable private AI command center for Windows, macOS and Linux with OpenZero, ZSEC Shield and TalkToAI workspaces

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.

RAG 真的物有所值吗？ragornot 在真实 AWS Lambda + Bedrock 后端上，通过四种检索模式（Flat/BM25、Hierarchical、LLM-only、RAG）运行相同查询，并测量延迟、质量、成本和碳排放——用数据帮你决定是否使用 RAG。静态 Next.js 部署于 GitHub Pages。Does RAG actually earn its cost? ragornot runs the same query through four retrieval modes (Flat/BM25, Hierarchical, LLM-only, RAG) against a live AWS Lambda + Bedrock backend and measures latency, quality, cost, and carbon — so you can decide RAG-or-not with data. Static Next.js on GitHub Pages.

Agent Fridge——阻止 AI 编码 agent 相互覆盖彼此的成果。提供路径声明、租约、一次写入笔记，并为任意终端生成共享看板。Agent Fridge - stop AI coding agents from overwriting each other's work. Path claims, leases, write-once notes, and a generated shared board for any terminal.

在同一 chunk 集合上对比 Lexical / Vector / Graph RAG，提供确定性评估、自我修正的 LangGraph agent 循环、PII 治理与 RAG 就绪度分析器。Lexical vs Vector vs Graph RAG over one identical chunk set, with deterministic evaluation, a self-correcting LangGraph agent loop, PII governance, and a RAG-readiness analyzer.

一个真实运营业务的自驱动 AI 组织的"飞行记录仪"——零收入、第一天起，所有决策均有案可查。Flight recorder of an autonomous AI org running a real business. €0 revenue, day 1, all decisions on file.

协调 OpenClaw AI Agent 攻克 LHON——一种导致失明的罕见遗传疾病。安装 Skill，让你的 Agent 参与真实医学研究。Coordinating OpenClaw AI agents to cure LHON — a rare genetic disorder causing blindness. Install the skill, let your agent contribute to real medical research.

面向编码 Agent 的 MCP 原生部署控制平面。MCP-native deployment control plane for coding agents.

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

DeepSeek Harness 个人自研插件集：上下文罗盘 / 跨会话知识 / 子代理模型路由 / AI 生图（Personally developed plugins for DeepSeek Harness）

AI 教材数字化与互动辅导平台：PDF/扫描教材经 MinerU OCR 结构化出题，文本 + 视觉双模型审校与确定性质量门禁；学生端七种题型互动、分层提示与错题多轮陪练闭环；FastAPI + PostgreSQL JSONB + React 19

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

基于你的 AI Agent 集群已编写的 markdown 协作日志之上，为每个 Agent 提供独立收件箱。A per-agent inbox over the markdown coordination logs your AI agent fleet already writes

脚手架搭建生产级 AI Agent 项目最快的方式。The fastest way to scaffold production-ready AI Agent projects

通过 MCP 为协作型 AI agent 提供基于 PostgreSQL 的共享记忆。Shared PostgreSQL-backed memory for collaborating AI agents via MCP

📚 构建并评估 RAG 流水线，实现数据导入、嵌入、检索与问答，并提供准确性与相关性指标。📚 Build and evaluate RAG pipelines to ingest, embed, retrieve, and answer questions with metrics for accuracy and relevance.

织光 WeaveMind V1.0 — 看得见、会记忆、会自我进化的多智能体 AI 团队。多用户鉴权、结构化数据适配器、验收溯源、报告分享/PDF/通知，本地运行数据私有。

🤖 DeepTutor 是一款 AI 驱动的学习助手，可根据个人需求定制教育内容，提供个性化资源与支持🤖 Enhance learning with DeepTutor, an AI-powered assistant that personalizes education to fit your needs. Discover tailored resources and support.

使用本地 LLM 与私密法律文档对话，在自有硬件上获得带引用、可验证的答案。Chat with private legal documents using local LLMs. Get cited, verifiable answers on your own hardware.

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.

🚀 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.

为 Codex 及 AI 编程 Agent 提供的持久化项目记忆与智能层。Persistent project memory and intelligence layer for Codex and AI coding agents.

🛠️ 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.

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

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

Haven 42 是一款证据门控、本地优先的 AI 工作台，支持 Windows、Linux 和 macOS 上的编码、聊天与媒体处理。Haven 42 is an evidence-gated, local-first AI workbench for coding, chat, and media on Windows, Linux, and macOS.

AI 构建，你决定是否上线 —— AI agent 工作的审核关卡。AI builds it. You decide if it ships. — review gates for AI-agent work.

用日常语言描述应用需求，AI 专家团队即可设计、构建、测试并私有发布到你的 GitHub — 无需编码。面向非技术用户的 Claude Code 插件。个人使用免费；商业许可可用。Describe an app in plain words and a team of AI specialists designs, builds, tests and privately publishes it to your own GitHub — no coding needed. A Claude Code plugin for non-technical people. Free for personal use; commercial licence available.