仓库/Skill 库

MCP服务器，可将几乎任何内容转换为MarkdownA Model Context Protocol server for converting almost anything to Markdown

SOTA 低比特 LLM 量化（INT8/FP8/MXFP8/INT4/MXFP4/NVFP4）与稀疏化方案；面向 PyTorch、TensorFlow 与 ONNX Runtime 的领先模型压缩技术SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

ToolHive是用于运行和管理MCP服务器的企业级平台ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.

面向Unity Editor的MCP连接插件，专为Cursor、Claude Code、Codex、Windsurf及其他IDE设计Model Context Protocol (MCP) plugin to connect with Unity Editor — designed for Cursor, Claude Code, Codex, Windsurf and other IDEs

潜入 Shell 的幽灵。Ante 是一个自包含的 Agent 框架，核心高度优化。体验类似 Claude Code 或 Codex，但无其依赖与模型限制。Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.

开源 LLM/VLM 负载均衡器与服务平台，用于规模化自托管 LLM（和 VLM）🏓🦙 作为 llm-d、Docker Model Runner 等项目的替代方案，组件更少、部署更简单，基于 ggml 生态构建。支持 CPU 和 GPU。Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

[GenAI 应用开发框架] 🚀 快速轻松构建 GenAI 应用 💬 在代码中使用结构化数据和链式调用语法与 GenAI Agent 交互 🧩 使用事件驱动的 *TriggerFlow* 管理复杂的 GenAI 业务逻辑 🔀 无需重写代码即可切换任意模型[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code

一个支持与 MySQL 数据库安全交互的 Model Context Protocol (MCP) server。A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases

使用 Model Context Protocol (MCP) 和 REST API 为 TikTok、Instagram Reels 和 YouTube Shorts 创建短视频。Creates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API.

一个作为统一工具集成的桌面 MCP client，通过 Model Context Protocol (MCP) 加速 AI 采用，并支持跨厂商 LLM API 编排。A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.

AI 音频数据集（AI-ADS）🎵，包含语音、音乐和音效，可为 Generative AI、AIGC、AI 模型训练、智能音频工具开发及音频应用提供训练数据。AI Audio Datasets (AI-ADS) 🎵, including Speech, Music, and Sound Effects, which can provide training data for Generative AI, AIGC, AI model training, intelligent audio tool development, and audio applications.

AI 短剧制作的 skill 集合：拆角色、出设定图、排大纲 | Agent skills for AI short-drama production — character bibles, model sheets, adaptation outlines. Runs in Claude Code & codex.

论文"LAMBDA: A large Model Based Data Agent"的官方仓库。https://www.polyu.edu.hk/ama/cmfai/lambda.htmlThis is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html

x64dbg-MCP Server 是 x64dbg 的原生 MCP（Model Context Protocol）插件，通过 HTTP 暴露调试器全部功能。可连接任意兼容 MCP 的 AI 助手，以编程方式控制 x64dbg：设置断点、单步执行、读取内存、转储寄存器等。基于 Zig 构建——零依赖、单二进制输出，跨平台。x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

[CVPR2024 (Highlight)] RichDreamer：一种可泛化的法线-深度扩散模型，用于生成细节丰富的文本到 3D 内容。Live Demo：https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC[CVPR2024 (Highlight)] RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. Live Demo：https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC

基于 Hermes Agent 的自主攻击性安全、漏洞悬赏与红队 Agent 框架，具备专用推理技能与多模型 LLM 编排能力。Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.

DeepSeek v4 Flash EXL3 运行于单台 DGX SparkDeepSeek v4 Flash EXL3 on one DGX Spark

Model Context Protocol (MCP) 服务器的 Node.js 实现，支持从多源（包括 **Web of Science**、arXiv 等）搜索和下载学术论文。A Node.js implementation of the Model Context Protocol (MCP) server for searching and downloading academic papers from multiple sources, including **Web of Science**, arXiv, and more.

AI 驱动的 CLI 编码 Agent，内置 20+ 工具，支持 MCP 与多模型提供商。AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers

将 Minimax-H3 蒸馏为 4 步。Distill Minimax-H3 into 4 steps

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.

DeepSeek Harness 插件，支持跨预设会话迁移的可预览；固定 schema 的交接保留状态、源模型意图与未处理图像，原始会话保持不变DeepSeek Harness plugin for previewable cross-preset session migration. Fixed-schema handoffs preserve state, source-model intent, and unresolved images; the original session stays untouched.

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.

fak — 面向 Claude Code、Codex、Cursor 和 MCP 的 Fused Agent Kernel：通过缓存稳定的模型流量、上下文压缩 + 崩溃恢复、本地重复服务、纳秒级工具策略以及本地 GGUF 推理，减少 token 消耗与重复工作。fak — the Fused Agent Kernel for Claude Code, Codex, Cursor, and MCP: use fewer tokens and do less repeated work with cache-stable model traffic, context compaction + crash resume, local repeat serving, nanosecond tool policy, and local GGUF inference.

发布 AI Agent 制品，而非 demo 表演 — 验证器把关、跨模型族运行，自动学习哪个模型最优。Ship AI-agent artifacts, not demo theater — verifier-gated, cross-family runs that learn which model wins.

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.

面向 Claude、Cursor 及 AI agent 的 GeneXus 18 MCP server，通过 Model Context Protocol 对 KB 对象（transactions、web panels、procedures、SDTs）进行读取、编辑与分析。GeneXus 18 MCP server for Claude, Cursor, and AI agents — read, edit, analyze KB objects (transactions, web panels, procedures, SDTs) over the Model Context Protocol.

[CoLM 2026] MoANT 官方代码：面向多任务大语言模型微调的语义感知秩一专家混合模型[CoLM 2026] Official code for MoANT: Mixture-of-Rank-One-Experts with semantic-aware Intuition for Multi-task Large Language Model Finetuning

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.

面向律所的自托管、GDPR 合规 AI Agent。零云依赖、哈希链审计追溯（符合 AI Act 第 12 条）、自带模型、支持 9 种语言版本。willchen96/mike 的硬分叉，AGPL-3.0 许可。Self-hosted, GDPR-safe AI agent for law firms. Zero-cloud, hash-chained audit trail (AI Act art. 12), bring-your-own-model, 9 language editions. Hard fork of willchen96/mike, AGPL-3.0.

本地 Windows 桌面监视器，用于查看正在运行的 Claude Code agent —— 实时状态、预估成本、模型、主机以及一键聚焦，按项目分组。只读且完全离线。Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by project. Read-only and fully offline.

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.

运行 Ollama 本地 LLM 服务的 Docker 镜像。默认安全，所有 API 请求需 Bearer token（首次启动时自动生成）。OpenAI 兼容 API。支持首次启动模型预拉取、NVIDIA GPU (CUDA) 加速和持久化模型存储。多架构：amd64、arm64。Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.

Autobots | 由 NVIDIA NIM 驱动的去中心化模型 agent 集群。通过专用 6 文件控制架构编排高精度、端到端可鉴权软件开发流程，具备自动化安全审计、无冗余任务路由与自主状态管理能力。Autobots | A decentralized model agentic swarm powered by NVIDIA NIM. Orchestrating high-precision, end-to-end authenticated software development through a specialized 6-file control architecture. Features automated security auditing, non-redundant task routing, and autonomous state management.

Hearting —— 面向 Claude Code、Codex 与 OpenCode 的 agent 设置。一份可移植契约覆盖三者，支持能力路由、跨运行时密封调度、节点级模型分层与实时 Fleet 视图，前身为 agent_settingHearting — the agent setting for Claude Code, Codex, and OpenCode. One portable contract projected onto all three, with routed capabilities, sealed cross-harness dispatch, per-node model tiers, and a live Fleet view. Formerly agent_setting.

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.