仓库/Skill 库

面向 MCP 的 Agent 评估标准——对输出质量打分、捕获安全失败、强制成本预算。The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

一个 science agent，可协助任意通用 AI agent 执行大规模数据管理操作。基于 IOWarp 平台积累的工作完成，由 Illinois Tech 的 Gnosis Research Center 开发，获 NSF 资助。A science agent supporting any general AI agent in performing data management operations at scale. Builds upon the heritage of the IOWarp platform and proudly represents work done at Gnosis Research Center at Illinois Tech. Supported by NSF.

本地优先的 MCP server，提供 Garmin Body Battery、HRV、睡眠与训练数据 — 兼容 Claude/CursorLocal-first MCP server for Garmin Body Battery, HRV, sleep & training data — Claude/Cursor ready

AI 的 Linux — 一个开放、联邦化、自托管的 AI 操作系统。人类、AI Agent 与本地 LLM 在你拥有的节点上共享应用、知识与能力。MIT。The Linux of AI - an open, federated, self-hosted AI operating system. Humans, AI agents, and local LLMs share apps, knowledge, and capabilities on nodes you own. MIT.

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

将 Claude Code 和 Codex 从聊天助手转变为自主编码系统Turn Claude Code and Codex from chat assistants into autonomous coding systems

实验性的本地优先 memory CLI，面向 MCP agent：只读访问 Gmail、日历、iMessage 与文件 → 输出带引用的本地上下文。Experimental local-first memory CLI for MCP agents: read-only Gmail, calendars, iMessage, and files → cited local context

开源 DNS 与邮件安全扫描器：一个 MCP 端点、57 项检查、零安装，基于 Cloudflare Workers。Open-source DNS & email security scanner. One MCP endpoint, 57 checks, zero install. Cloudflare Workers.

自托管博客平台，AI agent 可代为运行。一个 Bun 进程，两个 SQLite 文件，路径上无需任何云端账号。A self-hosted blog platform an AI agent can run for you. One Bun process, two SQLite files, no cloud account anywhere in the path.

AI Agent 的开源安全方案：macOS 与 Linux 上的内核强制出站控制、仅由运维持有的密钥、抗篡改审计。一条命令即可保护 Claude Code、Cursor 或任何 MCP harness。链路中无供应商介入Open-source security for AI agents: kernel-enforced egress control on macOS and Linux, keys only the operator holds, tamper-evident audit. One command protects Claude Code, Cursor, or any MCP harness. No vendor in the path.

本地优先的 MCP server，提供 WHOOP 恢复、HRV 与睡眠数据 — 兼容 Claude、Cursor、ChatGPTLocal-first MCP server for WHOOP recovery, HRV & sleep — Claude, Cursor, ChatGPT ready

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.

通过 x402 提供 205 个按调用付费的 MCP 工具，无需 API key。覆盖股票、加密/DeFi、宏观数据、链上分析、天气、政府数据等 200+ 类目。基于 Base 链的 USDC 结算。205 pay-per-call MCP tools via x402 — no API keys. Stocks, crypto/DeFi, macro data, on-chain analytics, weather, government data, and 200+ more. USDC on Base.

零基础设施构建 AI agent 与工作流。Build AI agents and workflows with zero infrastructure

每条声明均经机器校验，包括"零运行时守护进程"——受治理的 skill、规则与可回放状态。一份契约，适配所有宿主 AgentEvery claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract, every host agent.

https://cambio-uruguay.com 的源代码Source code of https://cambio-uruguay.com

Aixle Flow — 通过持久化、可检视的工作流编排编码 Agent。Aixle Flow — orchestrate coding agents through durable, inspectable workflows.

面向 AI Agent 的类脑持久化记忆：混合检索、知识图谱、睡眠-巩固生命周期、专家路由（HMoE），以及基于图 Laplacian 扩散的衰减、巩固、自动链接与谱检索子系统。提供 65 个 MCP 工具，本地运行，无需云端。Brain-like persistent memory for AI agents. Hybrid search, knowledge graph, sleep-consolidation lifecycle, expert routing (HMoE), and a graph-Laplacian diffusion subsystem driving decay, consolidation, auto-link, and spectral retrieval. 65 MCP tools. Local, no cloud.

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

开源 AI 占星 chatbot：支持 Vedic kundli、西洋星盘、塔罗、数字学、解梦，通过远程 MCP 进行真实计算，multi-LLM，Next.js 16，MIT 许可。Open source AI astrology chatbot. Vedic kundli, Western charts, tarot, numerology, dreams. Real calculations via remote MCP, multi-LLM. Next.js 16, MIT.

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

面向 LLM Agent 的本地优先上下文引擎——在检索路径上无需 LLM 调用即可检索、权衡并压缩代码库到上下文窗口。采用 SQLite 知识存储，支持 CLI + HTTP + MCP，提供 know/miss Agent 契约。Local-first context engine for LLM agents — retrieves, weighs, and compresses your codebase into the context window with no LLM call on the retrieval path. SQLite knowledge store; CLI + HTTP + MCP; know/miss agent contract.

围绕你的 AI Agent 搭建的工程化组织——任务、隔离会话、对抗式评审、记忆与决策路由，以环境的形式构建。The engineering organization around your AI agents — tasks, isolated sessions, adversarial review, memory, and decision routing, built as environment.

DebugBundle 产品源码与运行时代码。DebugBundle product source and runtime code.

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

完整的 Portkey Admin API MCP serverFull Portkey Admin API MCP server

可移植的 Rust Agent Client Protocol (ACP) server，具备模型路由、工具、权限、沙箱、会话与 MCP 集成。Portable Rust Agent Client Protocol (ACP) server with model routing, tools, permissions, sandboxing, sessions, and MCP integration.

基于 Tauri、SvelteKit 和 Rust 构建的现代多 Agent 桌面 AI 客户端。A modern, multi-agent desktop AI client built with Tauri, SvelteKit, and Rust.

无状态的统一多提供商 AI 运行时，兼容 OpenAI 与 Anthropic API，支持 Vercel UI 流式输出，提供托管 Agent 与 Skills，覆盖 14 万+ 模型。Stateless unified multi-provider AI runtime with OpenAI & Anthropic-compatible APIs, Vercel UI streaming, managed agents and Skills across 140k+ models.

OAuth 2.1 授权服务器，实现 MCP 授权规范。OAuth 2.1 Authorization Server. Implements the MCP Authorization Spec

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.

面向 Bugzilla 的安全加固 MCP server，使用 Rust 编写。Security-guarded MCP server for Bugzilla, written in Rust

改配置+重启才能加 MCP？DeepSeek Harness (DSH) 插件「技能配置」解决：设置页粘贴 JSON 即连 MCP 服务器、热加载免重启；上传 zip/.skill 自动识别 SKILL.md，创建/编辑/启停技能，即点即用

面向 Claude Code、Codex、Cursor 等编码 Agent 的 Git 原生决策记忆。保留约束与被否决的备选方案，只呈现当前仍然生效的决策。Git-native decision memory for Claude Code, Codex, Cursor and other coding agents. Preserve constraints and rejected alternatives; surface only the decisions still in force.

C++ AI Agent like langgraph. 支持嵌入普通程序中扩展实现AI功能

AI 原生时序记忆图，采用统一 DSL——将概念、查询、智能体工作流与语音统一为可部署的原语AI-native time-series memory graph with a single DSL — unifies concepts, queries, agent workflows, and voice into deployable primitives.