仓库/Skill 库

潜伏在终端与桌面里的幽灵 AI 编程 agent「Wraith」· A ghost-themed AI coding agent for terminal & desktop

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

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

你的分身。Claude Code、Codex 和 OpenCode 的任务控制中枢：查看每个 session、审批 Agent 行为、按计划调度运行。自托管，MIT 协议。You, multiplied. Mission control for Claude Code, Codex, and OpenCode: see every session, approve what your agents do, and run them on a schedule. Self-hosted, MIT.

管理你生活的 AI，让你在身体、心理与财务上保持健康。Telegram 可下载。AI that manages your life. Making you physically, mentally, and financially healthy. Download on Telegram.

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.

原生 macOS 的 WYSIWYG Markdown 编辑器，支持文件内审阅循环——建议、评论和修订以 CriticMarkup 字节形式存储；原生 LaTeX 数学（Vinculum）和图表（MermaidKit），零 JavaScript，字节无损，纯本地运行。A native macOS WYSIWYG Markdown editor with an in-file review loop — suggestions, comments, and tracked changes as plain CriticMarkup bytes. Native LaTeX math (Vinculum) and diagrams (MermaidKit), zero JavaScript, byte-lossless, local-only.

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 AI 编码 Agent 的厂商中立 continuation 协议：纯文件项目状态、标准库验证、恢复与冷启动 Agent 交接。Vendor-neutral continuation protocol for AI coding agents. Plain-file project state, stdlib validation, recovery and cold-agent handoff.

AI 运营门店。人类定方向，Agent 执行落地。AI run the shop. Humans set direction, agents execute.

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.

动态 README，包含 AI 生成的 SCP 基金会与 Wikipedia 随机文章摘要。A dynamic README with AI-generated summaries of random articles from the SCP Foundation and Wikipedia.

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

机器可读的架构决策记录。Git 原生的决策记忆与治理，面向人类与 Agent 编写的方案 — 集成 lint、CI 与 MCP。Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, and MCP.

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.

🤖 利用 TRPO、PPO、DPO、GRPO、DAPO、GSPO 等先进算法提升强化学习的稳定性与效率，优化策略训练。🤖 Enhance reinforcement learning stability and efficiency with advanced algorithms like TRPO, PPO, DPO, GRPO, DAPO, and GSPO for optimized policy training.

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

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.

为 AI Agent 设计的记忆系统，学习真正起作用的教训：在行动瞬间注入经验，依据结果归功，以反证挑战。本地优先、多 Agent、测试门控。Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.

DeepThink-AIOS 是一个完全本地化的多 agent 系统，配备双沙箱代码/逻辑验证、ChromaDB RAG 记忆与动态 VRAM 多路复用。DeepThink-AIOS is a fully local, multi-agent System with dual-sandbox code/logic verification, ChromaDB RAG memory, and dynamic VRAM multiplexing .

扩展 gastown 的 Gas City pack，包含自定义 Agent、公式与规划工作流。A Gas City pack with custom agents, formulas, and planning workflows, extending gastown

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

面向科学 grounding 的 MCP server：搜索 arXiv、OpenAlex、Crossref、Semantic Scholar、PubMed——通过公开元数据获取付费期刊的参考文献/引用信息。MCP server for scientific grounding: search arXiv, OpenAlex, Crossref, Semantic Scholar, PubMed — references/citations from paywalled journals via public metadata

在工作发生的地方就地捕获团队知识，由 agent 归档，并以可核验的引用形式给出回答。A team's knowledge, captured where the work happens, filed by an agent, and answered with citations you can check.

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.

以孟加拉语优先、面向方言的 LLM 研究。开源孟加拉语 tokenizer，性能优于 Sarvam、AI4Bharat 和 GPT-4o（fertility 1.52，几乎零破损 conjuncts）。非商用，保护孟加拉语及其方言。Bengali-first, dialect-aware LLM research. Open-source Bengali tokenizer that outperforms Sarvam, AI4Bharat, and GPT-4o (fertility 1.52, near-zero broken conjuncts). Non-commercial, preserving Bengali and its dialects.

Local-first 学术 PDF 阅读器：离线 CPU LLM 翻译与注释、OCR、ECDICT 词典。Tauri + FastAPI。Local-first academic PDF reader: offline CPU LLM translation & glossing, OCR, ECDICT dictionary. Tauri + FastAPI.

自主研究 Agent：文献综述、创意构思、实验、论文撰写与评审。为 OpenProgram 构建。Autonomous research agent: literature review, ideas, experiments, paper writing, and review. Built for OpenProgram.

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

众多 Agent，一个目标——你的目标。Many Agents, one objective... yours

🤖 基于 AI 分析与智能搜索，定制化发现 ArXiv 上你感兴趣的最新论文🤖 Discover the latest research papers on ArXiv tailored to your interests using AI-powered analysis and smart search features.

面向 LLM 的无损上下文压缩：token 用量减少 2–8 倍，按字节精确还原（sha256 校验）。提供 Claude Code 与 Cursor 的 MCP server。Lossless context compression for LLMs: 2x-8x fewer tokens, byte-exact reconstruction (sha256-verified). MCP server for Claude Code & Cursor.