Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
The AI Config Plaza. Stop configuring AI tools from scratch. Discover, share, and one-click install verified configurations for MCP servers, Agents, and Prompts.
Scan your dev machine for AI agents, MCP servers, IDE extensions, suspicious files, and risky package-manager configs — in seconds.
makes it easy to deploy and serve Haystack Pipelines and Agents.
A simple NextJS MCP client with sensible keybindings
MD2Card Markdown 转知识卡片 将 Markdown 文档转换为精美的知识卡片，支持多种风格
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
Local-first creative studio with 37 model routes, transparent costs, local archives, and MCP access.
MCP server provides Feishu related operations to AI encoding agents such as cursor 飞书MCP插件，读取文档、发送消息、合同审批、数据处理.....
This MCP server provides tools for listing and retrieving content from different knowledge bases.
Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quarantine, schema pre-inject. No hosted gateway.
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.
Agent Skills
AI assistant for Obsidian with , , and powered by Google Gemini.
基于 Claude Code Agent Skills 的 AI 提示词工程系统 - 10个场景化专家，自动路由，精准生成优秀提示词 ## 项目简介 这是一个基于 Claude Code Agent Skills 技术的智能提示词生成系统。通过自然语言请求，系统会自动路由到对应的专业 Skill，帮助用户写出高质量的 AI 提示词。
基于 LangGraph 和 DeepAgents 框架的智能体 Skills 能力演示项目。
基于 GJB 438C-2021 [5.10] 标准模板的 SRS 文档自动生成
Generate and review MiniMax H3 video prompts from user goals and multimodal references.
面向 AI Agent 的精选 Skills 集合。每一个 skill 都在日常工作中实际使用、迭代、踩过坑，覆盖内容创作、设计视觉、工具集成、合规文书等场景。
Command-line tool for distributed LLM inference benchmarks on SLURM clusters using TensorRT LLM, SGLang and vLLM.
Ready-to-run training recipes for reinforcement learning (GRPO, DAPO, GSPO, CISPO), preference optimization (DPO, ORPO), and supervised fine-tuning (SFT) on Fireworks.
A git custom command that enhances Git's native worktree functionality with interactive features, automation, and repository migration capabilities.
先归根，再分化；先明道，再造物。 从混沌需求出发，生成可运行、可验证、可进化的 Agent Skill。
"Writing doesn't just communicate ideas; it generates them."