Game Boy / Game Boy Color / Super Game Boy emulator, debugger and embedded MCP server for macOS, Windows, Linux, BSD and RetroArch.

30 秒找到真正适合你的 DeepSeek Harness插件。每天自动抓取 GitHub 上的 `dsh-plugin` 项目并逐个复核：真实插件分类收录，蹭标签项目剔除。通过场景化分类、精选推荐、热度排行和图文导览，帮你快速看懂每个插件能做什么、适合谁，以及如何开始使用。欢迎 Star ，让好用的插件更快被发现。

Adds MCP server to Blockbench

Plug/unplug any DeepSeek Harness plugin cleanly: list every mounted layer, disable/enable without deleting, remove bundles + patch rows + dependencies in one pass, and audit for orphaned/dangling plugin state. Zero runtime dependencies; read-only by defau

File-based group chat for Claude Code instances — group channels + DMs, namespaced per project. Installable as a skill or plugin.

Claude Code plugin for German/EU legal audits (DSGVO, TDDDG, UWG, AI Act, etc.). Not legal advice.

Solidity Static Analyzer that easily integrates into your editor

Collection of skills for Upstash

Headless IDA Pro MCP Server

AI-powered ECG analysis: submit ECG images and receive diagnosis reports from ARPI's ECG AI.

DeepSeek Harness Codex 跨平台桌面版，无需提前安装任何环境，开箱即用

DoiT official MCP Server

一个微调美观的DeepSeek harness客户端（欢迎插件加入）

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

WordPress plugin that turns Elementor & WordPress into an MCP server. 200+ AI-ready tools for building, editing, and managing page designs programmatically.

竹知了 —— 一转就哇哇叫的传统玩具，Web 模拟版。零依赖单文件，真实录音采样，移动端优先。

Whale Girl skin series for DeepSeek Harness. 适用于 DeepSeek Harness 的，鲸鱼娘系列皮肤。

Fantasy Premier League Kotlin/Compose Multiplatform sample

跨工具（Cursor / WorkBuddy / Claude Code 等）的 SKILL.md 技能管理器与 Rules 规则管理器（含远程规则导入），TypeScript 零运行时依赖实现

Modern, lightweight profanity detection & content moderation toolkit with l33t speak detection, multi-language support, and guard rails

TDA - Thread Dump Analyzer (for Java). Analyze your Thread Dumps with a GUI or use it as MCP Server.

极简实用的微信小程序反编译 Web 工具

Figma Plugin & MCP server to bypass API limits

Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute.