Kaixxrua/dsh-aigc-radar 预览 preview

Kaixxrua/dsh-aigc-radar

Project Overview项目介绍

This is a native plugin built exclusively for DeepSeek Harness (DSH) that connects to the public AIGC Radar curated project library API. It lets DSH agents search for mature AIGC-related open source GitHub projects that have at least 500 stars, with results displayed as native structured search cards in the DSH web UI that persist across session replays. It ships two core tools: search_ai_projects for running keyword queries against the library, and get_project_categories for browsing the full bilingual category taxonomy.

The plugin supports two discovery routing layers: explicit user discovery and proactive automatic reuse checking. For explicit discovery, users can simply ask the DSH agent for a project matching their specific needs, and the plugin will return sorted, categorized results without requiring any manual tool invocation. For proactive checking, the plugin automatically runs a search before the agent implements any major new module or subsystem, preventing redundant work on solutions that already exist. Only narrow tasks like bug fixes, styling changes, or simple CRUD do not trigger an automatic check.

Installation requires an existing DSH installation, and can be done via npm with the command dsh plugin --profile web add dsh-aigc-radar, or installed from source directly via GitHub. The plugin is released under the open source MIT license. Anonymous usage is limited to 30 calls per day per IP address. Free registered accounts get 60 calls per day plus 1200 calls over a rolling 30-day window, while paid member accounts get 400 daily calls and 8000 monthly calls. Users must add their MCP token from aigcnews.cn to their DSH profile configuration to use authenticated access.

这是一个专为 DeepSeek Harness (DSH) 开发的原生插件,用于搜索 AIGC Radar 开源项目库。它连接 AIGC Radar 的公开 MCP 端点,可为 DSH 代理搜索星标数 500 以上的成熟开源 AIGC 相关项目,返回结构化结果并以原生搜索卡片的形式展示在 DSH 的 Web 界面中,结果在会话重放时也能正常显示,共提供搜索项目和获取分类列表两个工具。

该插件支持主动和显式两种发现模式,用户可以直接向代理提问需求,就能获取符合分类标签的项目结果,不需要手动调用工具。在代理准备实现大型模块或子系统之前,插件会主动检查库中是否已有成熟方案,避免重复造轮子,仅对细小的修改工作不触发检查,适合开发 AIGC 相关项目的开发人员和 DSH 日常用户使用。

插件采用 MIT 许可证开源,安装需要先配置好 DSH 环境,可通过 dsh 命令直接安装 npm 上的预构建包,也支持从 GitHub 源码安装。匿名用户每天每 IP 可调用 30 次,免费注册账号可获得每日 60 次加月度 1200 次的配额,会员账号配额更高,用户需要在 DSH 配置中填入从 aigcnews.cn 获取的 MCP 令牌。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 3 stars - very few users, little community feedback星标只有 3,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add dsh-aigc-radar

把 Kaixxrua/dsh-aigc-radar 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-aigc-radar

English | 简体中文

AIGC Radar project search for DeepSeek Harness (dsh).

Stop rebuilding what already exists. While you plan and implement, the agent proactively checks the curated AIGC Radar library for mature, battle-tested projects that already solve your problem — before you write a line of code. Results render as native search cards in the dsh Web UI — not raw markdown — and survive session replay.

search_ai_projects rendering as a native search card in the dsh Web UI

What you get

Tool What it does
search_ai_projects Searches the curated AIGC Radar library: GitHub projects above a 500-star floor, enriched with categories, bilingual (zh/en) tags and descriptions, and daily star-growth metrics
get_project_categories Lists the category taxonomy (categories + subcategory counts) for filter discovery

Two routing layers make discovery automatic rather than opt-in:

  • Explicit discovery — ask "找个能做 deep research 的开源框架" and the agent comes back with starred, categorized results, no "use the tool" needed
  • Proactive reuse check — before the agent implements a major module or subsystem (auth, payments, workflow engines, search/indexing, protocol implementations, end-to-end RAG/Agent pipelines…), or recommends the architecture / technology / build-vs-reuse approach for one, it runs one library check on its own initiative, so mature alternatives surface before anyone rebuilds them. Narrow work (bug fixes, renames, styling, CRUD) is deliberately excluded

Why a native plugin instead of the MCP server?

AIGC Radar also ships as an MCP server — and this plugin now rides that same MCP endpoint (POST /api/mcp), so every call counts against the same rate limits and quotas. What the plugin adds on top:

  • Native web search cards — structured sources render as cards in the Web UI and are rebuilt faithfully on session replay (presentationMeta), which the MCP transport cannot express
  • Typed canonical output — the result is one validated JSON value, so Code Mode can compose it programmatically (await tools.search_ai_projects({ q: 'mcp' })) with full type inference
  • First-party prompt routing — the discovery-routing guidance lives in system-prompt assembly, not in MCP instructions that clients may truncate

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-unread-dot 下一个 Next dsh-qqbot-bridge →