Home/Plugins/Tags/ai

ai plugins for DeepSeek Harness

8 indexed projects tagged ai · 14,531 combined stars · updated 2026-10-25

8 indexed projects carry the `ai` tag. Combined, they hold 14,531 GitHub stars. The list below is ranked by stars, not by our opinion — we do not sell placement in it.

Where they sit: Awesome Lists (2), Memory & Context (1), Agents & Teams (1), Terminal & CLI (1).

4 of these 8 have Chinese in their description — the language gap is why this index exists.

Ranked by stars

  1. 1MemTensor/MemOS ★ 12,053
    Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
  2. 20xsline/awesome-deepseek-harness ★ 1,249
    DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.
  3. 3yejiming/MuseAI ★ 678
    创建你的 AI 角色，进入你的故事世界。和角色聊天、冒险、穿书，让每一次互动都留下羁绊（支持 DeepSeek Harness 插件，欢迎使用）
  4. 4dshplugin/dsh-plugin-hub ★ 318
    DeepSeek Harness 社区内置插件市场（dsh-plugin）— 搜索插件、下载并安装 10000+ 人工精选社区插件，每日更新、完全免费。内置在 Harness「设置 → 插件中心」，无需离开应用即可浏览、搜索、安装各类 AI 插件。
  5. 5FeatherHunter/dsh-mattpocock-skills-deck ★ 212
    🌟安装即自带mattpocock/skills v1.3.1的27个工程与效率技能，无需手动装技能。400亿token打造本插件，在原始技能之上提供10倍的开发效率，也能帮助新手更快上手该技能套件。全力支持GitHub issue；Markdown为预览版；GitLab暂不支持。感谢您的使用和支持🌹
  6. 6zimodzh/dsh-plugin-dev-skills ★ 15
    An Agent Skills skill for developing DeepSeek Harness (DSH) plugins（开发 DSH 插件的 Agent Skill）——插件/服务/事件/工具/LLM 适配器/打包安装的标准。Works with Claude Code, Codex, DSH, VS Code Copilot & any compatible agent.
  7. 7hiyms/dsh-web-search-provider ★ 4
    Improve web search in Deepseek Harness, use server-side search service.
  8. 8AlexKaiqi/dsh-multi-model-provider ★ 2
    Model catalog, portraits, Agent selection, and multimodal runtimes for DeepSeek Harness

How to read this list

  • Ranking is GitHub stars only. Sponsored placements never appear in this list; if we ever take one it is labelled and sits outside the ranking.
  • Stars measure attention, not quality. A 200-star plugin that solves your problem beats a 30,000-star desktop client you will not use.
  • We do not execute plugin code. Descriptions are the upstream repo's own.

Related