DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
492 个项目，匹配「harness」
HOWILLMAKEIT
DeepSeek Harness 插件：维护 llm-pi-ai 模型的准确上下文窗口，避免长会话被误判为上下文溢出。
Qinling-Melon-Farmers
DeepSeek Harness (DSH) local-first cross-session project memory: zero bundled runtime deps, bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embeddings or external service. / DSH 本地项目记忆插件。
hkkz9522
DeepSeek Harness session manager: delete, archive, move sessions across workspaces, migrate presets, favorites, review-later, search, filter, sort, prioritize, add tags & notes, and batch-manage sessions. | DSH 会话管理：删除、归档、跨工作区移动、预设迁移、收藏、待回看、搜索、筛选、排序、优先级、标签、备注及批量操作。
rootkiller6788
A pluginized microkernel architecture for building, orchestrating, and extending multi-agent systems in DeepSeek Harness.
kirkchinese
为 DeepSeek Harness 打造：选中 AI 回答或思考内容，随时追问、学习、检查与纠偏。
sailoumili
小说创作模式：一个统筹队长统领全局，5 个专职子代理各司其职——架构世界、策划剧情、管理人物、执笔写文、质检复核——协同写作。
WeirdSky924
Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.
gulagala001
让你的 DSH，火力全开。长上下文、任务验证、提示词优化、代码理解、电脑操作与四套完整主题。
hr98w
融合 Claude Code 的 Auto Memory 与 Codex 的 Session 记忆整理，为 DeepSeek Harness 提供简单、透明、上下文友好的长期记忆。Claude Code-inspired Auto Memory meets Codex-inspired Session consolidation, bringing simple, transparent, and context-efficient long-term memory to DeepSeek Harness.
quqxui
Long-term memory plugin for DeepSeek Harness (dsh): four-channel retrieval fusion and continuous memory evolution. Memory construction and retrieval are based on MemGAS (ICLR 2026).
Ultronen
Archive Management for DeepSeek Harness: browse, search, preview and restore archived chats, with workspace bulk archiving, ZIP backups and a Recycle Bin.
Zephyr-vibe
DSH Session Manager: manage conversations, archive/restore, delete safely, open record folders.
xiaoyuyu6420
一条命令备份/恢复 DeepSeek Harness（dsh）的全部数据：升级快照、会话日志体检修复、迁移预检、救援通道、凭据脱敏、GitHub 同步。 One command to back up & restore all of ~/.dsh: /backup, auto-backup, upgrade snapshots, session doctor & repair, migrate precheck, rescue console, credential redaction.
FeatherHunter
DeepSeek Harness 的 Prompt 工具箱：别再复制粘贴——24 条深度模板随手点，/prompt 与智能推荐主动兜底，装好即用、可自定义。 | The Prompt toolbox for DeepSeek Harness: stop copy-pasting — 24 deep templates at a click, /prompt & smart suggestions as backup; out of the box, fully customizable.
TOBYCAI
DSH 会话管理插件：设置面板 + 侧边栏双入口，归档/恢复/跨工作区移动/软删进回收站；回收站可恢复·批量清空·7/30/90 天自动清理，按标题·会话 ID·工作区搜索，带磁盘与血统详情；已适配 DSH 0.1.7 与 0.2.0（v4 日志，旧格式会话亦可移动，活跃会话排队移动）。Session Manager for DeepSeek Harness — archive/restore/move/trash lifecycle, search & per-session stats, 0.1.7 & 0.2.0 ready (v4 session format). | macOS/Windows/Linux |
fredalxin
Solo-style isolated brainstorm branches and Handoffs for DeepSeek Harness
chumingjun
Visual AI workflow orchestrator for DeepSeek Harness (dsh): multi-agent DAGs, live execution, recovery, and Feishu integration.
omdsh-dev
An dsh plugin for role-based LLM retry&fallback strategy. 基于角色的模型重试备用策略插件
PerryLink
Claude Code /rewind for DeepSeek Harness — git-first workspace snapshots before every mutation, turn-boundary session forks, one-shot /rewind restore. A dsh-plugin capability seam.
seven282
用于优化 DeepSeek harness提示词优化器，提升 AI 输出质量
JunNanLYS
让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.
PerryLink
RETIRED 2026-10-05 — the official DeepSeek Harness now ships native continuable subagents (subagent with backgroundMode: continuable, plus send_message / interrupt_agent / list_agents / job_*). Use those instead.
Wenaixi
DSH port of obra/superpowers — 完整移植、中文化、DSH 原生
Zoria-Lind
Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.