Discover The Best DSH plugins
2467results
Find plugins for conversation memory, knowledge retrieval and context management.
dsh-mcp-bridgeCurated, verified MCP server bundle for DeepSeek Harness (dsh): one install brings demo, memory, filesystem, GitHub, Playwright and remote HTTP MCP servers, with a connectivity verifier and CI checks.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Edge-Echo/dsh-mcp-bridgedsh-memory-vaultCross-session memory vault for DeepSeek Harness: remember / recall / forget tools, per-turn prompt injection, and a browser management page.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:flymysql/dsh-memorydsh-mindsea识海 MindSea —— 给 DeepSeek Harness 加一套会自己长的记忆：每轮聊完自动沉淀，话 / 事 / 版本 / 阶段 / 决定 五层结构，带一块能翻能筛的面板
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SQHLnb666/mindseadsh-mnemosyneDeepSeek Harness 演化记忆系统：证据、时间、情境、状态演化、情绪与纠错
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:canyueY/dsh-mnemosynedsh-mnemosyneDeepSeek Harness 演化记忆系统：证据、时间、情境、状态演化、情绪与纠错
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DSH-Raising-Plan/dsh-mnemosynedsh-obsidian-assistantDeepSeek Harness plugin (Cordis toolset) for reading, searching, and editing a local Obsidian vault, with optional Local REST API integration.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:iamzcr/dsh-obsidian-assistantdsh-persona-memoryPersistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, secret scanning, and a WebUI memory-management settings page. Ported in spirit from pi-hermes-memory. TypeScript sources, built with tsc + esbuild.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Quophic/dsh-persona-memorydsh-plugin-wiki-toolsNative DeepSeek Harness tools for an Obsidian wiki vault: wiki_query, wiki_write, and wiki_lint implement the mechanical core (path routing, delta tracking, index/log bookkeeping, health checks) of the wiki skill suite.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Lion-1209/dsh-plugin-wiki-toolsdsh-seeker-osDeepSeek Harness 的对话体验增强套件：思考折叠、工具调用聚合、html/iu 卡片、对话截图与下载、消息撤回（文件与对话一并回退，含版本翻页），外加供应商中心、记忆/技能/连接器/画廊/档案七个工作台与 Personal Agent（主 Bot/子 Bot/群聊/期刊日记/通话；宿主侧 always-on 调度、DOST 式多消息与审批卡、按 owner 隔离的记忆引擎）。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Kr-ATG/dsh-seeker-osdsh-synapsisSynapsis 析域 —— 把讲义铺成一张能走进去的概念图（DSH Web UI 面板插件）
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Mathilde1214/dsh-synapsisdsh-task-memoryTask-isolated long-term memory for DeepSeek Harness: remember / recall / search stay inside one task boundary, with optional prompt injection.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wangyihao0001-oss/dsh-task-memorydsh-triad定时自动化 · 用量趋势 · 技能与 MCP Server 管理 · 自动沉淀的长期记忆——一套插件装齐 DSH 四个工作台。纯插件注入，不动官方源码，一句话安装。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Kr-ATG/dsh-triadlooki-pluginRecall captured moments, search past experiences, and inspect recent context through Looki.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:looki-ai/looki-pluginnowledge-mem-deepseek-harnessOne memory layer for every AI tool and agent, packaged for DeepSeek Harness with startup context, prompt-time recall, Mem MCP tools, and DSH thread capture.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nowledge-co/nowledge-mem-deepseek-harness@deepseek-ai/dsh-plugin-memoryPersistent 5-layer memory system for DeepSeek Harness (entry injection, relevance retrieval, agent tools, and LLM-backed auto-extraction).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NattoCB/dsh-plugin-memory@dsh-cc/acpAgent Client Protocol server for driving dsh-cc agents over JSON-RPC stdio (vendored from @deepseek-ai/dsh-acp)
@dsh-cc/advisor-watchdogAdvisor watchdog: an opt-in second model (cheap lane via runSideQuery) reading every completed turn's delta and injecting severity-tiered advisory notes at the next step; default off
@dsh-cc/bundle-acpAgent Client Protocol bundle for the dsh acp profile: host-plane swap to the CC preset + the @dsh-cc/acp protocol driver over dsh-base and dsh-acp-app
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dsh-cc/dsh-cc#e099bb1b40ab7534dd1daaae87d25cedb86a4b38&path:packages/bundle/cc-acp@dsh-cc/bundle-permissionsClaude Code permission parity layer for dsh profiles: five-level settings cascade + CC permission-rule engine
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dsh-cc/dsh-cc#e099bb1b40ab7534dd1daaae87d25cedb86a4b38&path:packages/bundle/cc-permissions@dsh-cc/bundle-shellCC shell host-plane infra: tools registry swap (deferred-name support) + settings migrations; the glue plugin code lives here but is mounted by the CC preset (packages/preset/cc)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dsh-cc/dsh-cc#e099bb1b40ab7534dd1daaae87d25cedb86a4b38&path:packages/bundle/cc-shell@dsh-cc/bundle-tuiTerminal surface bundle for the dsh tui profile: CC-mode TUI over dsh-base
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dsh-cc/dsh-cc#e099bb1b40ab7534dd1daaae87d25cedb86a4b38&path:packages/bundle/cc-tui@dsh-cc/command-agentsHuman-facing slash command to list, inspect, and stop continuable background agents
@dsh-cc/command-auto-modeHuman-facing /auto-mode command: show the built-in classifier slot defaults and the effective trusted-scoped autoMode configuration
@dsh-cc/command-branchHuman-facing slash command to fork the current session into a new branch
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.