Discover The Best DSH plugins

Memory and knowledge · DeepSeek Harness plugins — Page 29

1213results

Find plugins for conversation memory, knowledge retrieval and context management.

@achasoft/dsh-memory

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client

Memory and knowledge · Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:navid-kianfar/dsh-memory
@agentframe/dsh-agentframe-suite

AgentFrame Suite — 三件套整合包 + WebUI 控制面板 (记忆/压缩/调度可视化)

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ljsysfurryACE/dsh-agentframe-plugins#d598f5d09da0c8a474982a3a36176820186202ad&path:packages/agentframe-suite
@agentframe/dsh-aura-scheduler

Proactive scheduling v2: value network + file/process/http sensors + HMAC webhook triggers + off-peak window

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ljsysfurryACE/dsh-agentframe-plugins#d598f5d09da0c8a474982a3a36176820186202ad&path:packages/aura-scheduler
@agentframe/dsh-compaction

AgentFrame compaction backend for DeepSeek Harness: semantic + physical KV compression (28.4x) replacing LLM summarization

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ljsysfurryACE/dsh-agentframe-plugins#d598f5d09da0c8a474982a3a36176820186202ad&path:packages/compaction-agentframe
@agentframe/dsh-compaction

AgentFrame compaction backend for DeepSeek Harness: semantic + physical KV compression (28.4x) replacing LLM summarization

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ljsysfurryACE/dsh-compaction
@agentframe/dsh-memory-director

MemoryDirector plugin for DeepSeek Harness: LLM-driven remember/forget across turns (the official harness has no memory concept)

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ljsysfurryACE/dsh-agentframe-plugins#d598f5d09da0c8a474982a3a36176820186202ad&path:packages/memory-director
@agentframe/dsh-memory-director

MemoryDirector plugin for DeepSeek Harness: LLM-driven remember/forget across turns (the official harness has no memory concept)

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ljsysfurryACE/dsh-memory-director
@aiwayds/dsh-llmwiki-memory

dsh-plugin: OKF v0.2 topic memory for dsh - local-first git-tracked bundle, hot-path LLM-free injection, two-stage observer with background distill

Memory and knowledge · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fan56/dsh-llmwiki-memory
@aiwayds/dsh-topics-memory

dsh-plugin: OKF v0.2 topic memory for dsh - local-first git-tracked bundle, hot-path LLM-free injection, two-stage observer with background distill

Memory and knowledge · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fan56/dsh-topics-memory
@akslcw/dsh-negative-ledger

Agent negative-knowledge ledger for DeepSeek Harness: records failed paths with evidence hashes and retry conditions, auto-invalidates on evidence change.

Memory and knowledge · Agent collaboration · Developer tools
@bananiceee/dsh-zhushou

DSH 侧边栏助手插件(dsh-zhushou):在侧边栏管理/选择助手,选中后在 DSH 主会话内直接以助手人设/模型/参数对话;不选则保持原生会话。A DSH sidebar assistant plugin: manage and pick assistant personas in the sidebar, then chat with them inside the main DSH session; leave it unselected for the native experience.

Memory and knowledge · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Starlight-bananice/dsh-zhushou
@blake-r/dsh-tool-trajectory-recall

Model-facing same-session recall/search tools over the durable session log.

Memory and knowledge · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:blake-r/dsh-plugins#585c40b34c69d84da20592d9b396bd78b4fafb30&path:packages/dsh-tool-trajectory-recall
@botharness/core

BotHarness core: PersonaBot registry, memory, and state

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:BotHarness/BotHarness#938a0d93d9d52c2a9e6503a793b3b5b01af54234&path:packages/core
@bryan-cmf/dsh-infra-bootstrap

DSH-Plugin: minimal infrastructure entry — infra_status / infra_bootstrap tools that probe the mounted infra stack (memory, observability, search, skills) and report readiness.

Memory and knowledge · Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Bryan-cmf/dsh-infra-bootstrap
@bryan-cmf/dsh-vector-memory

DSH-Plugin: durable agent memory core — mem_save / mem_search / mem_health tools backed by the DSH storageDomain (durable, survives restarts), plus a 記憶 view tab.

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Bryan-cmf/dsh-vector-memory
@catheadowl/dsh-extras

Curated extras for dsh: one npm package, several independent plugin modules — gates (turn-close quality gates), markdown (md_rename tool + doc-link gate), prompt (declarative prompt injection), routes (any_nav knowledge routing). `dsh plugin add @catheadowl/dsh-extras` installs them all; per-row `disabled` turns one off.

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:CatheadOwl/dsh-extras
@chenqiuyushuang/dsh-nexus

Nexus — a zero-config, cost-protected memory layer for DeepSeek Harness

Memory and knowledge · Financial data · Interface extensions
@companion-memory/dsh-plugin

伴侣记忆内核的 DeepSeek Harness 适配器:提示词分区、回合上下文与记忆工具。

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AkinoHaruka/companion-memory#ba7b34aecde5ef8b7b2b9ac6282148efb9cf6be7&path:packages/dsh-plugin
@companion-memory/host

面向 DSH 路由的 Companion Memory 因果链产物 Oracle 评估器。

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AkinoHaruka/companion-memory#ba7b34aecde5ef8b7b2b9ac6282148efb9cf6be7&path:packages/host
@creative-dswork/dsh-expmem

Experience Memory for DeepSeek Harness

Memory and knowledge · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:creativedswork/dsh-expmem
@deepseek-ai/dsh-client-coral-board

Coral reasoning-thread task board: bottom-right capsule over shell.overlay showing active threads + done-candidates from coral_threads.json (node half reads the file, zero model tokens, read-only)

Memory and knowledge · Agent collaboration
@deepseek-ai/dsh-client-ui-balance

API balance capsule: bottom-right floating pill over shell.overlay, node half queries configured provider balance endpoints (zero model token cost), multi-API entries with add/remove

Memory and knowledge · Agent collaboration · Financial data · Interface extensions
@deepseek-ai/dsh-dify

Dify agent and knowledge-base capability for the DeepSeek Harness — the ctx.dify Service Definition, an HTTP Service Provider, and the model-facing dify_chat and dify_retrieve tools

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:staff-os/dsh-dify
@deepseek-ai/dsh-ragflow

RAGFlow knowledge-base retrieval capability for the DeepSeek Harness — Service Definition, HTTP API provider, and model-facing ragflow_retrieve tool

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:staff-os/dsh-ragflow

Find the right plugin, then get started

  1. Search by task

    Use a feature keyword or category, then sort by recent updates or GitHub stars.

  2. Explore capabilities

    Read the description, AI analysis and original README to understand what a plugin does.

  3. Check and install

    Review compatibility, dependency ranges and instructions, then copy the available install command.

Questions about DSH Hub

What is DSH Hub?

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.

Does inclusion mean a plugin is tested and compatible?

No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.

How do I install a plugin?

Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.