Discover The Best DSH plugins

Memory and knowledge · DeepSeek Harness plugins — Page 20

2467results

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

@toustifer/agentflow

Lifecycle orchestration engine for AI agent teams on DeepSeek Harness with task-scoped Git worktrees, state-gated delivery transitions, and off-context memory.

Memory and knowledge · Agent collaboration · Developer tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:toustifer/agentflow
@towzai/dsh-memory

DSH 跨会话记忆插件 | Cross-session memory plugin: YAML 存储、embedding 语义检索、标题优先注入、两级自动注入

Memory and knowledge · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Towzai/dsh-memory
@yansera/dsh-living-memoir

Long-term memory for DeepSeek Harness: a short, categorized Markdown living document that gets rewritten instead of appended to, with a dedicated Web GUI page.

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Yansera/dsh-living-memoir
@zhang-zhengyuan/dsh-tool-memory-amem

A-MEM style long-term memory for DeepSeek Harness with guarded auto-capture, hybrid retrieval, prompt recall, four model-facing memory tools, and a four-stage admission gate (rule filter + semantic dedup + trust score + retrieval-time rerank hook) tuned against the OWASP ASI06 memory-poisoning family.

Memory and knowledge · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Zhang-Zhengyuan/dsh-memory-amem
@zleap-ai/dsh-sag

Local SAG personal knowledge base plugin for DeepSeek Harness

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Zleap-AI/dsh-sag#15b1363a24b18394dfcd85172fa68d66030b9482&path:packages/dsh-sag
aifp-mcp

AiFP Cognitive Memory — persistent memory MCP server for AI assistants. Chinese-first retrieval with causal chains, Hebbian associations and graph diffusion. 记忆感知系统

Memory and knowledge · Agent collaboration · Developer tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wjabanjj/aifp-mcp
companion-one

自包含陪伴单体插件:内置上下文压缩、七层记忆、陪伴行为层、沟通风格学习与可塑人格。

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:27Synthesis/dsh-companion-one
dsh-agent-memory

Agent-driven long-term memory for DeepSeek Harness: scoped memory (global + per-workspace), layered entries (fact/knowledge/episodic), time-bucket compaction (day→week→month→year), agent-decided content.

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jonah791/dsh-agent-memory
dsh-agentic-rag

Agentic RAG for DeepSeek Harness: three-path retrieval (hybrid/graph/wiki), document continuation reading, and a knowledge-base management panel over the built-in or external knowledge service.

Memory and knowledge · Agent collaboration · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chenzhiya77/dsh-agentic-rag
dsh-ai-memory

dsh Cordis bundle (npm name: dsh-ai-memory) over the Rust crate in this repo (Cargo.toml package name: ai-memory). Not a JS memory rewrite.

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zzjzzb/ai-memory
dsh-arcaea-theme

An original high-key prismatic memory theme for the DeepSeek Harness web UI.

Memory and knowledge · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:a1swg1159-pixel/dsh-arcaea-theme
dsh-assist

Portable personas, private memory, and opt-in idle chat for DeepSeek Harness Desktop.

Memory and knowledge · Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:a740411040/dsh-assist
dsh-awesome-hud

DSH Web/桌面端插件:聊天页右上角「HUD面板」悬浮面板,新建会话页提供右上角悬浮入口并在该页恒为收起(面板位置与已有会话一致),面板开合状态按会话独立记忆,展示会话状态、上下文窗口占用与一键压缩、git 分支与变更、子代理任务、待办任务、计划清单、MCP 全局启停(含 codex gpt-reserve 额度行);git graph 右键菜单可基于指定提交创建并切换到新分支;「便笺」按工作区共享并支持二次确认清空,「待办」按工作区共享;与 better-sidebar 右侧栏互斥协作,模块可见性可在 HUD 设置菜单中按 profile 持久化。

Memory and knowledge · Agent collaboration · Interface extensions · Developer tools · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Ycet/dsh-awesome-hud
dsh-brain-compaction

人脑式上下文压缩逻辑 — DeepSeek Harness 上下文压缩统一协同层: 集成 dsh-argp / dsh-compaction-instant / dsh-headroom / dsh-sgme / dsh-memory-vault / dsh-mcp-lens / dsh-context-doctor,提供统一配置、工具协调与验证机制。适配 DSH 0.1.5。

Memory and knowledge · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Lsc-91-69/dsh-brain-compaction

dsh-btw

★ 2
dsh-btw

Global /btw command: one-off model Q&A that is not recorded into session memory (Claude Code /btw equivalent)

Memory and knowledge · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:clclyzybzjsq/dsh-btw
dsh-cc-dream-memory

Claude Code-style auto memory and reviewable Dream consolidation for DeepSeek Harness. Community plugin, not affiliated with Anthropic.

Memory and knowledge · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add dsh-cc-dream-memory
dsh-character-studio

DeepSeek Harness native immersive roleplay studio & companion system. Unifies decoupled character cards with Hindsight graph memory.

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Ryu6Zero/dsh-character-studio
dsh-codebase-memory

DeepSeek Harness plugin: persistent per-workspace codebase knowledge memory (memory_store / memory_recall / memory_forget / memory_list tools, /memory command), stored in a project-file JSON store.

Memory and knowledge · Financial data · Productivity
dsh-codevault

A DeepSeek Harness (dsh) plugin that records what you understood while reading open-source code: quick-capture notes or full deep-reading notes, grouped into one card per repo / file / symbol, stored as Markdown + JSONL you can open in Obsidian; query past reads and link cards to notes already in your own Obsidian vault. 中文名:源码阅读档案。

Memory and knowledge · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:1014029855/dsh-codevault
dsh-conversation

Conversation outline panel for the DSH web surface: user questions (index, time, per-turn stats) as level-0 nodes with the assistant reply's Markdown headings hanging beneath them — level slider, search scope, bookmarks, copy/export, section jump, keyboard nav and reading-position memory. Read-only UI: it never touches prompts, messages, tool results or provider traffic, and it writes nothing outside its own localStorage keys.

Memory and knowledge · Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:huangfuren/dsh-conversation
dsh-ctf-ui

CTF and security analysis skills for DeepSeek Harness (DSH): supervised continuable Solvers, scoped structured memory, durable task state, and evidence review. TSecBench v1 local mode: 96.94, 71/74 flags. 持续型子代理编排、结构化记忆与证据复核。

Memory and knowledge · Skills · Agent collaboration · Interface extensions
dsh-cultivation

角色养成:为 Agent 赋予可养成的 AI 角色(角色扮演 + 情感陪伴)——会话级角色绑定、亲密度随对话成长、分区记忆 + 追加日志自动归档、AI 设计助手。

Memory and knowledge · Agent collaboration · Productivity
dsh-dafeiyu-life

大肥鱼 · DSH 生活系统:主 Session 可回忆人生记忆与真实经历、管理自主待办,并按权限使用 B站读取与互动;支持低成本 AI 维护本地表情包检索规则与兴趣感知排序。

Memory and knowledge · Agent collaboration · Financial data · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:minedalang/dsh-dafeiyu-life

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.