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。
70 个项目，匹配「pi」
benz-ai-x
DSH Research Graph · 研图 — DeepSeek Harness plugin for research topics, traceable knowledge cards, and reusable AI discussions.
everclear077
Progressive tool discovery for DeepSeek Harness — tiny stable surface, searchable catalog, real pipeline execution, context cache intact.
KLRSL
dsh-memory-layer：给 DeepSeek Harness 的「记忆层」——本地单文件 SQLite、触发式召回、五条可解释清理规则、工作流链；零服务、零 API、零遥测。A memory layer for DSH: local SQLite, trigger-driven recall, explainable cleanup, workflow chains.
Lee-Hilex
基于 MinerU 的 DeepSeek Harness 多模态文档解析插件：PDF/Word/PPT/Excel/HTML/图片 → 结构化 Markdown（免 Token 的 Agent 轻量解析 / 精准解析双 API 模式）
PianoPrince
拖拽真迁移 DSH 会话跨工作区：批量移动、分组合并、挂错归位、回收站、备份恢复 + 对话内 agent 工具；步步备份可回滚，零 token / True migration of DSH sessions across workspaces: bulk move, group merge, misfiled homing, recycle bin & backup restore + conversational agent tools; every step backed up, zero tokens
Saktawdi
DeepSeek Harness（dsh）动态 Cordis 插件：模型高可用回退 + 五种模式子智能体编排（fanout / pipeline / supervisor / map-reduce / router）
gusibi
A memory-first personal AI Agent that grows with your work.开源、开箱即用的 AI Agent。
joekytc
Run multi-agent task pipelines on DSH like a team — plan, execute, review, and deliver code through a visual kanban with provable completion.
linkbag
Role-based AI swarm orchestration for DeepSeek Harness: per-role model pinning with fallbacks, parallel task DAG with review loops, live Swarm dashboard tab.
skepsun
极简·省 token 的 DSH 长期记忆插件：零 LLM 自动捕获、符号索引渐进披露、ESR 证据闭环。Minimalist token-saving memory for DeepSeek Harness: zero-LLM auto-capture, symbolic index, ESR-lite evidence closure.
stas130286-blip
BrainAgent — brain-inspired plugin for DeepSeek Harness (dsh): a pipeline of heuristic filters, statistical memory stores and context injections; reward-ledger + UCB1 bandit learning loop (RL-lite). 915 tests. Free noncommercial use.
Ottohere-Mourn
Teach once, replay anywhere — harness-agnostic Teach-by-Demonstration engine (Record → Compile → Replay → Verify) with OpenMausBot and DeepSeek Harness integrations.
kiligzzz
Piano-key style in-conversation navigation bar for the DeepSeek Harness web GUI: one key per user message, hover preview tooltip, click-to-jump across full history. Official dual-face dsh plugin, no dsh source changes.
Epsirom
TypeScript runtime for LLM agent graphs with bounded loops, live updates, isolated Git worktrees, and explicit integration. Framework-agnostic core, OpenAI-compatible runner, and plugins for Pi and DeepSeek Harness.
EternalNight996
🧑💼为 DeepSeek Harness Web 主窗口添加「工作角色」页签 + 「像素办公室」浮层：内置 508 张完整角色卡（The Agency 255 + agency-agents-zh 253），支持搜索 / 中英切换 / 分部分类选人；Canvas 2D 像素小人可站立、打字、踱步，浮层可拖动折叠缩放，选人即入列；闲聊台词可接 AI（内置或外部接口，20 字内中文）。npm 双面包 + cordis 组合补丁层（dsh.bundle.patch），一条命令安装，不改 dsh 源码，重启不丢。
H97y
Automated development pipeline plugin for DeepSeek Harness: requirement pool → LLM refine/design/plan/review → workspace-routed implementation → verify → merge → report
NattoCB
dsh-plugin-memory: a persistent 5-layer memory system plugin for DeepSeek Harness (DSH) — index+topics split, truncation budget, relevance injection, idle LLM auto-extraction, and 6 agent tools.
WenhongPan
Project and session organization for DeepSeek Harness: multi-folder projects, searchable chats, attention summaries, and native folder picking.
geguanming
DSH Ox-Horse Office - a DeepSeek Harness web plugin rendering multi-agent sessions as a live pixi.js office
itcraft-cn
Local-first AI memory with project isolation — for terminal, for private use
twoyoung91
Local personal memory and knowledge management for DeepSeek Harness. It supports local FTS, CPU-embedding or OpenAI-Compatible Embedding API.
SZMY-haruhi
为 DSH 新增 Tavily 搜索 API，作为其网页搜索服务提供商。Adds Tavily Search API as a web search provider for DSH.
Spirtxiaoqi7
Editable, session-isolated personalization memory for DeepSeek Harness
derekhu0002
ArchGraph — an architecture-graph driven framework for Agentic Engineering. A long-term memory for coding agents, built on one ArchiMate 3.2 intent graph read/written through a single MCP interface.