dsh-simple-wiki-memory
rainow
DSH的简化版llm-wiki记忆插件,纯md文档。A lightweight long-term memory framework for DeepSeek harness, simplified LLM-Wiki. No RAG, no vector DB, no LLM calls at runtime. Just Markdown + git.
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。
125 个项目,匹配「db」
rainow
DSH的简化版llm-wiki记忆插件,纯md文档。A lightweight long-term memory framework for DeepSeek harness, simplified LLM-Wiki. No RAG, no vector DB, no LLM calls at runtime. Just Markdown + git.
AngelosZou
Workspace-scoped Python virtual environment management for a DeepSeek Harness project — discover, create, install into, and remove virtual environments without sandbox, network, or subprocess pitfalls.
Dbi-Eshuh
Customize DSH Web thinking status with custom flowing text, animated GIF/APNG/WebP, or combined image-and-text modes.
PerryLink
Zero-dependency verification standard for DeepSeek Harness (dsh) plugins — static structure gates (R), cordis contract checks (K), sandbox smoke (D), ecosystem-listing checks (CC). 零依赖 DSH 插件核验标准:静态结构门禁、cordis 契约扫描、无头沙箱冒烟与生态收录核验。
boheastill
MCP server that lets an AI agent see and operate an Android device you own over adb, for app testing and automation. Vision plus UI-tree fusion, for any MCP client.
c-ling
DeepSeek Harness 黄金实时看板与策略诊断插件:Au99.99/XAU/CMB 行情、独立交易日历、招行双边历史、持仓建议与探索性回放。
caomengxuan666
Niubash runtime, sandbox, profile bundle, and Web UI plugin for DeepSeek Harness
chengdb
在 Web GUI 里可视化管理项目的全部能力——Skills、MCP 服务器、快捷消息, 全部支持项目级 / 全局级双作用域,全部可以不离开浏览器完成安装、启停与分发
flyemFSB
滑动变祖器
lkh081231
Let your coding agent SEE what it builds. Cross-platform screenshot feedback for AI agents: an MCP server, a Claude Code hook, and a native DeepSeek Harness plugin that drops screenshots straight into the conversation as images. Python + uv, zero install via uvx. Windows / Linux / macOS.
masknull
DSH 0.1.7 Windows ACL 沙箱在非系统盘工作区下全部命令 spawn 前失败的临时修复插件——不动任何系统 ACL,恢复 workspace-write。 | Temporary fix for the DSH 0.1.7 Windows ACL sandbox failing on non-system-drive workspaces (grantWrite / SetNamedSecurityInfoW Win32 5) — restores workspace-write without touching system ACLs. 支持 DSH 0.1.7-rc.1+。
newborne
Full-featured ADB device management plugin for DeepSeek Harness - control your Android device via AI
FengLingYaaa
DSH plugin: strip leftover GPT sandbox_permissions that are not strictly wider than the current session.
Fisfzy
让 DeepSeek Harness (DSH) 通过原生工具直接操控本机 Abaqus/CAE 的 Cordis 插件。21 个 DSH 原生工具覆盖完整建模链(几何/材料/网格/接触/分析步/载荷/边界/作业/ODB),TypeScript 编写,socket bridge 直连本机(不走 MCP)。
GHJIVHIDD
Docker 容器沙箱部署级插件(与 dsh-plugin-vm-sandbox 全能力对齐,无需 OrbStack):39 个 docker_* 模型工具、快照/回滚、文件传输、端口转发、后台任务、审计、共享/配额/回收、网络策略与华丽原生 UI。
GHJIVHIDD
原生UI界面。面向 DeepSeek Harness Web 的虚拟机沙箱插件:它基于 OrbStack 为每个会话提供独立的 debian/alpine 沙箱虚拟机,在会话视图环中新增「虚拟机」页签,支持查看/启动/休眠/删除和详细配置展示,同时为模型提供 `vm_list`、`vm_create`、`vm_exec`、`vm_delete` 工具,并内置全局运行上限、闲置自动休眠、归档/删除自动清理等资源治理能力。
HuanLinOTO
让模型通过 adb 操作安卓手机的 DSH 插件(截图、UI 树、点击、滑动、输入文本、按键、打开应用) | DSH plugin exposing adb-based tools that let the model operate an Android phone (screenshot, UI dump, tap, swipe, input text, press keys, open apps).
InterPSS-Project
InterPSS Agentic Power System Simulation Agent for AC load flow, DC-based contingency analysis, and NERC TPL style reporting. Integrated into Deepseek Harness as a DSH Plugin, one can run power system simulations in the traditional way in a local sandbox or in the native AI env.
Jyleaves
Windows Git Bash fix for DeepSeek Harness (dsh): MSYS sandbox conflict + terminal inspector, with the minimal-win collective-thinking preset (we/let's chain)
Linxiushen
QuickJS/WASM-isolated workflow engine for DeepSeek Harness with bounded resource controls
PangYiMing
DSH plugin for controlling mobile devices (ADB/iOS) — DeepSeek Harness 操控手机插件
QWQcool
In-process graph memory kernel for DeepSeek Harness, backed by TriviumDB.
SeverusZh
dsh-yolo-mode - an LLM-powered auto-approval plugin for DeepSeek Harness sandbox escalations (built-in presets + custom permission levels, fail-closed)
ZHI-QI
dsh-okf-memory: 会话记忆 → OKF 知识沉淀插件(神经自我学习驱动)。Session-to-OKF memory plugin: predictive recall, uncertainty-driven capture, reinforcement feedback, consolidation & forgetting.