dsh-hud
a903067276-rgb
HUD status panel plugin for DeepSeek Harness (dsh) web: git status, MCP servers, skills, model & token usage in a floating panel
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。
802 个项目,匹配「mod」
a903067276-rgb
HUD status panel plugin for DeepSeek Harness (dsh) web: git status, MCP servers, skills, model & token usage in a floating panel
avdergh
Research, create, and understand Path of Exile 2 builds with AI agents and Path of Building.
dawnliming
DSH global Chinese-mode toggle: a 中 switch in the input box; when on, a Simplified-Chinese requirement is injected into every session system prompt.
k-ying
DeepSeek Harness 内嵌 VSCode 编辑器插件:嵌入完整 code-server,agent 写文件时自动弹出红绿 diff 跟随(edit sync / file locking / follow mode)
lcestou
Claude Code CLI as an LLM provider for dsh (DeepSeek Harness): live model list, per-session resume, approval relay, images, a memory/rewind/changes panel, and workspaces on remote SSH boxes
ouli-1242
DSH 插件:一个设置面板,统一管理 MCP 服务器、技能、场景、记忆、子智能体人格、AGENTS.md 预设与归档会话——一个场景即可切换整个环境,模型也能帮你驱动这一切。 | DSH plugin: one settings panel managing MCP servers, skills, scenes, memories, subagent personas, AGENTS.md presets and archived sessions — one scene can switch the environment, and the model can help drive it all too.
unknowbug
Modular engineering methodology framework for AI agents — reverse engineering & software development (core + re-binary / re-code / swe modules).
zeng6125-rgb
DSH 插件:LLM 自动重试设置卡片——重试次数/退避/抖动与 25 个错误码可勾选(也能自己输入),可按 provider/model 单独设策略、回答被输出 token 上限截断时自动续写且提示词可改,内置重试观测面板,改完实时生效。
ziduup
DeepSeek Harness 编程模式组合包:标准模式之上强制执行 Superpowers 工程纪律(TDD、系统化调试、先计划后编码、完成前验证、代码审查)与常驻 Ponytail 代码量纪律,内置 20 个技能(14 superpowers + 6 ponytail),dsh plugin add 一键安装。
1225Sakura
Multi-agent orchestration layer for DeepSeek Harness (omd) — autopilot/ralph/team modes, 19 role cards, 40 bilingual skills, bundled MCP state server. OMC/OMX adaptation.
54xkeee
Vision for DeepSeek Harness: Doubao Web by default (zero-cost, no API key), Antigravity IDE quota (flash/pro), any IDE CLI, Gemini — auto detail escalation, evidence memory
AKS1st
统计各模型 tokens 消耗并估算费用,显示账户余额 | Model token usage stats and cost estimation with account balance for DSH
BOWLUNA
Edit a DeepSeek Harness (dsh) custom mode: system prompt, base mode, and plugin switches.
BertramWang12399
Project mode plugin for DSH Web GUI: sidebar entry, full-screen project manager, live per-project context injection (instructions + refreshable memory), session badge
CHplus0
A DeepSeek Harness (DSH) agent preset that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style. 学习模式
Cavan-Ou
Battle-tested multi-agent collaboration playbook for DeepSeek Harness: model-tier routing, spec discipline, git single-writer rule — as an installable skill. 多 agent 管线里运行 DSH 的实战协作规范
HaoyueQin
[maintenance mode] A desktop shell for DeepSeek Harness — the pluggable AI agent harness from DeepSeek. Wrap the official dsh web UI into a native-feeling, always-on desktop app. / 为 DeepSeek Harness(DeepSeek 开源的可插拔 AI agent harness)打造的桌面应用壳,把官方 dsh web 界面包装成原生质感、常驻后台的桌面应用。
JerryLiu369
Agent-native multi-provider web search for AI agents (Claude Code, Hermes, DeepSeek Harness, OpenCode, Codex). Model grounding (Responses, ARK) + semantic search (Exa, Parallel) + keyless defaults via MCP, CLI, and DSH plugin.
Letter2025
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
NEVSTOP-LAB
DSH 审批模式插件,在 DSH 窗口的权限下拉框(Read Only / Workspace Write / Full Access)旁边加一个「审批模式」按钮,在 Workspace Write 模式下工具调用自动放行
NOirBRight
ChatGPT Codex login, sortable catalog, and Fast models for DeepSeek Harness
OrinVoss
DSH Math Modeling Team Plugin Pack: 2 role agent presets (modeling-coding / paper) for DeepSeek Harness, multi-folder Git collaboration + vision sub-agent; includes a full run on 2023 CUMCM-C. | DeepSeek Harness 数学建模团队插件包:2 套岗位Agent预设(建模编程+论文)、多文件夹协同+识图子代理,含2023国赛C题全流程跑通示例。
PerryLink
Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.
Tikzen
Interactive multi-agent collaboration, meetings, group chats, and task execution for DeepSeek Harness.