awesome-dsh-plugin
dorisaimpatient855
Curated plugins for DeepSeek Harness (dsh) — install, extend, and customize models, tools, sandboxes, UI, and agent loops.
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。
142 个项目,匹配「models」
dorisaimpatient855
Curated plugins for DeepSeek Harness (dsh) — install, extend, and customize models, tools, sandboxes, UI, and agent loops.
gaoqiaoliangjie666
将 QwenWork 桌面 App 包含的模型自动接入 DeepSeek Harness,零配置使用。Bring the models in the QwenWork desktop app into DeepSeek Harness with zero configuration.
hi-fangj
Model capability radar plugin for the DeepSeek Harness Web GUI
mtty-ai
MiniMax token-plan quota dock for DSH web — drop-shape 5h usage %, click for detail panel, auto-hides for non-MiniMax models
nlqh7
给 DeepSeek Harness 纯文本模型加视觉:采用codex风格聊天框拖图自动分流给用户配置的视觉模型转文字,v4 不切换模型即可识图。 Vision for text-only DSH models: routes chat-box images to a user-configured vision model and returns text descriptions, deepseek-v4-pro reads images without switching.
reimu-create
DSH plugin: text-only models (e.g. DeepSeek-V4) automatically see images via a vision model. Official surface-replace, cache-friendly, human transcript untouched. 纯文本模型自动识图桥
sudipnext
ChatGPT OAuth and Codex models for DeepSeek Harness — browser callback, device code, no API key, no pi-ai
vitas
Model pricing & capability board for DeepSeek Harness: ~7,250 models across 213 providers, honest lowest-listed comparison, session costs priced by the route you actually called, and cache-leak attribution. Local-first, no server.
x5427876
Use OpenCode Zen free models in DeepSeek Harness with anonymous access or an optional API key
xiaoxianyu-office
DSH bundle plugin: chat-image bridge + read_image deny + conversational image_recognize for text-only main models | 纯文本主模型识图桥接与识图工具
ximengxiaolan
Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????
yakoylp
Convert Office documents and PDFs (incl. scanned, via CPU-first routing OCR with lightweight models: PP-DocLayout-L layout, RapidOCR text, SLANet tables, FormulaNet formulas) to structurally-formatted Markdown. CLI + dsh agent tool (md_convert).
yoshino-xiao7
DeepSeek Harness 的社区 Grok Build Provider:官方 CLI 浏览器 OAuth、动态模型、流式工具调用与额度面板。Community Grok Build provider with official CLI OAuth, dynamic models, streaming tools, and a quota dashboard.
zclDragon
dsh plugin: generate_image tool for text-only models via the Antigravity CLI (Gemini image generation).
CroissanTTs
[百炼(DashScope)模型目录预置插件]Alibaba Bailian (DashScope) model catalog preset for DeepSeek Harness — 36 models with per-family reasoning effort adaptation, context windows, and auto-adaptation of existing Bailian routes.
JD962
This plugin was developed using DeepSeek Harness and the DeepSeek V4 Flash 0731 / Pro 0813 models, with multiple rounds of refinement. It enhances the existing sub‑agent functionality and adds several other features.
Leeminjing
Give text-only DeepSeek models on-demand vision: upload images, DeepSeek answers by calling a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).
Lzh3070
DeepSeek Harness 插件:模型可见性管理——按渠道/模型隐藏或显示模型选择菜单里的条目 / Control which models appear in the DSH model selector
MYCF711
Qoder models in DeepSeek Harness (DSH) — three-tier model catalog, credential failover, OpenAI-compatible shim, settings card
Movingelated
DSH (DeepSeek Harness) plugin: delegate read-only collection tasks to a local Ollama model — zero cloud token cost, zero API key. 把只读采集任务交给本机 Ollama 模型:含设置面板 + 选型尺 + AI 可读说明书。
Mrlilili
⌨️ DSH 插件:快捷键切换模型 (Ctrl+Shift+M) 和推理等级 (Ctrl+Shift+R)。纯客户端实现,无需 Host。 DSH plugin: keyboard shortcuts to cycle models (Ctrl+Shift+M) and reasoning effort levels (Ctrl+Shift+R). Pure client bundle, no Host required.
Rock-ql
DSH relay plugin: reasoning-effort autofill, /models sync, capability-aware Fast toggle | DSH 中转站思考等级与 Fast 开关插件
TNTsama11
DeepSeek Harness (DSH) plugin that lets a text-only agent call DeepSeek-V4-Flash-Vision-Exp to see images on demand, without manually switching models.
TwistedRiCen
DSH-native Vision Evidence bridge for text-only reasoning models with native image attachments and strict multi-image validation.