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。
456 个项目，匹配「mode」
Youngxj
DeepSeek Harness 项目组插件
YuanyuanMa03
Curate tool output before it enters the model's context — keep error/warning lines and head/tail, spill the full text with a pointer. ~24x smaller model view, measured. For DeepSeek Harness.
ZChenW
ChatGPT OAuth, multi-account switching, and Codex models for DeepSeek Harness.
acdcgz
SearXNG-backed WebSearchProvider for DeepSeek Harness (ctx.web) — self-hosted, zero per-search model cost, multi-engine aggregation
arcships
DeepSeek Harness (dsh) LLM adapter backed by aimux — one Rust engine, 325+ providers as dsh model routes
bitterSmilezzz
DSH 模型流式缺陷修复：opencode 端点 muse-spark-1.2 不发送 finish_reason/[DONE]，llm/stream 收尾改 stop（直连可用、不触发重试）
bpc-oss
DeepSeek Harness plugin: subagent_routed — run a one-shot subagent fully mounted on ANY agent preset from ANY session, with per-call model/provider override and a model-availability pre-check.
br1nosense
让 DeepSeek Harness (DSH) 纯文本模型也能发送并识别图片：识图技能（火山 doubao）+ 宿主补丁。Vision + host patch for DSH text-only models.
chou109
dsh-vision-bridge：在 DeepSeek Harness 聊天框粘贴图片，任意模型都能看懂——纯文本模型自动转成图片路径并调用 vision_chat 识图，支持图片的模型直接接收原图。粘贴即用，自动识别、自动回答。dsh-vision-bridge: paste any image into the DeepSeek Harness chat box — every model can see it: text-only models get an automatic vision_chat bridge, vision-capable models receive the image directly. Paste, send, done.
coderdailyone
Security-first browser automation plugin for DeepSeek Harness (dsh) — 15 tools, policy re-checked on every action, no model-controlled paths
ddll8023
Session access-mode plugin (Default / No Edit / Auto) for DeepSeek Harness (DSH). dsh-plugin
dingminhua
该仓库暂未提供项目说明。
dshplugin-me
Evidence-backed working memory for DeepSeek Harness: a cited ledger of what already worked in this workspace, built from the session log you already have. No index, no model, no capture step.
fineven
Zhipu BigModel all-in-one plugin for the DeepSeek Harness: web search (web_search_prime) + web reader (webReader, server-side rendered) + GLM-4.6V vision (vision_analyze + pasted-image hook), one ZAI_API_KEY
fonlan
该仓库暂未提供项目说明。
fulander0301
Model-facing read_tiff tool for DeepSeek Harness: decodes TIFF/TIF images (multi-page, LZW/Deflate/PackBits/CCITT/JPEG compression, bilevel, 8/16-bit and float) into viewable PNGs with full header metadata, plus optional vision-model description.
grasir-ctrl
Give DeepSeek Harness eyes: one-click install the dsh-plugin-deepeye vision plugin with the free Zhipu GLM-4V-Flash model. Paste images into text-only LLMs
hZsFN
Image message bridge for text-only models in DeepSeek Harness (dsh): image blocks → text placeholder + local path, vision via qwen script
hanchn
A zero-config, multi-provider vision tool for DeepSeek Harness with automatic local model discovery and privacy-aware remote fallback.
jacujay
DSH plugin: auto-detect current model vendor and show balance/quota in the composer input row (DeepSeek/Moonshot/MiniMax/StepFun/Zhipu/SiliconFlow/OpenRouter + custom endpoints)
jiangr100
DeepSeek Harness plugin: switch a session's agent preset (Standard / Code / Minimal / Creator) mid-conversation, straight from the session header.
jiaoqsh
DeepSeek Harness plugin: read_document tool — Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF as Markdown for the model
jin123-alpha
External vision proxy extension for DeepSeek Harness, enabling text-only models to analyze and understand images via OpenAI-compatible vision APIs.
julygotostudy
DeepSeek Harness 模型余额悬浮层插件：实时显示 API 账户余额与上下文占用率