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。
98 个项目，匹配「ai」
Xieweikang123
Give a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.
cnChenKai
Tavily-backed WebSearchProvider for DeepSeek Harness (ctx.web) - keyless mode, no API key required
cwbcheng
DSH Cordis plugin: turn any source text into an AI knowledge graph (facts/inferences/concepts/definitions/examples/counter-examples/rules) with two-way linking between the graph and the original text.
djasdh
Low-footprint memory backend for AI agents — single binary, ~50MB RAM, verify-augmented accuracy
dongsheng123132
Content-addressed proof that a DSH profile declaration, pnpm lock and installed bundles agree
dttxorg
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.
haiziyao
Vision routing and image generation for DeepSeek Harness through a fixed Mix model.
lingxin-maz
DeepSeek Harness (DSH) plugin status panel & profile ops console: pending-restart (SSE), one-click restart, multi-profile sync install (web+desktop), supply-chain preview, rollback/undo, updates/align, health, diff, boot report, audit log & agent tools.
mochgolf
Transparent image preprocessing route for DeepSeek Harness
moguiyu
Tavily Search for DSH: multiple API keys, rotation/failover, usage gauge, settings card. | DSH Tavily 搜索：多 Key、轮换/故障转移、用量仪表盘、设置卡片。
nyantused-cpun
兰亭 (Folio) · 咨询材料生成引擎：15 个 DSH 原生工具 + 会话协议自动执行 + L0 守卫 + 可换方法论包，零 key 起步。Consulting material engine for DeepSeek Harness: HTML/PPT/DOCX/quote with mechanical quality gates, bilingual demo outputs in the v1.0.2 release. Help wanted: Word layout, Excel formatting/formulas, Linux/mac ports.
querit-ai
Official Querit search plugins for AI agent harnesses: pi-querit (Pi extension), dsh-querit (DeepSeek Harness web seam), opencode-querit (OpenCode plugin)
shaoqiuyuavailable
Scene-aware vision routing layer for DeepSeek Harness (dsh): decides which engine/backend an image should go to (chat/UI/table/code) before other vision plugins route it. Switch-gated, front-loaded, never touches other plugins' tools. 场景级识图路由层。
tiefeiyu
A see_image vision tool plugin for DeepSeek Harness — describe images through any OpenAI-compatible vision model (GitHub Copilot, OpenAI, Ollama, vLLM, LM Studio).
uknowmyface
Local OCR for DeepSeek Harness — read text from screenshots on your Mac with Apple's Vision framework. No API key, no upload.
wjwjw
Workspace file explorer plugin for the DeepSeek Harness web GUI
xiaozhe7772222
Universal image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint. Supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more. | DeepSeek Harness 统一绘图路由器
xzyonline
Session-bound file attachments for DeepSeek Harness: drag, paste, or select files into the chat; the agent reads them via bounded, session-authorized tools. GB18030/GBK decoding, secret redaction, zip-bomb defense. One-click install. | DeepSeek Harness 会话文件附件插件：文件拖入/粘贴/选择进对话，模型经会话授权工具受限读取。GB18030/GBK 中文编码、敏感信息脱敏、压缩炸弹防护。一键安装。
54xkeee
Eyes for text-only DeepSeek on DeepSeek Harness: model-invokable vision tool + wrapper adapters + general VLM channels (OpenAI-compatible / Gemini / local Ollama)
Aidenwu0209
Unlimited-OCR for DeepSeek Harness with a native tool and GUI configuration
Jeffine322
DeepSeek Harness (dsh) plugin - read_pdf tool for PDF text extraction. Read and extract text from PDF files with AI agents / LLM tools, built on PDF.js (unpdf).
Koreyer
A DeepSeek Harness tool plugin that lets text-only agents "see" local images — auto-detects the real format and returns a detailed text description via any OpenAI-compatible vision model.
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).
ZhuXinAI
CLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.