AI Agent Hub
Back to plugins
dsh-move-rag preview

dsh-move-rag

Memory Updated 2026.09.11

Run the following command in DeepSeek Harness:

dsh plugin install xingmen-1/dsh-move-rag

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install xingmen-1/dsh-move-rag in the DeepSeek Harness terminal to install the dsh-move-rag local knowledge-base plugin from https://github.com/xingmen-1/dsh-move-rag.

About this plugin

Your desktop is buried in PDFs, Word docs, code snippets, and tech notes, yet finding the right piece still means digging through folders or Googling. dsh-move-rag turns that into a single drag-and-drop: toss a file onto a pinned desktop icon and it extracts text, chunks it, builds a 512-dim hash embedding, and writes a cosine index—all local, no cloud vector store, no model weights to download.

The panel ships with a search box that returns source files, similarity scores, and context snippets. Right-click the icon to expand the panel or open the web sidebar. For the agent, two tools (knowledge_search and kb_dev) let the model query your corpus on demand, effectively plugging a private RAG backend into every conversation.

It suits Windows developers who accumulate local documentation and prefer an offline, zero-dependency workflow, as well as anyone who wants to attach a personal knowledge base to DeepSeek Harness without standing up a separate vector service.

Screenshots

Use Cases

  • Drag scattered PDFs, Word docs, and code files onto the desktop icon so the agent can search your private corpus instantly
  • Answer questions over local documents in an air-gapped or offline environment with zero cloud vector-store dependency
  • Check whether your knowledge base already covers a topic before asking the model, grounding answers in your own notes

Best For

  • Windows developers who accumulate a large local document library and prefer offline retrieval
  • Individuals who want a private document backend for DeepSeek Harness without operating a separate vector service
  • Privacy-sensitive small teams that require a zero-cloud-dependency workflow