dsh-move-rag
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
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.