Auto-discovered marketplace from fa-ina-tic/memvid-rag
npx claudepluginhub fa-ina-tic/memvid-ragSimple Local RAG based on memvid
fa-ina-ticAgent Skills for local RAG (Retrieval-Augmented Generation) using memvid-sdk.
These skills follow the Agent Skills specification so they can be used by any skills-compatible agent, including Claude Code and Codex CLI.
Install via Claude Code plugin marketplace:
/plugin marketplace add fa-ina-tic/memvid-rag
/plugin install memvid-rag@memvid-rag-skills
Place the contents of this repository in a /.claude folder at your project root. See the Claude Skills documentation for details.
Copy the skills/ directory to ~/.codex/skills following the Agent Skills specification.
pip install memvid-sdkCOHERE_API_KEY - Cohere (default)OPENAI_API_KEY - OpenAIVOYAGE_API_KEY - Voyage AINVIDIA_API_KEY - NVIDIAThis plugin enables semantic search over PDF documents:
| Command | Description |
|---|---|
/memvid-rag:create | Create a new knowledge.mv2 index file |
/memvid-rag:index | Index PDF documents with vector embeddings |
/memvid-rag:search | Search indexed documents semantically |
/memvid-rag:status | Show RAG system statistics |
Initialize a new knowledge base:
/memvid-rag:create
Add PDF documents to the knowledge base:
/memvid-rag:index ./documents/research-paper.pdf
Query your indexed documents:
/memvid-rag:search What are the key findings?
/memvid-rag:search How does the algorithm work? --k=10 --mode=sem
--k=<number> - Maximum results (default: 5)--mode=<lex|sem|hybrid> - Search mode (default: hybrid)--snippet_chars=<number> - Max characters per snippet (default: 240)--min_relevancy=<float> - Minimum relevancy threshold--adaptive=<true|false> - Enable adaptive result countAll indexed data is stored locally in a knowledge.mv2 file in your working directory.
MIT