Memvid Rag — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Memvid Rag (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
Aggregate score unchanged between these scans.
The primary manifest — the file an agent reads to learn what this artifact does.
Agent 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-skillsPlace 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:createAdd PDF documents to the knowledge base:
/memvid-rag:index ./documents/research-paper.pdfQuery 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
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.