Vector Embed
- 642 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
vector-embed is an agent skill that generates 384-dimensional ONNX embeddings via ruvector for developers who need semantic search, RAG pipelines, or agent memory storage.
About
vector-embed is a ruflo skill that generates and stores vector embeddings using the ruvector npm package at version 0.2.25. It embeds text or files with ONNX all-MiniLM-L6-v2 producing 384-dimensional vectors, normalizes them, and stores results in an HNSW index cited at 52,000+ inserts per second and roughly 0.045ms search latency. Developers reach for vector-embed to embed text, code, or documents for semantic search, similarity comparison, clustering, or claude-flow agent memory via memory_store and memory_search. The argument hint accepts `<text-or-file>` input for direct embedding runs.
- Converts text, documents, and code into dense vector embeddings using leading models
- Supports multiple embedding providers and local models through a unified interface
- Optimized for RAG, semantic search, and long-term agent memory workflows
- Includes batch processing and dimensionality reduction utilities
- Seamless integration with vector databases and agent toolchains
Vector Embed by the numbers
- 642 all-time installs (skills.sh)
- +6 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #1,524 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill vector-embedAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 642 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you generate vector embeddings for RAG pipelines?
Generate high-quality vector embeddings from text, documents, or code for semantic search, RAG pipelines, and agent memory systems.
Who is it for?
Developers building RAG pipelines or agent memory who want local ONNX embeddings via ruvector without external API calls.
Skip if: Teams requiring cloud-hosted embedding APIs or dimensions other than 384-dim MiniLM-L6-v2.
When should I use this skill?
Embedding text, code, or documents for semantic search, similarity comparison, clustering, or claude-flow memory storage.
What you get
Normalized 384-dimensional embeddings stored in an HNSW index for semantic search or agent memory.
- 384-dim normalized embeddings
- HNSW index entries
By the numbers
- Uses ruvector@0.2.25 with ONNX all-MiniLM-L6-v2 384-dimensional embeddings
- HNSW indexing cited at 52,000+ inserts per second
- HNSW search latency cited at ~0.045ms
Files
Vector Embed
Generate and store vector embeddings using the ruvector npm package.
When to use
Use this skill to embed text, code, or documents into 384-dimensional vectors for semantic search, similarity comparison, or clustering. ruvector uses ONNX all-MiniLM-L6-v2 with HNSW indexing (52,000+ inserts/sec, ~0.045ms search).
Steps
1. Ensure ruvector@0.2.25 is available:
npm ls ruvector 2>/dev/null | grep '0.2.25' || npm install ruvector@0.2.25If embed text later reports ONNX WASM files not bundled, also run:
npm install ruvector-onnx-embeddings-wasm2. Embed the input (use the text subcommand, with text as a positional arg):
- Single string:
npx -y ruvector@0.2.25 embed text "your text here" - With output file:
npx -y ruvector@0.2.25 embed text "your text here" -o vec.json - For a file: read its content via the Read tool, then pass it as the positional argument.
- For batch: loop over files in shell — ruvector@0.2.25 has no built-in
--batch/--globflags.
3. Adaptive (LoRA) variant: npx -y ruvector@0.2.25 embed text "..." --adaptive --domain code 4. Confirm — report vector dimension (384), norm, and any output path written. 5. Store metadata in AgentDB if needed: mcp__claude-flow__memory_store({ key: "embed-SOURCE", value: "VECTOR_METADATA", namespace: "vector-patterns" })
MCP alternative
Register the MCP server once with the pinned version:
claude mcp add ruvector -- npx -y ruvector@0.2.25 mcp startThen call MCP tools directly: hooks_rag_context (semantic context), brain_search (collective brain), hooks_ast_analyze, hooks_route.
Caveats
- The
embed --batch --globandembed --fileflags do not exist in ruvector@0.2.25; onlyembed text <text>is supported. Read files yourself and callembed textper file. - ONNX runtime is not bundled by default. If embedding fails, install
ruvector-onnx-embeddings-wasmor runnpx -y ruvector@0.2.25 doctorto diagnose.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What embedding model does vector-embed use?
vector-embed uses ruvector@0.2.25 with ONNX all-MiniLM-L6-v2 to produce normalized 384-dimensional vectors stored in an HNSW index for semantic search and agent memory.
What performance does ruvector HNSW indexing claim?
vector-embed cites ruvector HNSW indexing at 52,000+ inserts per second and approximately 0.045ms search latency for local embedding retrieval workloads.