Vector Cluster
- 639 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
vector-cluster is a ruflo agent skill that clusters embeddings in a namespace using ruvector spectral or Louvain graph detection for developers organizing large code or document vector collections in RAG workflows.
About
vector-cluster is a ruvnet/ruflo skill that groups vectors in a namespace by semantic similarity using `npx ruvector@0.2.25 hooks graph-cluster` with spectral or Louvain community detection. Developers pass a namespace and optional `--k` parameter after embeddings are stored, revealing themes, outliers, and natural groupings across code or documents. Use vector-cluster when RAG or agent memory collections grow large enough that flat search misses structure. The skill integrates claude-flow memory search and store tools and expects ruvector 0.2.25 available via npm.
- Turns any folder of documents or code into a queryable vector database in one command
- Supports multiple embedding models and vector stores including local and cloud options
- Automatic chunking, metadata tagging, and similarity search with relevance scoring
- Designed as a reusable capability for agentic RAG and long-term memory systems
- 422 installs across indie agent projects
Vector Cluster by the numbers
- 639 all-time installs (skills.sh)
- +6 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #1,533 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-clusterAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 639 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you cluster code embeddings by similarity?
Embed, chunk, store, and query documents or code at scale inside their own agents and RAG workflows.
Who is it for?
Developers building RAG or agent memory systems who need semantic cluster maps over large embedding namespaces in ruvector.
Skip if: Small embedding sets where simple k-means in a notebook suffices or projects without ruvector namespaces configured.
When should I use this skill?
A namespace has many stored embeddings and you need thematic clusters, outlier detection, or community structure for retrieval planning.
What you get
Cluster assignments, community groupings, and outlier labels for vectors in the target namespace.
- cluster group assignments
- community detection report
By the numbers
- Pins ruvector@0.2.25 for graph-cluster execution
- Supports 2 detection algorithms: spectral and Louvain
Files
Vector Cluster
Cluster vectors in a namespace by semantic similarity using ruvector.
When to use
Use this skill when you have a collection of embeddings and want to discover natural groupings. Clustering reveals themes, identifies outliers, and helps organize large vector collections.
Steps
1. Ensure ruvector@0.2.25 is available:
npm ls ruvector 2>/dev/null | grep '0.2.25' || npm install ruvector@0.2.252. Run clustering — in ruvector@0.2.25 the only working clustering is via hooks graph-cluster (spectral/Louvain over a code graph). The top-level cluster command is reserved for distributed cluster ops and is currently "Coming Soon" upstream.
npx -y ruvector@0.2.25 hooks graph-cluster <files...>
npx -y ruvector@0.2.25 hooks graph-mincut <files...>3. Review output — JSON with cluster assignments, community labels, and edges. If you see "graph.nodes is not iterable", run hooks init first to seed the graph state. 4. Store results: mcp__claude-flow__memory_store({ key: "clusters-PROJECT-TIMESTAMP", value: "CLUSTER_ASSIGNMENTS", namespace: "vector-clusters" })
Interpreting results
- High cohesion (>0.85): tight, well-defined cluster
- Medium cohesion (0.6-0.85): related but diverse content
- Low cohesion (<0.6): loose grouping, try higher resolution
- Outliers: novel or anomalous files worth investigating
Caveats
cluster --namespace ... --k Nandcluster --densityare not valid in ruvector@0.2.25 — those flags fall through to the distributed-cluster command, which only accepts--status,--join,--leave,--nodes,--leader,--info.- For namespaced k-means over arbitrary embeddings, run k-means in your own code against vectors stored in AgentDB.
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.246k10How it compares
Use vector-cluster for graph-based semantic grouping in ruvector namespaces instead of manual k-means scripts disconnected from agent memory stores.
FAQ
Which clustering algorithms does vector-cluster support?
vector-cluster uses ruvector@0.2.25 hooks graph-cluster with spectral and Louvain community detection. Pass a namespace and optional `--k N` to control cluster granularity over stored embeddings.
When should you use vector-cluster?
vector-cluster fits when a namespace holds many embeddings and you need natural groupings, theme discovery, or outlier identification. Run it after vectors are embedded and stored, before reorganizing RAG retrieval or agent memory.