vector-hyperbolic
Place hierarchical data in the Poincare ball using depth for the radius and npx ruvector@0.3.3 embed text for direction (a unit-norm text embedding alone has no depth)
How do I install this agent skill?
npx skills add https://github.com/ruvnet/ruflo --skill vector-hyperbolicIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill is safe for its intended purpose of embedding hierarchical data. It installs and executes a specific version of the ruvector package from the NPM registry. It presents a standard low-risk surface for indirect prompt injection as it processes and stores user-provided text.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Vector Hyperbolic
Embed hierarchical data in the Poincare ball model using ruvector.
When to use
Use this skill when your data has inherent hierarchy — dependency trees, module structures, taxonomies, org charts, ontologies. Hyperbolic space captures hierarchical distances with far fewer dimensions than Euclidean embeddings.
Steps
- Ensure ruvector@0.3.3 is available:
npm ls ruvector 2>/dev/null | grep '0.3.3' || npm install ruvector@0.3.3 - Know what a text embedding can and cannot give you. ONNX sentence embeddings (all-MiniLM-L6-v2) are unit-norm. Rescaling or exp-mapping a unit vector puts every point at the same radius (the MCP
embeddings_hyperbolic convertgives tanh(0.5) = 0.4621 for all of them), so the radius carries no depth and parent/child distances come out nearly the same as cross-branch distances. Projecting a text embedding does not create hierarchy. - Put the hierarchy in yourself. Choose each node's radius from its depth in the tree (root near 0, leaves near 1, for example r = tanh(depth * k)), and take its direction from the text embedding, or use embeddings trained on the tree's edges. Measure on your own tree: parent-child distance should be clearly smaller than cross-branch distance.
npx -y ruvector@0.3.3 embed text "hierarchical concept" -o concept.vec.json # direction only - Geodesic distance for points strictly inside the unit ball:
d(u, v) = arcosh(1 + 2 * ||u-v||^2 / ((1-||u||^2)(1-||v||^2))). The MCPembeddings_hyperbolic distancecomputes it (curvature -1) and returnssuccess: falsefor a point on or outside the ball rather than a null distance. - Store results:
mcp__plugin_ruflo-core_ruflo__memory_store({ key: "hyperbolic-CONCEPT", value: "COORDINATES_AND_NEIGHBORS", namespace: "hyperbolic-embeddings" })
Caveats
- ruvector@0.3.3 has no
--model poincareflag;attention hyperbolicis the Poincare-ball attention op, not a text-embedding projector. - "Norm encodes depth" only holds when you set the radius from depth yourself (step 3). It does not come from the embedding.
- If you need a hyperbolic search index, store the placed coordinates in AgentDB and compute geodesic distance in your own retrieval code.
Poincare ball properties (for points you placed by depth)
| Property | Meaning |
|---|---|
| Norm close to 0 | Root-level concept (only if you assigned radius by depth) |
| Norm close to 1 | Leaf-level concept (same condition) |
| Small geodesic distance | Close in the hierarchy you encoded |
| Large geodesic distance | Distant subtrees in the hierarchy you encoded |
Use cases
- Dependency analysis: embed module imports to find tightly coupled subtrees
- Code architecture: map class hierarchies to discover structural patterns
- Knowledge organization: embed concepts to reveal taxonomic relationships
- Codebase navigation: find most specific/general modules relative to a query
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/ruvnet/ruflo/vector-hyperbolic">View vector-hyperbolic on skillZs</a>