Agent skill

Hyperspacedb Core

by YARlabs in YARlabs/hyperspace-db

Core operations for HyperspaceDB — a multi-geometry vector database.

MITAuto-check passedDatabases

Install Hyperspacedb Core

skills CLI
$ npx skills add YARlabs/hyperspace-db --skill hyperspacedb-core -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install YARlabs/hyperspace-db hyperspacedb-core --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/YARlabs/hyperspace-db.git skills-src && mkdir -p .claude/skills && cp -r skills-src/integrations/hyperspacedb-skills/skills/hyperspacedb-core .claude/skills/hyperspacedb-core && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hyperspacedb-core
GitHub stars
162
Token cost
~1.5k tokens
SKILL.md length
233 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Core operations for HyperspaceDB — a multi-geometry vector database.

  • Works in 5 steps: Collections → Insert Data → Search → …
  • You need to: create
  • SKILL.md covers Connection, 1. Collections, 2. Insert Data and 3. Search, plus 4 more sections
  • Needs HYPERSPACE_API_KEY

What it does

Hyperspacedb Core is an agent skill from YARlabs/hyperspace-db. Core operations for HyperspaceDB — a multi-geometry vector database. Use this skill whenever you need to: create or manage collections, insert vectors or text, perform semantic search, retrieve points by ID, or delete data. Trigger on: "create collection", "insert vector", "search", "find similar", "vector database", "semantic memory", "HyperspaceDB", "embed and store".

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases, covering Vector databases. It works with Model Context Protocol. The repository describes itself as: [H] HyperspaceDB is a high-performance, vector database. It features 1-bit quantization, async replication, and native support for hierarchical datasets (Lorentz, Poincaré ball &… The licence is MIT.

When your agent uses it

  • You need to: create
  • Manage collections
  • Perform semantic search
  • Retrieve points by ID

Example prompts

  • “create collection”
  • “insert vector”
  • “search”
  • “/hyperspacedb-core”

Requirements

  • Python 3
  • A credential in HYPERSPACE_API_KEY

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Collections
  2. Insert Data
  3. Search
  4. Point Operations
  5. Maintenance

What it can do on your machine

Read from SKILL.md and the folder at commit a43ccf7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript and python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HYPERSPACE_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hyperspacedb Core loads about 1.5k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 233 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from YARlabs/hyperspace-db at commit a43ccf7, republished under its MIT licence (© YARlabs). 233 words, ~1,533 tokens.

Download SKILL.mdSave it as .claude/skills/hyperspacedb-core/SKILL.md (or your agent's skills folder).
name
hyperspacedb-core
description
Core operations for HyperspaceDB — a multi-geometry vector database. Use this skill whenever you need to: create or manage collections, insert vectors or text, perform semantic search, retrieve points by ID, or delete data. Trigger on: "create collection", "insert vector", "search", "find similar", "vector database", "semantic memory", "HyperspaceDB", "embed and store".

HyperspaceDB Core Operations

HyperspaceDB is a high-performance, multi-geometry vector database with built-in AI capabilities. The server communicates over gRPC (port 50051 by default).

Connection

typescript
import { HyperspaceClient } from 'hyperspace-sdk-ts';

const client = new HyperspaceClient(
  process.env.HYPERSPACE_HOST ?? 'localhost:50051',
  process.env.HYPERSPACE_API_KEY ?? 'I_LOVE_HYPERSPACEDB'
);
python
from hyperspacedb import HyperspaceClient

client = HyperspaceClient(
    host=os.environ.get("HYPERSPACE_HOST", "localhost:50051"),
    api_key=os.environ.get("HYPERSPACE_API_KEY", "I_LOVE_HYPERSPACEDB")
)

Always use environment variables for HYPERSPACE_HOST and HYPERSPACE_API_KEY. Never hardcode connection strings in application code.


1. Collections

Create a Collection

createCollection takes a CollectionSchema — a multi-component descriptor that defines vector geometry and the MRL (Multi-Resolution Layered) cascade pipeline.

typescript
import { HyperspaceClient, CollectionSchema } from 'hyperspace-sdk-ts';

// Simple single-component collection
const schema: CollectionSchema = {
  components: [
    {
      name: "main",
      metric: "cosine",   // cosine | l2 | lorentz | poincare | hybrid
      fullDimension: 1536,
      weight: 1.0
    }
  ],
  cascadePipeline: [
    { componentName: "main", cutoffDimension: 1536, storeInRam: true, rerankTopK: 100 }
  ]
};

await client.createCollection("my_memory", schema);

// Hybrid collection: 33 Lorentz dims + 768 Euclidean dims (total 801 dims)
const hybridSchema: CollectionSchema = {
  components: [
    { name: "hybrid_main", metric: "hybrid", fullDimension: 801, weight: 1.0 }
  ],
  cascadePipeline: [
    { componentName: "hybrid_main", cutoffDimension: 801, storeInRam: false, rerankTopK: 200 }
  ]
};
await client.createCollection("ontology_and_text", hybridSchema);

Geometry selection guide:

Data typeRecommended metric
NLP embeddings (normalized)cosine
Dense numeric featuresl2
Hierarchical / taxonomic datalorentz
Hyperbolic manifoldspoincare
Mixed: hierarchy + semantic texthybrid (33 Lorentz + N Euclidean dims)

Use hyperspace_analyze_geometry (via MCP) to auto-detect the best metric for your data.

List Collections
typescript
const collections = await client.listCollections();
Delete a Collection
typescript
await client.deleteCollection("my_memory"); // irreversible!

2. Insert Data

Insert Raw Vector
typescript
const id = await client.insert(
  [0.1, 0.2, ..., 0.9],  // float32 array, length = fullDimension
  { source: "user_chat", timestamp: "2026-07-14" },  // metadata
  "my_memory"
);
Insert Text (auto-embed on server)
typescript
const id = await client.insertText(
  "The user asked about quantum entanglement.",
  { user_id: "u123", session: "sess_abc" },  // metadata
  "my_memory"
);
Batch Insert
typescript
// batchInsert takes an array of {vector, metadata} objects
const ids = await client.batchInsert(
  [
    { vector: [...], metadata: { key: "val1" } },
    { vector: [...], metadata: { key: "val2" } },
  ],
  "my_memory"
);

typescript
const results = await client.search(
  queryVector,   // number[] | Float32Array | Float64Array
  10,            // top-k
  "my_memory",
  {
    filters: [...],    // optional Filter[]
    mrlDimension: 256, // optional: use truncated MRL dimension for faster search
    useWasserstein: false,
    includePayload: false,
  }
);
// results: Array<{ id, distance, metadata, typedMetadata, payload? }>
Hybrid Search (Vector + BM25 Full-text)

For collections with hybrid metric or when you need keyword+semantic fusion:

typescript
const results = await client.search(
  queryVector,
  10,
  "my_memory",
  {
    hybridQuery: "quantum entanglement",  // BM25 text query
    hybridAlpha: 0.5,  // 0.0 = pure BM25, 1.0 = pure vector, 0.5 = balanced
  }
);
Search by Text (server-side embedding)
typescript
const results = await client.searchText(
  "quantum physics papers",
  10,
  "my_memory",
  {
    hybridAlpha: 0.7,  // optional: blend vector score with BM25
  }
);
Filtering
typescript
const results = await client.search(queryVector, 10, "my_memory", {
  filters: [
    { and: [
      { match: { key: "source", value: "research_paper" } },
      { range: { key: "year", gte: 2020 } }
    ]}
  ]
});

4. Point Operations

Get Points by IDs
typescript
const points = await client.getPoints([1, 42, 99], "my_memory");
Delete a Point
typescript
await client.delete(pointId, "my_memory");

5. Maintenance

typescript
await client.rebuildIndex("my_memory");  // optimize HNSW graph
await client.vacuum();                   // purge deleted vectors, reclaim disk

Common Pitfalls

  • Dimension mismatch: The vector dimension must exactly match the collection's configured dimension.
  • Wrong metric for data: Use lorentz for hierarchical/ontological data, not l2.
  • Forgetting to vacuum: Deleted points are soft-deleted; call vacuum() to reclaim disk.
  • Replication Factor 1 in production: Always use RF ≥ 2 for fault tolerance in DePIN deployments.

See Also

© YARlabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in integrations/hyperspacedb-skills/skills/hyperspacedb-core of YARlabs/hyperspace-db.

Open the folder on GitHubat commit a43ccf7

Compare with similar skills

Hyperspacedb Core next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hyperspacedb Core compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hyperspacedb Core this skillYARlabs/hyperspace-db162—~1.5kAutomated safety check: PassMIT
Codebase Explorationgiancarloerra/SocratiCode3.3k1 repos~1.5kAutomated safety check: PassAGPL-3.0
Mongodb Search And AImongodb/agent-skills1891 repos~1.7kAutomated safety check: PassApache-2.0
Chat Formatruvnet/ruflo74k—~362Automated safety check: NotesMIT
Codebase Managementgiancarloerra/SocratiCode3.3k1 repos~1.8kAutomated safety check: PassAGPL-3.0
Flowflow Spacesmirkobozzetto/flowflow171—~1kAutomated safety check: PassEUPL-1.2

Similar skills

  • Codebase Exploration

    giancarloerra/SocratiCode

    Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts.

    3.3k GitHub starsUsed in 1 repo~1.5k tokens
    DatabasesAuto-check passed
  • Mongodb Search And AI

    mongodb/agent-skills

    Official

    Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions.

    189 GitHub starsUsed in 1 repo~1.7k tokens
    DatabasesAuto-check passed
  • Chat Format

    ruvnet/ruflo

    Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval

    74k GitHub stars~362 tokensUpdated today
    DatabasesAuto-check: notes
  • Codebase Management

    giancarloerra/SocratiCode

    Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.

    3.3k GitHub starsUsed in 1 repo~1.8k tokens
    AI & LLM EngineeringAuto-check passed
  • Flowflow Spaces

    mirkobozzetto/flowflow

    Use FlowFlow spaces safely through their scoped MCP server. An agent skill from mirkobozzetto/flowflow.

    171 GitHub stars~1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Pgvector Semantic Search

    timescale/pg-aiguide

    A skill your agent uses for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search.

    1.9k GitHub stars~3.8k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

More from YARlabs/hyperspace-db

  • Hyperspacedb Cognitive

    YARlabs/hyperspace-db

    Cognitive AI tools for HyperspaceDB: Chain-of-Thought stability analysis, Koopman momentum prediction, trust scoring, and Lyapunov convergence for agent reasoning.

    162 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Hyperspacedb Graph

    YARlabs/hyperspace-db

    Graph traversal, Lorentz hierarchy, and concept relationship operations for HyperspaceDB.

    162 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Hyperspacedb MCP

    YARlabs/hyperspace-db

    Model Context Protocol (MCP) server for HyperspaceDB. An agent skill from YARlabs/hyperspace-db.

    162 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Hyperspacedb Memory

    YARlabs/hyperspace-db

    Zero-overhead cognitive long-term and episodic memory for AI agents (Mem0 drop-in and mcp-hyperspace-memory).

    162 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Questions about Hyperspacedb Core

What does Hyperspacedb Core do?

Core operations for HyperspaceDB — a multi-geometry vector database. Hyperspacedb Core is an agent skill from YARlabs/hyperspace-db. Core operations for HyperspaceDB — a multi-geometry vector database.

When should I use Hyperspacedb Core?

Hyperspacedb Core fits situations like: you need to: create; manage collections; perform semantic search; retrieve points by ID.

How do I install Hyperspacedb Core in Claude Code?

Run `npx skills add YARlabs/hyperspace-db --skill hyperspacedb-core -a claude-code`. Or copy the skill folder (integrations/hyperspacedb-skills/skills/hyperspacedb-core in YARlabs/hyperspace-db) into .claude/skills/hyperspacedb-core in your project. Claude Code loads it when a task matches its description.

How do I install Hyperspacedb Core in Codex?

Run `npx skills add YARlabs/hyperspace-db --skill hyperspacedb-core -a codex`. Or copy the skill folder (integrations/hyperspacedb-skills/skills/hyperspacedb-core in YARlabs/hyperspace-db) into .agents/skills/hyperspacedb-core in your project. Codex loads it when a task matches its description.

Can I use Hyperspacedb Core in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add YARlabs/hyperspace-db --skill hyperspacedb-core -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hyperspacedb-core, .gemini/skills/hyperspacedb-core, .github/skills/hyperspacedb-core and .opencode/skills/hyperspacedb-core in your project.

What does Hyperspacedb Core need to run?

Going by SKILL.md and its folder, Hyperspacedb Core needs credentials named HYPERSPACE_API_KEY. Our summary lists: Python 3; A credential in HYPERSPACE_API_KEY.

Does Hyperspacedb Core access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hyperspacedb Core safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hyperspacedb Core use?

Hyperspacedb Core is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hyperspacedb Core use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hyperspacedb Core?

Skills that share tags, products or a category with Hyperspacedb Core: Codebase Exploration (giancarloerra/SocratiCode, 3.3k stars), Mongodb Search And AI (mongodb/agent-skills, 189 stars), Chat Format (ruvnet/ruflo, 74k stars) and Codebase Management (giancarloerra/SocratiCode, 3.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hyperspacedb Core?

YARlabs (a GitHub user) maintains it in YARlabs/hyperspace-db, which has 162 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 9, 2026.

Source: YARlabs/hyperspace-db on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.