Agent skill

Hyperspacedb Memory

by YARlabs in YARlabs/hyperspace-db

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

MITAuto-check passedAgent Workflows

Install Hyperspacedb Memory

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

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

GitHub CLI
$ gh skill install YARlabs/hyperspace-db hyperspacedb-memory --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-memory .claude/skills/hyperspacedb-memory && 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-memory
GitHub stars
162
Token cost
~880 tokens
SKILL.md length
177 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 2 steps: Tier 1: Zero-Code MCP Server… → Tier 2: Drop-in Mem0 Replacement SDKs
  • Implementing agent memory
  • SKILL.md covers 1. Tier 1: Zero-Code MCP… and 2. Tier 2: Drop-in Mem0…
  • Calls pip and npm; needs HYPERSPACE_API_KEY

What it does

Hyperspacedb Memory is an agent skill from YARlabs/hyperspace-db. Zero-overhead cognitive long-term and episodic memory for AI agents (Mem0 drop-in and mcp-hyperspace-memory). Use this skill when implementing agent memory, episodic fact storage, semantic recall with session isolation, memory update/delete, Fréchet mean consolidation, or geodesic hallucination defense. Trigger on: "agent memory", "Mem0", "episodic memory", "remember", "recall", "forget", "mcp-hyperspace-memory", "hyperspace-memory", "long term memory".

Its SKILL.md is about 880 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 Agent Workflows, covering Agent memory. It works with Model Context Protocol and Mem0. 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

  • Implementing agent memory
  • Episodic fact storage
  • Semantic recall with session isolation
  • Memory update/delete

Example prompts

  • “agent memory”
  • “episodic memory”
  • “remember”
  • “/hyperspacedb-memory”

Requirements

  • Python 3
  • Node.js
  • A credential in HYPERSPACE_API_KEY
  • A credential in YOUR_YARINK_API_KEY

Workflow steps

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

  1. Tier 1: Zero-Code MCP Server (mcp-hyperspace-memory)
  2. Tier 2: Drop-in Mem0 Replacement SDKs

What it can do on your machine

Read from SKILL.md and the folder at commit f3ef6c7. 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

    Shell commands in SKILL.md call:

    • pip
    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use pip and npm, which can reach the network depending on how they are called.

    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 Memory loads about 880 tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 177 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~880

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 f3ef6c7, republished under its MIT licence (© YARlabs). 177 words, ~880 tokens.

Download SKILL.mdSave it as .claude/skills/hyperspacedb-memory/SKILL.md (or your agent's skills folder).
name
hyperspacedb-memory
description
Zero-overhead cognitive long-term and episodic memory for AI agents (Mem0 drop-in and mcp-hyperspace-memory). Use this skill when implementing agent memory, episodic fact storage, semantic recall with session isolation, memory update/delete, Fréchet mean consolidation, or geodesic hallucination defense. Trigger on: "agent memory", "Mem0", "episodic memory", "remember", "recall", "forget", "mcp-hyperspace-memory", "hyperspace-memory", "long term memory".

Hyperspace AI Agent Memory (Mem0 Alternative)

Hyperspace Memory is a high-performance cognitive memory layer designed for LLMs, autonomous agents, and spatial multi-agent swarms.

Compared to legacy memory tools (Mem0, Zep):

  • 100x lower latency (< 2ms vs 2,500ms)
  • Zero LLM tokens on write ($0.000000 per insert vs $0.01 per insert)
  • 61.4x RAM compression via extreme 1-bit ADC quantization
  • Lorentz $\mathbb{H}^{32}$ hierarchy representation + Geodesic Hallucination Guard

1. Tier 1: Zero-Code MCP Server (mcp-hyperspace-memory)

Connect to Claude Desktop, Cursor, Windsurf, or Antigravity with a single JSON config:

json
{
  "mcpServers": {
    "hyperspace-memory": {
      "command": "npx",
      "args": ["-y", "mcp-hyperspace-memory"],
      "env": {
        "HYPERSPACE_HOST": "the.yar.ink",
        "HYPERSPACE_API_KEY": "YOUR_YARINK_API_KEY"
      }
    }
  }
}
The 8 Cognitive Tools:
  1. memory_remember: Store episodic facts with auto-vectorization (text, session_id, tags, importance).
  2. memory_recall: Semantic search with session isolation (query, session_id, top_k).
  3. memory_update: Modify an existing memory by ID (memory_id, new_text).
  4. memory_forget: Delete a memory item by ID (memory_id).
  5. memory_list_sessions: Enumerate all active conversation sessions.
  6. memory_explore_hierarchy: Traverse concept taxonomy in Lorentz space.
  7. memory_consolidate: Compute Fréchet mean of episodic memories into an abstract concept.
  8. memory_verify_claim: Calculate Geodesic Trust Score against stored premises to block hallucinations.

2. Tier 2: Drop-in Mem0 Replacement SDKs

Python (hyperspace-memory)
bash
pip install hyperspace-memory
python
from hyperspace_memory import Memory

# 1-Line Drop-in Replacement for Mem0
memory = Memory(config={
    "host": "the.yar.ink",
    "api_key": "YOUR_YARINK_API_KEY",
    "quantization": "extreme"  # 1-bit ADC + Lorentz f32
})

# Add memory (<2ms, 0 tokens)
res = memory.add(
    "Patient blood glucose is 14.2 mmol/L with rapid rising trend.",
    user_id="user_alice",
    agent_id="agent_medical",
    metadata={"category": "glucose"}
)
mem_id = res["results"][0]["id"]

# Semantic search with user isolation
memories = memory.search("glucose trend", user_id="user_alice", limit=5)

# Update & Delete
memory.update(mem_id, "Patient blood glucose normalized to 6.5 mmol/L.")
memory.delete(mem_id)
TypeScript (hyperspace-memory)
bash
npm install hyperspace-memory
typescript
import { Memory } from "hyperspace-memory";

const memory = new Memory({
  host: "the.yar.ink",
  apiKey: "YOUR_YARINK_API_KEY",
  quantization: "extreme"
});

const res = await memory.add(
  "Deployment target: production-us-east-1 on Kubernetes v1.30.",
  { userId: "devops_bob", agentId: "infra_agent" }
);

const results = await memory.search("Kubernetes version?", { userId: "devops_bob" });
console.log(results[0].memory);

© 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-memory of YARlabs/hyperspace-db.

Open the folder on GitHubat commit f3ef6c7

Compare with similar skills

Hyperspacedb Memory 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 Memory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hyperspacedb Memory this skillYARlabs/hyperspace-db162—~880Automated safety check: PassMIT
Mem0 Integration Pipelinemem0ai/mem067k—~3.3kAutomated safety check: PassApache-2.0
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT
Mem0 CLI Memory Commandsmem0ai/mem067k—~2kAutomated safety check: NotesApache-2.0
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT
agentmemory Setup and Diagnosticsrohitg00/agentmemory29k—~1kAutomated safety check: NotesApache-2.0

Similar skills

  • Adds Mem0 memory to an existing repository with a test-first pipeline that detects the language, lets you choose Platform or open source, and leaves a local feature branch.

    67k GitHub stars~3.3k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Adds, searches, lists, updates and deletes memories on the Mem0 platform from the terminal with the mem0 command, including a JSON mode built for agents.

    67k GitHub stars~2k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    59k GitHub stars~2.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Sets up and troubleshoots a local agentmemory install, covering the MCP connection, environment variables, ports, authentication and optional feature flags.

    29k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Claude-Mem Install for Grok Bot

    thedotmack/claude-mem

    Use this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-login observer, or remote cmem.ai. No Cursor…

    99k GitHub stars~440 tokensUpdated today
    Agent WorkflowsAuto-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 Core

    YARlabs/hyperspace-db

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

    162 GitHub stars~1.5k 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

Categories

Questions about Hyperspacedb Memory

What does Hyperspacedb Memory do?

Zero-overhead cognitive long-term and episodic memory for AI agents (Mem0 drop-in and mcp-hyperspace-memory). Hyperspacedb Memory is an agent skill from YARlabs/hyperspace-db. Zero-overhead cognitive long-term and episodic memory for AI agents (Mem0 drop-in and mcp-hyperspace-memory).

When should I use Hyperspacedb Memory?

Hyperspacedb Memory fits situations like: implementing agent memory; episodic fact storage; semantic recall with session isolation; memory update/delete.

How do I install Hyperspacedb Memory in Claude Code?

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

How do I install Hyperspacedb Memory in Codex?

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

Can I use Hyperspacedb Memory 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-memory -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-memory, .gemini/skills/hyperspacedb-memory, .github/skills/hyperspacedb-memory and .opencode/skills/hyperspacedb-memory in your project.

What does Hyperspacedb Memory need to run?

Going by SKILL.md and its folder, Hyperspacedb Memory needs the command-line tools its instructions call (pip and npm) and credentials named HYPERSPACE_API_KEY. Our summary lists: Python 3; Node.js; A credential in HYPERSPACE_API_KEY; A credential in YOUR_YARINK_API_KEY.

Does Hyperspacedb Memory access the network?

SKILL.md contains no URLs. Its commands use pip and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Hyperspacedb Memory 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 Memory use?

Hyperspacedb Memory 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 Memory use?

About 880 tokens (SKILL.md is roughly 3.5k 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 Memory?

Skills that share tags, products or a category with Hyperspacedb Memory: Mem0 Integration Pipeline (mem0ai/mem0, 67k stars), MemPalace Memory Search (MemPalace/mempalace, 59k stars), Mem0 CLI Memory Commands (mem0ai/mem0, 67k stars) and MemPalace Setup and Operation (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hyperspacedb Memory?

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 8, 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.