What is spatial-memory-mcp CLAUDE.md?

Contributor instructions for spatial-memory-mcp, a persistent semantic memory server for large language models. The server stores memories as searchable vectors and supports spatial navigation, using LanceDB and sentence-transformers.

Use them when changing the MCP server, memory storage, embeddings, validation, security, configuration, or related services.

They explain the project structure, architecture, configuration, and test commands so contributors can work without rediscovering how the repository fits together.

How arman-tech/spatial-memory-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to arman-tech/spatial-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/arman-tech/spatial-memory-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/arman-tech/spatial-memory-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/arman-tech/spatial-memory-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/arman-tech/spatial-memory-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/arman-tech/spatial-memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/arman-tech/spatial-memory-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/arman-tech/spatial-memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/arman-tech/spatial-memory-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 915 This file is loaded in full into every session.

When invoked 915 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00915	$0.00915
Opus 5.5	$0.00366	$0.00366
Sonnet 5.5	$0.00183	$0.00183
Haiku 4.5	$0.00092	$0.00092

Measured 2mo ago against content hash 4d21ac7e556c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spatial-memory-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spatial Memory MCP - Contributor Guide

This document helps AI assistants (and human contributors) work effectively on this codebase.

Project Overview

spatial-memory-mcp is a persistent semantic memory MCP server for LLMs. It provides vector-based memory storage with spatial navigation capabilities using LanceDB and sentence-transformers.

Architecture

spatial_memory/
├── server.py           # MCP server, tool handlers, instructions injection
├── factory.py          # Dependency injection, service instantiation
├── config.py           # Settings (Pydantic), environment configuration
├── core/               # Core infrastructure
│   ├── database.py     # LanceDB wrapper, CRUD operations
│   ├── embeddings.py   # Sentence-transformer embedding service
│   ├── models.py       # Pydantic data models (Memory, etc.)
│   ├── errors.py       # Exception hierarchy
│   ├── validation.py   # Input validation, security checks
│   ├── security.py     # Security utilities
│   ├── db_*.py         # Database utilities (search, indexes, migrations)
│   └── spatial_ops.py  # SLERP, vector operations
├── services/           # Business logic layer
│   ├── memory.py       # Core memory operations (remember, recall, forget)
│   ├── spatial.py      # Spatial operations (journey, wander, regions)
│   ├── lifecycle.py    # Decay, reinforce, consolidate, extract
│   ├── export_import.py# Import/export functionality
│   └── utility.py      # Stats, namespaces, health
├── adapters/           # External service adapters
├── ports/              # Interface definitions
└── tools/              # MCP tool definitions

Key Commands

# Run tests (unit tests only by default)
pytest tests/ -v

# Run all tests including integration
pytest tests/ -v -m ""

# Run integration tests only
pytest tests/ -v -m integration

# Type checking
mypy spatial_memory/

# Linting
ruff check spatial_memory/ tests/

# Format code
ruff format spatial_memory/ tests/

# Run the server directly
python -m spatial_memory

Read the full file on GitHub · 103 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 103 lines · 915 tokens per session scan A 4d21ac7e556c

Subscribe to this mod's changes

spatial-memory-mcp CLAUDE.md is an instructions file published in the GitHub repository arman-tech/spatial-memory-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 915 tokens to every session, about $0.0037 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Memory and context RAG and vectors

spatial-memory-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spatial-memory-mcp CLAUDE.mdarman-tech/spatial-memory-mcp	Instructions file	1	6mo ago	MIT	A	915	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

spatial-memory-mcp: Instructions file for Claude Code