What is vector-memory-mcp CLAUDE.md?

Project instructions for the vector-memory-mcp repository, a Python MCP server for semantic memory search using SQLite and sqlite-vec. They describe its dependencies, project structure, and Claude Desktop setup.

They are for maintaining and extending the vector-memory-mcp codebase, including its memory store, embeddings, security checks, dependencies, and Claude Desktop configuration.

They give an agent the repository's technical context before it changes code. This reduces guesswork about the Python version, storage layer, embedding model, and main files.

How Xsaven/vector-memory-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Xsaven/vector-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/Xsaven/vector-memory-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Xsaven/vector-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/xsaven/vector-memory-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/xsaven/vector-memory-mcp/claude-md)

Your own site

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

Per session 1,021 This file is loaded in full into every session.

When invoked 1,021 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	$0.01021	$0.01021
Opus 5.5	$0.00408	$0.00408
Sonnet 5.5	$0.00204	$0.00204
Haiku 4.5	$0.00102	$0.00102

Measured 2mo ago against content hash b91590f39b13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vector-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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vector Memory MCP Server

Project Overview

MCP (Model Context Protocol) Server для векторної пам'яті з використанням sqlite-vec для семантичного пошуку.

Technology Stack

Python: 3.11.8 (requires >= 3.10)
Package Manager: uv (сучасний Python package manager)
Database: SQLite 3.43.2 + sqlite-vec extension
Embeddings: sentence-transformers/all-MiniLM-L6-v2 (384-dimensional vectors)
MCP Framework: FastMCP >= 0.3.0

Key Dependencies

mcp>=0.3.0 - Model Context Protocol framework
sqlite-vec>=0.1.6 - Vector search extension для SQLite
sentence-transformers>=2.2.2 - Embedding models

Project Structure

main.py - Entry point with uv script configuration
requirements.txt - Python dependencies for pip/venv compatibility
pyproject.toml - Modern Python project configuration
.python-version - Python version specification (3.11)
claude-desktop-config.example.json - Claude Desktop configuration template
src/models.py - Data models and configuration
src/security.py - Security validation and sanitization
src/memory_store.py - Vector memory storage operations
src/embeddings.py - Embedding generation
memory/ - SQLite database storage directory

How to Run

Standalone

# On Apple Silicon (M1/M2/M3) - use run-arm64.sh script
./run-arm64.sh --working-dir /your/working/directory

# With custom memory limit (default: 10,000 entries)
./run-arm64.sh --working-dir /your/working/directory --memory-limit 100000

# Alternative with conda Python (has SQLite extensions support)
~/miniconda3/envs/vector-mcp/bin/python main.py --working-dir ./ --memory-limit 100000

# Using uv (requires Python with SQLite extensions support)
uv run main.py --working-dir ./ --memory-limit 100000

Configuration Options

--working-dir - Working directory for memory database (required, default: current directory)
--memory-limit - Maximum number of memory entries (optional, default: 10,000)
- Minimum: 1,000 entries
- Maximum: 10,000,000 entries
- Recommended for large projects: 100,000-1,000,000

Read the full file on GitHub · 105 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 · 105 lines · 1,021 tokens per session scan A b91590f39b13

Subscribe to this mod's changes

vector-memory-mcp CLAUDE.md is an instructions file published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 1,021 tokens to every session, about $0.0041 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 2026-09-01.

Memory and context

vector-memory-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vector-memory-mcp CLAUDE.mdXsaven/vector-memory-mcp	Instructions file	0	8mo ago	MIT	A	1,021	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

vector-memory-mcp: Instructions file for Claude Code