Local Memory MCP server
io.github.studiomeyer-io/local-memory-mcp·v2.4.4·15 starsPersistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
15 stars422 downloads/wk
Reviews
Write oneNobody has reviewed Local Memory yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Local Memory tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-11-04 · same rubric, same numbers if you re-run it
- Code scan17 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 3 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Local Memory compares
Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 85% of 802 Databases servers
- GitHub stars
- 15
- more than 81% of 604 Databases servers
- Downloads a week
- 422
- more than 83% of 411 Databases servers with a package
Release history: 2 versions in the registry since 2026-08-09, latest 2026-11-01, typically one every 85 days.
Install Local Memory in Claude Code, Cursor or VS Code
Runs npx -y @studiomeyer/local-memory-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add local-memory-mcp -- npx -y @studiomeyer/local-memory-mcp
What the publisher says
From the Local Memory repository's README, as published. We do not edit it. Read it on GitHub
<!-- studiomeyer-mcp-stack-banner:start -->
Part of the StudioMeyer MCP Stack — Built in Mallorca 🌴 · ⭐ if you use it
<!-- studiomeyer-mcp-stack-banner:end -->
local-memory-mcp
<!-- badges --> <!-- /badges -->Persistent local memory for Claude, Cursor & Codex. 25 tools. Hybrid retrieval (BM25 + vector cosine, RRF). Bi-temporal asOf queries + fact supersession. LLM-free contradiction detection + reflection. Portable JSON export/import. Multilingual embeddings. No cloud. No API keys.
Your AI assistant forgets everything when you close the chat. This fixes that.
Learnings, decisions, people, projects — stored in a single SQLite file on your machine that never leaves your computer. Built-in Knowledge Graph, duplicate detection, FTS5 keyword search, and (new in v2) hybrid retrieval that fuses BM25 with on-device vector cosine via Reciprocal Rank Fusion. The embedding model is multilingual (DE / EN / ES / 100+ languages) and runs locally — no API keys, no cloud.
📄 Deep dive: WHITEPAPER.md — architecture, design principles, the local-first contract, and an honest comparison vs. other memory systems.
Not affiliated with danieleugenewilliams/local-memory-releases — that is a different "Local Memory" project with the same descriptive name. This package is published as @studiomeyer/local-memory-mcp — always use the scoped name to disambiguate.
A note from us
We have been building tools and systems for ourselves for the past two years. The fact that this repo is small and has few stars is not because it is new. It is because we only just decided to share what we have built. It is not a fresh experiment, it is a long story with a recent commit.
We love building things and sharing them. We do not love social media tactics, growth hacks, or chasing stars and followers. So this repo is small. The code is real, it gets used, issues get answered. Judge for yourself.
If it helps you, sharing, testing, and feedback help us. If it could be better, an issue is more useful. If you build something with it, tell us at hello@studiomeyer.io. That genuinely makes our day.
From a small studio in Palma de Mallorca.
Quick Start
Claude Code
claude mcp add memory -- npx -y @studiomeyer/local-memory-mcpClaude Desktop
Easiest: one-click MCPB bundle. v2.0.0 ships pre-built .mcpb bundles for every major desktop platform — download the one for your OS from the latest release and double-click. Claude Desktop walks you through the install — no JSON editing, no npm install, no terminal.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Local Memory: common questions
- Is Local Memory MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Local Memory safety report
- How do I install Local Memory?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Local Memory need an API key?
- No secret keys are declared. It reads 4 settings from the environment.
- Is Local Memory maintained?
- The last commit was 14 days ago (2026-11-01). The latest release is v2.4.4.
- What can I use instead of Local Memory?
- Servers from other publishers that do the same job: CPersona MCP server, hmem — Humanlike Memory for AI Agents MCP server and memo MCP server. Compare all Local Memory alternatives.
- How does Local Memory compare with other Databases MCP servers?
- safety score 91/100 (higher than 85% of 802 Databases servers); github stars 15 (more than 81% of 604 Databases servers); downloads a week 422 (more than 83% of 411 Databases servers with a package). Full comparison.
Alternatives to Local Memory
Same job from other publishers: the closest match first, then the best rated.
- CPersonaPersistent AI memory in one SQLite file: 3-layer hybrid search, confidence scoring, 29 tools.not reviewedGrowingA
- hmem — Humanlike Memory for AI AgentsPersistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.not reviewedGrowingA
- memoMemory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.not reviewedGrowingA
- open-memexLocal-first memory for AI coding agents — Markdown + SQLite FTS5, shared across editors via MCP.not reviewedGrowingB
SAME - Stateless Agent Memory EnginePersistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.not reviewedGrowingB
