Enterprise DNA Enterprise DNA
M MCP Servers Developer low

AndreLYL/memkin

by Various

Local-first personal memory extraction and storage。一个面向个人工作场景下的、本地优先的记忆系统

MCP

AndreLYL/memkin

Added 3 Sept 2026

#agentmemory #ai #claude #codex #cursor #feishu #hermes #knowledge-graph

Overview

A local-first memory extraction and storage system for personal work scenarios. It is written in TypeScript and stores memory data on the local machine. The project is focused on individual memory collection in a user's own environment.

Best for

Best for
An individual developer who wants a local-first personal memory store for their own work.

Use cases

  • Store personal work context in a local memory store
  • Extract memory from personal work activities
  • Integrate local-first memory into a TypeScript application

How to use

Install

npx memkin start     # 无配置时自动进入 setup 向导,完成后启动服务并打开 Web UI

Tested with

Claude Desktop, Claude Code, Cursor, Windsurf

Notes

A local-first memory extraction and storage system for personal work scenarios. It is written in TypeScript and stores memory data on the local machine. The project is focused on individual memory collection in a user’s own environment.

5 stars on GitHub. Last updated 2026-07-28. Licensed Apache-2.0.

Use cases

  • Store personal work context in a local memory store
  • Extract memory from personal work activities
  • Integrate local-first memory into a TypeScript application

Pros

  • Local-first design keeps memory data on the user’s machine
  • Narrow scope is well matched to personal work tools
  • TypeScript codebase fits developer workflows

Cons

  • No retrieval flow is described, only extraction and storage
  • Very small user community at 5 stars
  • Local-only focus is not built for shared team memory

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Local-first design keeps memory data on the user's machine
  • Narrow scope is well matched to personal work tools
  • TypeScript codebase fits developer workflows

Cons

  • No retrieval flow is described, only extraction and storage
  • Very small user community at 5 stars
  • Local-only focus is not built for shared team memory
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks