utk09-NCL

utk09-NCL / mini-memory-mcp

Public

A lightweight, local-first persistent memory server for AI tools. Stores structured memory entries in SQLite and exposes them over both the Model Context Protocol (MCP) and a plain REST HTTP API

claude codex mcp reactjs
10
6
100% credibility
Found Apr 12, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

A local tool for storing, searching, and managing short structured notes that AI assistants can access to maintain persistent context.

How It Works

1
🔍 Find Mini Memory

You discover a handy tool to save short notes so your AI helper remembers important details across chats.

2
📥 Set it up on your computer

Download the program and launch it – it quietly creates a private storage spot just for your notes.

3
🌐 Open the web dashboard

Go to the web address shown in your browser to see a clean page for managing your memories.

4
✨ Save your first note

Type a title, add concise details, pick tags like 'project:work' – it saves instantly and feels organized.

5
🔎 Search and sort notes

Use the search box for words or phrases, click tags to filter – find exactly what you need fast.

6
🤖 Link to your AI chat

Tell your AI tool where to find it, so it pulls up your saved memories during conversations.

🎉 Smarter AI forever

Your AI now recalls your notes every time, making help more personal and efficient.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is mini-memory-mcp?

Mini-memory-mcp is a lightweight, local-first TypeScript server that stores structured memory entries—titles, compressed content, and tags—in SQLite for AI tools. It exposes them over both the Model Context Protocol (MCP) for stdio or streamable HTTP, and a plain REST API with CRUD endpoints like GET/POST /api/memories for search and filtering. A React UI lets you browse, edit, and manage memories in the browser, solving the problem of persistent context for AI agents without cloud dependencies.

Why is it gaining traction?

It stands out as a mini, lightweight GitHub alternative to heavier memory stores, packing full-text search (phrases, negation), tag filtering (namespace:value), and MCP tools (list/create/read/update/delete/search) into one local server. Devs dig the dual API support—plug into Claude Desktop, Copilot VS Code, or custom HTTP clients—plus content compression rules to cram more context. No setup hassle: npm start for HTTP mode, npm run start:mcp for stdio.

Who should use this?

AI workflow hackers integrating persistent memory into Claude CLI or Copilot agents, backend devs building lightweight RAG pipelines, or solo tinkerers needing tagged, searchable notes for local models. Ideal for frontend teams wanting a simple HTTP API alongside MCP, or anyone tired of ephemeral chat histories in tools like lightweight Discord bots or GitHub clients.

Verdict

Grab it if you're experimenting with MCP—docs are solid, setup is dead simple, but with 10 stars and 1.0% credibility, it's early-stage; expect to tweak for production. Worth forking for custom lightweight tags or context hacks.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.