A vibe-coded memory management system with RAG capabilities for Claude via the Model Context Protocol (MCP). SimpleMem is an MCP server that provides persistent memory storage and retrieval for Claude and other MCP clients. It combines traditional file-based storage with modern RAG (Retrieval-Augmented Generation) capabilities, including semantic search and automatic relationship discovery. Think
Add this skill
npx mdskills install jcdickinson/simplememWell-documented MCP server providing persistent memory with semantic search and RAG capabilities
A vibe-coded memory management system with RAG capabilities for Claude via the Model Context Protocol (MCP).
⚠️ Warning: This project is completely vibe-coded. It works, but don't look too closely at the implementation details. The code was written by an AI having a good time, not by someone following best practices.
SimpleMem is an MCP server that provides persistent memory storage and retrieval for Claude and other MCP clients. It combines traditional file-based storage with modern RAG (Retrieval-Augmented Generation) capabilities, including semantic search and automatic relationship discovery.
Think of it as Claude's personal notebook that never forgets and can find connections between ideas automatically.
Download the latest release for your platform from GitHub Releases:
simplemem-vX.X.X-linux-amd64.tar.gzExtract and place the binary in your PATH.
# Clone the repository
git clone https://github.com/jcdickinson/simplemem
cd simplemem
# Install dependencies
just deps
# Build the binary
just build
If you have Nix with flakes enabled:
# Run directly from GitHub
nix run github:jcdickinson/simplemem
# Or clone and run locally
git clone https://github.com/jcdickinson/simplemem
cd simplemem
nix run
# Install to profile
nix profile install github:jcdickinson/simplemem
# Run in development shell
nix develop
SimpleMem uses TOML-based configuration with flexible options for API keys and settings.
Create a config.toml file (see config.toml.example for reference):
[voyage_ai]
model = "voyage-3.5"
rerank_model = "rerank-lite-1"
api_key = { "path" = "~/.config/simplemem/voyage_api_key.txt" }
# OR
api_key = "api-key-here"
You can also configure using environment variables:
export SIMPLEMEM_VOYAGE_AI_API_KEY="your-api-key"
export SIMPLEMEM_VOYAGE_AI_MODEL="voyage-3.5"
export SIMPLEMEM_VOYAGE_AI_RERANK_MODEL="rerank-lite-1"
--config path/to/config.toml--db path/to/database.db (can also be set in config)Add to your MCP client configuration:
{
"mcpServers": {
"simplemem": {
"command": "./simplemem",
"args": [
"--db",
"path/to/your/database.db",
"--config",
"path/to/config.toml"
]
}
}
}
# Create a memory
just test-json '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"create_memory","arguments":{"name":"my-memory","metadata":{"title":"My First Memory","description":"A test memory","tags":{"category":"test","priority":"low"}},"content":"# Hello World\n\nThis is my first memory!"}},"id":1}'
# Search memories (primary discovery method)
just test-json '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"search_memories","arguments":{"query":"hello world"}},"id":1}'
# Read a specific memory
just test-json '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"read_memory","arguments":{"name":"my-memory"}},"id":1}'
# Run comprehensive semantic backlinks test
just test-backlinks
# Verify backlinks are working
just test-json '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"get_backlinks","arguments":{"name":"my-memory"}},"id":1}'
create_memory: Create a new memory with metadata object and markdown contentread_memory: Read a specific memory by nameupdate_memory: Update existing memory metadata and contentdelete_memory: Remove a memory and all related datasearch_memories: Semantic search with optional tag filtering (primary discovery method)get_backlinks: Get memories related to a specific memorychange_tag: Modify tags on memoriesNote:
list_memorieshas been temporarily removed to encourage efficient semantic search usage instead of token-heavy full listings.
{
"name": "my-memory-name",
"metadata": {
"title": "A Human-Readable Title",
"description": "Brief description of the memory",
"tags": {
"category": "personal",
"priority": "high",
"status": "active"
},
"custom_field": "any_value",
"version": "1.0"
},
"content": "# Memory Content\n\nYour memory content in **Markdown** format.\n\n- Clean markdown without frontmatter\n- Links to [[other-memories]]\n- Whatever you need!"
}
Memories are stored as YAML frontmatter + Markdown:
---
title: A Human-Readable Title
description: Brief description of the memory
tags:
category: personal
priority: high
status: active
custom_field: any_value
version: "1.0"
created: 2025-01-24T12:00:00Z
modified: 2025-01-24T12:00:00Z
---
# Memory Content
Your memory content in **Markdown** format.
- Clean markdown without frontmatter
- Links to [[other-memories]]
- Whatever you need!
# Show available commands
just
# Run tests (when they exist)
just test
# Format code
just fmt
# Run with verbose logging
just run-verbose
# Test semantic backlinks functionality
just test-backlinks
# Clean up build artifacts
just clean
For rapid development iteration:
# Test any JSON-RPC call with custom database
just test-json '' /tmp/test.db
# Quick minimal test
just test-clean /tmp/debug.db
# Build and test in one command
just build-test
This is a vibe-coded project, so contributions should match the energy:
LGPL 3.0 - Use it, modify it, vibe with it (but share improvements back to the community).
"It works on my machine, and that machine has good vibes." ✨
Install via CLI
npx mdskills install jcdickinson/simplememSimpleMem is a free, open-source AI agent skill. A vibe-coded memory management system with RAG capabilities for Claude via the Model Context Protocol (MCP). SimpleMem is an MCP server that provides persistent memory storage and retrieval for Claude and other MCP clients. It combines traditional file-based storage with modern RAG (Retrieval-Augmented Generation) capabilities, including semantic search and automatic relationship discovery. Think
Install SimpleMem with a single command:
npx mdskills install jcdickinson/simplememThis downloads the skill files into your project and your AI agent picks them up automatically.
SimpleMem works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Codex, Gemini Cli, Amp, Roo Code, Goose, Opencode, Trae, Qodo, Command Code. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.