memmd-mcp
Provides a shared memory layer for OpenAI Codex, allowing agents to persist and retrieve structured memories (facts, context, preferences) across sessions via a single memory.md file.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@memmd-mcpremember that I'm using Python 3.12 for memmd-mcp"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
memmd-mcp
A shared memory layer for AI agents — one memory.md synced across Claude Desktop, Cursor, Claude Code, OpenAI Codex, and any MCP client. Auto-deduplication, contradiction resolution, and stale cleanup included.
Why memmd?
One memory, every client — Claude Desktop, Cursor, Claude Code, OpenAI Codex share the same
memory.mdZero external dependencies beyond
mcp— no embeddings, no API keys, fully offlineDeterministic, rule-based — no LLM calls for memory management
Human-readable
memory.md— inspect and edit anytime
Features
Deduplication — fingerprint + Jaccard similarity merges near-identical entries
Contradiction resolution — detects conflicting facts, keeps latest, archives old
Structured categories — Work Context · Projects · Personal Preferences · Archive
Section-aware recall — filter by category, keyword search with scoring
Stale cleanup — auto-archives old, unused entries on
summarize()Korean support — category aliases, fact patterns (
~는 ~), stopwords
Quick Start
Install and run
uvx memmd-mcpAdd to your MCP client
{
"mcpServers": {
"memmd": {
"command": "uvx",
"args": ["memmd-mcp"],
"env": {
"MEMMD_MEMORY_PATH": "/absolute/path/to/memory.md"
}
}
}
}Config location by client:
Claude Desktop —
~/Library/Application Support/Claude/claude_desktop_config.jsonClaude Code —
.claude/settings.jsonor user settingsCursor —
~/.cursor/mcp.jsonOpenAI Codex —
~/.codex/config.toml
Tools
Tool | Description |
| Store with auto-dedupe and contradiction merge |
| Search with keyword scoring and category filters |
| Delete by ID |
| Category overview + stale entry cleanup |
How It Works
remember
Dedupes by SHA-1 fingerprint and Jaccard similarity (>0.82)
Extracts facts from
key: value,key = value,key is value,key는 valueOn conflict: latest value wins, old entry archived with history
recall
Keyword search with token-overlap scoring
Filters:
category:Projects API token,section:"Work Context" deployKorean aliases accepted (
category:프로젝트)
summarize
Per-category summary of recent entries
Archives stale entries (default: >120 days, <3 accesses, no recent recall)
memory.md Format
# memory.md
<!-- memmd:version=1 -->
## Work Context
<!-- memmd-entry {...json...} -->
Memory content
## Projects
...
## Personal Preferences
...
## Archive
...Environment Variables
Variable | Default | Description |
|
| Path to memory file |
|
| Days before stale cleanup (min: 7) |
License
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/matamong/memmd-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server