mnemon-memory-mcp
A local-first, zero-cloud MCP server providing persistent layered memory for AI agents. It uses a single SQLite file with FTS5 and optional vector search to store episodic, semantic, procedural, and reference memories, enabling agents to retain context across sessions without external APIs or telemetry.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
Checks and signals
Each line is separate evidence, not a trust score.
- Popularity 3 GitHub stars
What you can do with it
- Provide long-term memory for AI agents across sessions
- Search memories using hybrid lexical and vector retrieval
- Import knowledge bases from markdown into structured memories
- Manage memory layers with different lifetimes and access patterns
Source and maintenance
- Last repository push
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
mnemon-mcp 1.0.1
{
"version": "1.0.1",
"transport": "stdio",
"identifier": "mnemon-mcp",
"registryType": "npm",
"environmentVariables": [
{
"name": "MNEMON_DB_PATH",
"description": "Path to SQLite database file (default: ~/.mnemon-mcp/memory.db)"
},
{
"name": "MNEMON_EMBEDDING_PROVIDER",
"description": "Embedding provider for vector search: 'openai' or 'ollama' (default: disabled)"
},
{
"name": "MNEMON_EMBEDDING_API_KEY",
"description": "API key for embedding provider (required for OpenAI)"
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"mnemon-memory-mcp": {
"command": "npx",
"args": [
"-y",
"mnemon-mcp@1.0.1"
],
"env": {
"MNEMON_DB_PATH": "<YOUR_MNEMON_DB_PATH>",
"MNEMON_EMBEDDING_PROVIDER": "<YOUR_MNEMON_EMBEDDING_PROVIDER>",
"MNEMON_EMBEDDING_API_KEY": "<YOUR_MNEMON_EMBEDDING_API_KEY>"
}
}
}
}Cline
{
"mcpServers": {
"mnemon-memory-mcp": {
"command": "npx",
"args": [
"-y",
"mnemon-mcp@1.0.1"
],
"env": {
"MNEMON_DB_PATH": "<YOUR_MNEMON_DB_PATH>",
"MNEMON_EMBEDDING_PROVIDER": "<YOUR_MNEMON_EMBEDDING_PROVIDER>",
"MNEMON_EMBEDDING_API_KEY": "<YOUR_MNEMON_EMBEDDING_API_KEY>"
}
}
}
}VS Code
{
"servers": {
"mnemon-memory-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mnemon-mcp@1.0.1"
],
"env": {
"MNEMON_DB_PATH": "<YOUR_MNEMON_DB_PATH>",
"MNEMON_EMBEDDING_PROVIDER": "<YOUR_MNEMON_EMBEDDING_PROVIDER>",
"MNEMON_EMBEDDING_API_KEY": "<YOUR_MNEMON_EMBEDDING_API_KEY>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"mnemon-memory-mcp": {
"command": "npx",
"args": [
"-y",
"mnemon-mcp@1.0.1"
],
"env": {
"MNEMON_DB_PATH": "<YOUR_MNEMON_DB_PATH>",
"MNEMON_EMBEDDING_PROVIDER": "<YOUR_MNEMON_EMBEDDING_PROVIDER>",
"MNEMON_EMBEDDING_API_KEY": "<YOUR_MNEMON_EMBEDDING_API_KEY>"
}
}
}
}Let your agent find its tools
Find servers like mnemon-memory-mcp from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.