frugal-memory runs on your own machine — the client starts it, so there is no endpoint to ping. 2 174 installs a week from pypi. Last commit 22 Oct 2026.
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
Today is the operative word: we check frugal-memory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add frugal-memory -- uvx frugal-memory
{
"mcpServers": {
"frugal-memory": {
"command": "uvx",
"args": [
"frugal-memory"
]
}
}
}
[mcp_servers.frugal-memory]
command = "uvx"
args = ["frugal-memory"]
{
"mcpServers": {
"frugal-memory": {
"command": "uvx",
"args": [
"frugal-memory"
]
}
}
}
{
"servers": {
"frugal-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"frugal-memory"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
MEMORY_LANG (Tool names and texts: 'de' (default) or 'en'), MEMORY_DB (Path of the SQLite file. Default: $XDG_DATA_HOME/frugal-memory/memory.db).
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
Embedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Answers built from our own checks of this server.