Installation

Requirements

• Python 3.12+
• pip, uv, or pipx
• An embedding provider for semantic search — pick one during mm init (see Embedding Providers below). Fine to skip at first: memtomem works keyword-only until you choose.

Which installer should I use?

Situation	Recommended choice	Why
First installation	uv tool install 'memtomem[all]'	isolated persistent CLI, with every feature used by this site
Existing pipx-managed CLI environment	pipx install 'memtomem[all]'	keeps the same tool-management workflow
Project dependency or controlled virtual environment	pip install 'memtomem[all]'	keeps the package version inside that environment

Verify python --version and uv --version before installing. On Windows, use py --version if python is unavailable. For the shortest no-model-download path, complete Quick Start with the Minimal preset first.

LTM Server (memtomem)

uv (recommended)

uv tool install 'memtomem[all]'

pipx

pipx install 'memtomem[all]'

pip

pip install 'memtomem[all]'

[all] is the recommended first install because it matches the main docs: ONNX dense embeddings, Korean tokenizer, Ollama / OpenAI providers, code chunking, the Web UI, Langfuse tracing, and LangGraph Store adapters. For a leaner footprint, drop the extras for a BM25-only install:

uv tool install memtomem                      # no extras — dense search, Web UI, Korean tokenizer unavailable until added

Opt into features later with e.g. uv tool install --reinstall 'memtomem[onnx,web]'.

After installing, verify the binary and upgrade with refreshed package metadata if the version looks stale:

mm --version
uv tool install 'memtomem[all]' --refresh

Optional extras

The extras below are what [all] bundles — install them individually when you want a narrower footprint.

Extra	Description	Command
onnx	fastembed local embeddings (recommended default)	pip install memtomem[onnx]
ollama	Ollama provider client	pip install memtomem[ollama]
openai	OpenAI provider client	pip install memtomem[openai]
korean	kiwipiepy Korean morphological analysis	pip install memtomem[korean]
code	tree-sitter AST chunking (Python / JS / TS)	pip install memtomem[code]
web	FastAPI + uvicorn Web UI	pip install memtomem[web]
langfuse	Langfuse observability tracing	pip install memtomem[langfuse]
langgraph	MemtomemStore and MemtomemBaseStore adapters	pip install memtomem[langgraph]
all	Everything	pip install memtomem[all]

mm CLI

After installation, the commands you’ll reach for most often:

Command	Purpose
mm init	Interactive setup wizard
mm status	Post-install DB / config / embedding health check
mm search <query>	Search the knowledge base
mm add <content>	Add a memory entry
mm web	Launch Web UI dashboard (http://localhost:8080)
mm --version · mm version	Print installed version

Full command list (including ingest, session, context, wiki, watchdog, schedule, tags, upgrade, uninstall): see the CLI Reference.

The MCP server itself ships as the memtomem-server console script. You don’t run it by hand — your MCP client launches it after registration. For plugin, scope, configuration-file, restart, and verification paths across all released clients, see Connect an AI Client.

Preset choice

Wizard label	Provider path	Download / network boundary	Recommended for
Minimal	BM25 keyword search only	no model download	first smoke test and exact identifiers
English (Recommended)	local ONNX embedding + English reranker	downloads local models once	mostly English projects
Korean-optimized	multilingual embedding + reranker + Korean tokenizer	downloads local models once	Korean or multilingual notes

The CLI tokens remain --preset minimal, --preset english, and --preset korean. Remote Ollama or OpenAI-compatible providers are explicit later choices; selecting them can send request data to the configured service.

File locations

memtomem keeps its local database and configuration under your home directory. The default ONNX path stays on the machine; optional remote embedding, LLM, rerank, and tracing providers send the configured request data to their endpoints.

Path	What
~/.memtomem/memtomem.db	SQLite store (chunks + vectors)
~/.memtomem/config.json	LTM configuration written by mm init
~/.memtomem/logs/web.log	Web UI log (from mm web -b)

Override the config directory with the MEMTOMEM_* env vars (see Configuration).

STM Proxy (memtomem-stm)

STM is optional. Install it after the LTM quick-start flow works if you want proactive memory surfacing (presenting relevant memories) or tool-response compression.

uv (recommended)

uv tool install memtomem-stm

pipx

pipx install memtomem-stm

pip

pip install memtomem-stm

uvx (no install)

uvx memtomem-stm --help

For ad-hoc execution only — use uv tool install or another tab for a permanent install with client registration.

Optional extras

Extra	Description	Command
langfuse	Langfuse observability tracing	pip install memtomem-stm[langfuse]
langchain	LangChain agent integration	pip install memtomem-stm[langchain]

mms CLI

After installation, the following commands are available:

Command	Purpose
mms init --demo --client auto	First-time, no-network demo + detected-client registration
mms doctor	Validate config, client registration, upstreams, and optional LTM
mms register --client claude|codex|auto	Register or refresh STM in a supported client
mms add <name> --command <cmd>	Register an upstream MCP server
mms add --from-clients	Bulk-import upstreams from existing MCP client configs
mms eject <name>	Restore an imported server to its original client and unregister it from STM
mms list	List registered servers (with a SURFACING column)
mms status	Config summary — enabled flag and server count
mms health	Probe upstream connectivity + LTM surfacing readiness
mms project route	Preview routing selected project MCPs through STM (--apply writes)
mms --version	Print installed version

The STM proxy itself ships as the memtomem-stm console script. As with LTM, you don’t launch it by hand — once STM is registered with your MCP client via mms init --client ..., mms register --client ..., or a generic JSON entry, the client starts it automatically. STM writes its proxy config to ~/.memtomem/stm_proxy.json; mms add / mms init manage it for you, so you rarely hand-edit it.

Embedding Providers

Provider	Setup	GPU	Cost
ONNX (fastembed)	Built-in	Not required	Free
Ollama	ollama pull nomic-embed-text	Not required	Free
OpenAI	API key required	—	Paid

Not sure which to pick? Start with ONNX — inference is local, free, and needs no extra daemon or API key. You can switch later by re-running mm init or setting MEMTOMEM_EMBEDDING__PROVIDER (note the double underscore — nested pydantic-settings keys use __ as delimiter).

Tech Stack

Category	Technology
MCP	FastMCP (stdio, SSE, Streamable HTTP)
Framework	Pydantic v2, Click (CLI), FastAPI (Web UI)
Database	SQLite (FTS5 full-text search), sqlite-vec (vector search)
Code parsing	tree-sitter (Python, JS, TS AST)
Korean	kiwipiepy morphological analyzer (optional)
Observability	Langfuse (optional)