frugal-memory MCP server

frugal-memory

<!-- mcp-name: io.github.komakeule57-maker/frugal-memory -->

A persistent memory for AI assistants that is just a SQLite file — and costs about a fifth of what reading markdown notes does.

No vector store, no embeddings, no external service, no API key. Python, SQLite with FTS5, stdio — the only dependency is the official mcp SDK. Nothing leaves your machine unless you explicitly turn on the optional fact check.

Measured over 275 real questions from 89 working sessions: 2,359 tokens per answered question, against 11,319 for the usual one markdown file per fact, found with grep and read whole. The gap grows as the memory does, because every answer here is capped and grep is not. All figures come from one installation, and the docs say where one did not hold up.

Why

An assistant's memory usually fails in one of two ways: it is a pile of markdown files that has to be read whole to be searched, or it is a vector database that answers that something matched but never why.

This one is a ranked full-text index over short entries, with two things bolted on that turn a note pile into a memory: entries are filed on two axes — where it belongs (project) and what kind of knowledge it is (pitfall, decision, measurement, …) — and when you write something down, the tool tells you which existing entries it overlaps with, so contradictions surface instead of quietly piling up.

Features

of about 1.2 KB in total instead of 4.2 KB of full text; zeige then fetches the entries you pick, about 6,000 characters per call unless you ask for everything. The worst case is known before you ask.

• Capped, calculable answers — a search returns eight preview lines

fetching an entry, that pair is remembered. Ask the same thing again and the entry that answered last time comes first. Word-for-word repeats only, and the header says when it fired.

• It learns from its own failures — when a search is followed by

vocabulary of knowledge kinds. Chronicle entries are hidden from search by default, but the header always says how many were held back.

• Two filing axes — a free-text project tag and a closed, enforced

existing entries and which numbers changed, so you can supersede instead of accumulate.

• Duplicate and contradiction hints — remember reports similar

view and stay findable, with a note on why and by what.

• Nothing is ever deleted — superseded entries drop out of the default

project's newest title lines for when you have forgotten the words to search for. Capped like everything else: one page, and a line saying how to get the rest.

• Browsing, not just searching — themen() lists projects and a

inside one project, with marke=. That filter is hard, so when the best match lies outside the project, recall names it instead of leaving you with a plausible-looking list of the wrong entries.

• Project-bound in use, not in search — the usual question is asked

whether two entries contradict each other or just supersede one another.

• Opt-in second opinion — optionally ask any OpenAI-compatible model

kinds are German; MEMORY_LANG=en switches all of it. The search also matches inflected forms and compound parts ("Rangliste" finds "Ranglisten"). Measured, that rarely changes the answer: the plain any-term stage of the search already finds what the stems would add (details).

• German by default, English on request — tool names, messages and

Requirements

• Python 3.11+
• The mcp SDK (requirements.txt, that's the whole list)
• SQLite with FTS5 — included in standard CPython builds
• Optional, for the fact check only: any OpenAI-compatible endpoint

Setup

From PyPI, as a command in its own environment:

pipx install frugal-memory        # or: uv tool install frugal-memory

Shortened. The full README is on GitHub.