MCP Memory

io.github.GermaniUPublished by GitHub account GermaniUv0.6.0Updated Oct 26, 2026

Local persistent memory for AI agents: SQLite + FTS5 (BM25) lexical search, zero external infra.

The publisher's own server: Memory.fit

VerifiedSTDIODesktop onlyKnowledge & Memory

Overview

AI-generated overview

Local persistent memory for AI agents, storing memories in a SQLite file with FTS5/BM25 lexical search and no external infrastructure.

What you can do
  • Store and keep persistent memories for an AI agent across sessions
  • Search stored memories using SQLite FTS5 full-text (BM25) lexical search
  • Run entirely on the local machine with a single SQLite file and no external services
When to use it
Useful when you want an assistant to remember information between sessions without running a database server or sending data to a hosted memory service, and keyword-based retrieval is enough.
Requirements
Runs as a local process via Docker (image ghcr.io/germaniu/mcp-memory:0.6.0, stdio transport). Set DB_PATH to the SQLite file path inside the container and keep it under the mounted /data volume so memories survive restarts. No authentication is declared.
Before you install
Memories are written to a SQLite file on your machine; if DB_PATH is outside the mounted volume, data is lost when the container restarts. Stored content persists locally and may include anything the assistant chooses to save, so review what gets remembered.

Installation

In SourceWeft

  1. Open MCP Memory in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.6.0LatestOct 17, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.

Other Memory integrations