Memory Vault

io.github.apurv101Published by GitHub account apurv101v0.5.0Updated Oct 24, 2026

Portable AI memory shared across models and harnesses - plain markdown you own.

The publisher's own server: Memory.fit

VerifiedStreamable HTTPWeb executableKnowledge & Memory

Overview

AI-generated overview

Memory Vault is a portable AI memory server that stores shared memory as plain markdown files you own, usable across models and harnesses.

What you can do
Provides a shared memory store that assistants can read and write across different models and harnesses, so context carries over between tools rather than being tied to one assistant. Memory is kept as plain markdown files in a directory you control, so you can inspect, edit, back up or move it yourself. Runs either as a remote endpoint or as a local process started with npx, with the storage directory and listening port configurable.
When to use it
Useful when you work with several AI assistants or harnesses and want one memory that persists across them, or when you want your assistant's memory to live in readable files you own rather than in a vendor's database.
Requirements
Either the remote endpoint with OAuth sign-in, or a local process run with npx (Node.js). The local server reads the MEMORY_DIR environment variable for the storage directory (defaults to ~/.memory-vault) and VAULT_PORT for the listening port (defaults to 8787).
Before you install
Authentication is required, so you sign in with an OAuth account. Memory is written and changed by the assistant, so review what it stores; the local server listens on a port, so consider whether that port is reachable beyond your machine. Memory content may be sent to the remote endpoint when you use the hosted option.

Installation

In SourceWeft

  1. Open Memory Vault in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.apurv101%2Fmemory-vault/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "memory-vault": {
      "type": "http",
      "url": "https://memoryvault.click/mcp"
    }
  }
}

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.5.0LatestSep 16, 2026

Score

60% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • 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

Memory.fit

fit.memoryOfficial publisher

Hosted Memory.fit server that lets an AI read your training, sleep, recovery and nutrition data and write back weekly plans, targets and meal plans.

Streamable HTTPWeb executableAuth
Location & LifestyleCredential requiredOct 29, 2026

pg.ddx.io: the PostgreSQL community's memory

io.ddx.pgOfficial publisher

pg.ddx.io: the PostgreSQL community's memory's hosted MCP server, published by pg.ddx.io; no sign-in required; Streamable HTTP; 29 tools.

Streamable HTTPWeb executable
Databases29 toolsOct 24, 2026

var.gg Naming Memory

gg.varOfficial publisher

Remote MCP server that suggests and searches code identifier names from domain concepts in Korean, Japanese, Chinese, Vietnamese and English, and exposes ERD…

Streamable HTTPWeb executable
Databases7 toolsOct 27, 2026

Counterparts

ai.counterparts

Local-first long-term memory for Claude Code and Claude Desktop: the assistant writes notes about you and your projects and recalls them in later sessions.

STDIODesktop only
Knowledge & MemoryNot validated yetNov 7, 2026

LAHZE - Persian AI Memory Platform

Published by GitHub account pedramgholizadeh

LAHZE - Persian AI Memory Platform's hosted MCP server; no sign-in required; Streamable HTTP; 13 tools.

Streamable HTTPWeb executable
Location & Lifestyle13 toolsNov 3, 2026