MCP servers · bryceblackroot

MemoryComb: a shared local memory for AI assistants

A memory library on your computer that Claude, ChatGPT and other AI tools can read and write together, in early testing on Mac and Windows.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

MemoryComb keeps one memory on your computer that Claude, ChatGPT and other AI tools all read and write, so context does not have to be explained again when switching between them. Every read produces a receipt, and an AI Scorecard shows which AI's facts turned out wrong. Each memory is checked for hidden instructions before an AI reads it, and AIs can fact-check each other, with the user settling any disagreement.

It suits people who use several AI assistants and want them to work from the same information. Import brings in what ChatGPT, Claude, Gemini or Grok already know about the user. Team sharing lets colleagues work from one shared memory.

In the Claude app, the .mcpb file from the latest release is installed by double-clicking it. Other tools are set up from Terminal on Mac or PowerShell on Windows; the Windows installer works for the current user only, without an admin password, and starts at login. A local dashboard then opens for connecting AIs. Memory stays in a folder on the computer, with encrypted daily backups to iCloud Drive or OneDrive. Uninstalling removes the app but keeps the memory folder.

Limitations and requirements

Early test software, available on Mac and Windows; Windows is the newer build. Team sharing runs from the computer of whoever starts the shared project and works only while that computer is on. Sharing is off unless switched on. The Claude app shows a "not verified" warning for extensions not yet in its directory. The software goes online once a day to check for a newer version. Memories and AI answers can be wrong, the software is provided as is, and nothing in it is professional advice.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    MemoryComb

    One memory for every AI: Claude, ChatGPT and more share a memory that lives on your computer.

    v0.3.2
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 17 Nov 2026