Memorymesh

Gives an assistant persistent local memory stored in SQLite, so context survives across sessions and tools.

What you can do

Memorymesh provides persistent AI memory backed by SQLite, described as zero-dependency and local-first. It is meant to be portable across tools, so stored memories can be reused by different assistants or clients rather than being tied to one. The manifest lists no tools, so the specific operations it exposes are not documented in the supplied material.

When to use it

Worth considering when you want an assistant to remember information between conversations and keep that memory on your own machine. It suits users who move between multiple AI tools and want one shared memory store.

Requirements

Runs as a local process on the user's machine over stdio, installed from the PyPI package memorymesh, so a Python environment is needed. Desktop only; no web execution. No authentication, environment variables, or headers are declared.