rememberLABSCO SUMMARY
Memory as a file, not as a service.
The comparison the project draws is with SQLite, and it is the right one: no server to run, no account to create, one file you can back up or delete. That also sets the ceiling — this is a store with good ranking, not an agent framework, and the embedding quality you get depends on which extra you install. Base install falls back to keyword matching with no dependencies at all.
What it is
An embeddable memory layer with a built-in MCP server. Memories live in SQLite on your machine and survive session restarts, tool switches and context-window resets, so what you tell one assistant stays available to the next one. The Python API is three calls — remember(), recall(), forget() — and the MCP server exposes the same store to Claude Code, Cursor, Gemini CLI and other MCP clients.
What you get
- Cross-session persistence: a decision made Monday is still known on Friday, without replaying the conversation history
- Cross-tool memory — what you teach one assistant is readable from the others pointed at the same store
- Recall ranked by semantic similarity, recency and importance rather than brute-force history search, with automatic categorisation and scope routing (preferences go global, decisions stay in the project)
- Pluggable embeddings: built-in keyword matching with zero dependencies, local sentence-transformers, a local Ollama instance, or OpenAI
- Optional encryption of memory text and metadata at rest, with no external dependencies
- Automatic deduplication that runs during normal use, the way SQLite's auto-vacuum does — nothing to schedule
- Everything local: no cloud calls, no telemetry, no data collection
Requirements
No account and no key on the base install. pip install memorymesh, then point your client at the memorymesh-mcp command — the PyPI package is memorymesh, published as io.github.sparkvibe-io/memorymesh, and the transport is stdio. Extras pull in the optional back ends: memorymesh[local] for on-device embeddings, memorymesh[ollama], memorymesh[openai], or memorymesh[all]. A hosted instance is also reachable through Smithery with npx -y @smithery/cli install @sparkvibe-io/memorymesh --client claude if you would rather not install anything. Runs on Linux, macOS and Windows. MIT licensed.
Setup effort
One command — pip install memorymesh
USE CASES
01
Not repeating yourself to a new session
Store the key facts and decisions after a session; the next one recalls only the relevant ones instead of replaying the whole history.
02
Carrying context between different AI tools
Point Claude Code, Cursor and Gemini CLI at the same store so a preference set in one is known in the others.
03
Keeping project decisions out of your global memory
Automatic categorisation routes preferences to the global scope and decisions to the project, so an unrelated repo does not inherit them.
04
Running memory with nothing installed but Python
The base install uses built-in keyword matching and no external dependencies; add a local, Ollama or OpenAI embedder later if recall quality matters.
10 tools
Listed in project docs. Your client may show a different list.
recallforgetforget_allupdate_memorymemory_statssession_startreview_memoriesstatusconfigure_projectBEFORE YOU INSTALL
What to know first
Tools you get
10 tools named in the project's documentation.
Requires
memorymesh-mcp on PATH
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install memorymeshMCP Clients
Claude Code, Claude Desktop, Cursor, Gemini CLI
JSON
{
"mcpServers": {
"memorymesh": {
"command": "memorymesh-mcp"
}
}
}Smithery
SMITHERY · TERMINAL
npx -y @smithery/cli install @sparkvibe-io/memorymesh --client claude
