Memorymesh

Persistent, zero-dependency AI memory using SQLite.

Connector by sparkvibe-io · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/sparkvibe-io-memorymesh

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 4 read · 4 write · 0 delete · 2 not yet classified
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 10

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

memory_stats
recall
review_memories
status

Write 4 · Create, change, send or run things.

configure_project
remember
session_start
update_memory

Not yet classified 2 · We could not tell from the name and description.

forget
forget_all

Files it touches

Any path the agent passes to its tools

Tools (10)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

configure_project
Set the project root at runtime without restarting the server. Use this when automatic project detection failed and you know the correct project path. Creates the project database at <path>/.memorymesh/memories.db.
forget
Forget (permanently delete) a specific memory by its ID. Use this when information is outdated or incorrect. Searches both project and global stores.
forget_all
Forget ALL stored memories in the specified scope. This is a destructive operation. Defaults to project scope only -- global memories are protected unless explicitly targeted.
memory_stats
Get statistics about stored memories: total count, oldest memory timestamp, and newest memory timestamp. Optionally filter by scope.
recall
Recall relevant memories from MemoryMesh. Searches stored memories using semantic similarity (when embeddings are enabled) and keyword matching. Returns the most relevant memories ranked by relevance.
remember
Store a new memory in MemoryMesh. Use this to save facts, preferences, decisions, or any information that should persist across conversations. Returns the unique memory ID.
review_memories
Audit memories for quality issues (scope mismatches, verbosity, staleness, duplicates). Returns issues with suggestions.
session_start
Retrieve structured context for the start of a new AI session. Returns user profile, guardrails, common mistakes, and project context to help the AI understand the user and avoid past errors. Call this at the beginning of every conversation.
status
Get MemoryMesh health status: project store, global store, embedding provider, and version. Use this to diagnose configuration issues. If project store is not configured, shows what detection was attempted and how to fix it.
update_memory
Update an existing memory's text, importance, scope, or metadata in place. Only the provided fields are changed; omitted fields keep their current values.

Signals

Weekly downloads: 26
Last release: Feb 28, 2026 (8 months ago)
Last package publish: Mar 3, 2026 (8 months ago)

From the package registry.

Details

Registry name: io.github.sparkvibe-io/memorymesh
Version: 4.1.0
Auth: No auth
Packages: pypi memorymesh
License: MIT
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry