Memwright MCP Server

by bolnet Your server? Claim it

local only

Memwright runs on your own machine — the client starts it, so there is no endpoint to ping. 108 installs a week from pypi. Last commit 30 May 2026.

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

Installs per day peak 130 · avg 39 · -33% w/w

a month agotoday

108

Installs / week

pypi · memwright

Stars

0 open issues

30 May 2026

Last commit

0 releases in 90 days

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Memwright every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add memwright -- uvx memwright

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memwright": {
      "args": [
        "memwright"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.memwright]
command = "uvx"
args = ["memwright"]

.cursor/mcp.json

{
  "mcpServers": {
    "memwright": {
      "args": [
        "memwright"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "memwright": {
      "args": [
        "memwright"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: PG_CONNECTION_STRING (PostgreSQL connection string for pgvector (default: postgresql://memwright:memwright@localhost:5432/memwright)), NEO4J_PASSWORD (Neo4j database password (default: memwright)), OPENROUTER_API_KEY (OpenRouter API key for embeddings (required for semantic search)), OPENAI_API_KEY (OpenAI API key for embeddings (alternative to OpenRouter)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Memwright

same job, measured the same way

Memory Engine MCP

by simoneb79

Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.

local only

rmbr

by srock44

Embedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.

130 installs/wk local only

Citadel

by citadeldb

Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools

1 508 installs/wk local only

ContextBridge

by thundereagle

MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.

local only

Local Memory

by studiomeyer-io

Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.

70 installs/wk local only

Engram

by hbarefoot

Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.

82 installs/wk local only

Memory Fts

by kurovu146

Long-term memory for Claude Code with SQLite FTS5 search and BM25 ranking

33 installs/wk local only

Nuzo Memory

by fabionfsc

Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage.

35 installs/wk local only

Memwright — questions

Answers built from our own checks of this server.

Why is there no uptime for Memwright?

Memwright runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package memwright was installed 108 times last week.

How do I connect Memwright?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls memwright straight from pypi; nothing to host, nothing to sign up for.

How many people use Memwright?

The pypi package memwright was installed 108 times in the last week. Week over week that is -33%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Memwright open source?

Yes — it is published under the MIT licence, written in Python and 14 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.