Loomal

memwright

MCP server by github.com/bolnet/agent-memory

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

13 starspypi: memwright

About memwright

memwright is an MCP (Model Context Protocol) server published by bolnet in the official MCP registry, listed under Databases on Loomal. Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

It ships as a Python package on PyPI (memwright), so any MCP client that can launch a local process can run it.

Development happens in the open at github.com/bolnet/agent-memory, where the project has earned 13 GitHub stars.

Use memwright with your agent

Claude Code · one command
claude mcp add memwright -- uvx memwright
Claude Desktop, Cursor & other MCP clients · config
{
  "mcpServers": {
    "memwright": {
      "command": "uvx",
      "args": [
        "memwright"
      ]
    }
  }
}
pypimemwright

Frequently asked questions

What is memwright?
memwright is an MCP (Model Context Protocol) server by bolnet in the Databases category. Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
How do I connect memwright to Claude, Cursor, or another MCP client?
Install memwright from its pypi package (memwright) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
Is memwright open source?
Yes — the source code is public at github.com/bolnet/agent-memory, with 13 GitHub stars.
Can AI agents pay to use memwright?
Not yet through Loomal — memwright is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.

Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain memwright? Claim this listing free by verifying GitHub ownership, or contact us.