Memwright

Overview

Memwright is a Model Context Protocol server that provides embedded memory for AI agents, combining SQLite, pgvector, and Neo4j graph search into a single interface. Any MCP-compatible AI assistant can use Memwright's tools directly, letting the model decide when to store, retrieve, and reason over information during conversations and agent runs.

Memwright runs locally as a Python package installed via uvx memwright. It communicates with your AI assistant over MCP via stdio. The current release is v0.1.3, distributed under the MIT license with source code available at bolnet/agent-memory on GitHub, where the project has 14 stars.

Memwright sits in the AI & Agents category on mcp.site and works with any MCP client, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain Memwright, claim this listing to verify ownership, earn the Verified badge, and keep the information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "memwright": {
      "command": "uvx",
      "args": [
        "memwright"
      ]
    }
  }
}