MemoryLayer

Official registry Security

Local-first persistent memory for AI agents, with reasoning and formal verification.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package @raajvamsy/memorylayer
Claude Code
claude mcp add memorylayer -e 'MEMORY_API_KEY=<your memory_api_key>' -- npx -y @raajvamsy/memorylayer@1.7.1
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "memorylayer": {
            "command": "npx",
            "args": [
                "-y",
                "@raajvamsy/memorylayer@1.7.1"
            ],
            "env": {
                "MEMORY_API_KEY": "<your memory_api_key>"
            }
        }
    }
}

Environment variables

  • MEMORY_API_KEY secret Optional MemoryLayer API key for higher rate limits. Memory content never leaves your machine; the key is used only for license validation. Get one free at https://memorylayer.in

Frequently asked questions

What is MemoryLayer?

Local-first persistent memory for AI agents, with reasoning and formal verification.

How do I install MemoryLayer?

It runs on your machine. In Claude Code: claude mcp add memorylayer -e 'MEMORY_API_KEY=<your memory_api_key>' -- npx -y @raajvamsy/memorylayer@1.7.1. For other clients, paste the JSON configuration from this page into their MCP settings.

Does MemoryLayer need an API key?

Yes. It expects MEMORY_API_KEY, which you set in its configuration.

Who maintains MemoryLayer?

It is published by in.memorylayer. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.