N3MemoryCore Lite (Working Memory)

About N3MemoryCore Lite (Working Memory)

Use N3MemoryCore Lite (Working Memory) with your agent

claude mcp add n3memorycore-lite-working-memory -- uvx n3memorycore-mcp-lite

{
  "mcpServers": {
    "n3memorycore-lite-working-memory": {
      "command": "uvx",
      "args": [
        "n3memorycore-mcp-lite"
      ]
    }
  }
}

Frequently asked questions

What is N3MemoryCore Lite (Working Memory)?

N3MemoryCore Lite (Working Memory) is an MCP (Model Context Protocol) server by neuralnexusnote in the RAG Systems category. Ephemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.

How do I connect N3MemoryCore Lite (Working Memory) to Claude, Cursor, or another MCP client?

Install N3MemoryCore Lite (Working Memory) from its pypi package (n3memorycore-mcp-lite) 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 N3MemoryCore Lite (Working Memory) open source?

Yes — the source code is public at github.com/neuralnexusnote/n3mcmcp-lite.

Can AI agents pay to use N3MemoryCore Lite (Working Memory)?

Not yet through Loomal — N3MemoryCore Lite (Working Memory) 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.