vector-memory

About vector-memory

Use vector-memory with your agent

claude mcp add vector-memory -- uvx mcp-server-vector-memory

{
  "mcpServers": {
    "vector-memory": {
      "command": "uvx",
      "args": [
        "mcp-server-vector-memory"
      ]
    }
  }
}

Frequently asked questions

What is vector-memory?

vector-memory is an MCP (Model Context Protocol) server by neerajg03 in the Knowledge & Memory category. Semantic document memory using Redis vector store. Save and recall files with natural language.

How do I connect vector-memory to Claude, Cursor, or another MCP client?

Install vector-memory from its pypi package (mcp-server-vector-memory) 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 vector-memory open source?

Yes — the source code is public at github.com/neerajg03/vector-memory.

Can AI agents pay to use vector-memory?

Not yet through Loomal — vector-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.