Turbo Quant Memory for VS Code

io.github.lexus2016/turbo-quant-memory

Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.

client:VS Code transport:stdio runtime:pypi

Install Turbo Quant Memory in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "tqmemory-fts-language",
      "description": "TQMEMORY_FTS_LANGUAGE",
      "password": true
    },
    {
      "type": "promptString",
      "id": "tqmemory-embedding-backend",
      "description": "TQMEMORY_EMBEDDING_BACKEND",
      "password": true
    },
    {
      "type": "promptString",
      "id": "tqmemory-migrate-on-startup",
      "description": "TQMEMORY_MIGRATE_ON_STARTUP",
      "password": true
    },
    {
      "type": "promptString",
      "id": "tqmemory-secrets-passphrase",
      "description": "TQMEMORY_SECRETS_PASSPHRASE",
      "password": true
    }
  ],
  "servers": {
    "turbo-quant-memory": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "turbo-quant-memory"
      ],
      "env": {
        "TQMEMORY_FTS_LANGUAGE": "${input:tqmemory-fts-language}",
        "TQMEMORY_EMBEDDING_BACKEND": "${input:tqmemory-embedding-backend}",
        "TQMEMORY_MIGRATE_ON_STARTUP": "${input:tqmemory-migrate-on-startup}",
        "TQMEMORY_SECRETS_PASSPHRASE": "${input:tqmemory-secrets-passphrase}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

Turbo Quant Memory in other clients

Turbo Quant Memory MCP server