Home › Knowledge & Memory › Turbo Quant Memory

Turbo Quant Memory

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

Python

★ 10 stars Last pushed 2026-11-04 License: MIT

View repository → Website →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (pypi 0.34.0)

uvx turbo-quant-memory

Or add to your MCP client config:

{
  "mcpServers": {
    "turbo_quant_memory": {
      "command": "uvx",
      "args": [
        "turbo-quant-memory"
      ],
      "env": {
        "TQMEMORY_FTS_LANGUAGE": "<YOUR_VALUE>",
        "TQMEMORY_EMBEDDING_BACKEND": "<YOUR_VALUE>",
        "TQMEMORY_MIGRATE_ON_STARTUP": "<YOUR_VALUE>",
        "TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_VALUE>"
      }
    }
  }
}

TQMEMORY_FTS_LANGUAGE — Snowball stemmer for the BM25 lane. Use Russian for Cyrillic-dominant corpora.
TQMEMORY_EMBEDDING_BACKEND — Embedder backend. Default fastembed (ONNX); sentence-transformers needs the [torch] extra.
TQMEMORY_MIGRATE_ON_STARTUP — Set to 1 to apply pending schema migrations automatically on startup.
TQMEMORY_SECRETS_PASSPHRASE secret — Argon2id passphrase for the secrets vault on headless hosts. Omit to use the OS keyring.

This server takes extra arguments — see its repository.