Memorys

Package (npm 0.25.0)

npx -y [email protected]

Or add to your MCP client config:

{
  "mcpServers": {
    "memorys": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "DATABASE_URL": "<YOUR_VALUE>",
        "CUBA_PROJECT_FILTER": "<YOUR_VALUE>",
        "CUBA_SYNC_DIR": "<YOUR_VALUE>",
        "CUBA_JUDGE": "<YOUR_VALUE>",
        "CUBA_JUEZ_CLI": "<YOUR_VALUE>",
        "CUBA_JUEZ_MODEL": "<YOUR_VALUE>",
        "CUBA_REM_RELATION_BATCH": "<YOUR_VALUE>",
        "CUBA_RERANKER_PATH": "<YOUR_VALUE>",
        "CUBA_RERANK_FIXED_SHAPE": "<YOUR_VALUE>"
      }
    }
  }
}

• DATABASE_URL required — PostgreSQL connection URL (e.g. postgresql://user:pass@localhost:5432/brain)
• CUBA_PROJECT_FILTER — Set to 'off' to disable v0.8 project scoping filters (admin/debug only).
• CUBA_SYNC_DIR — Directory used by cuba_sync export/import (default ./.memory-industry/, falls back to ./.cuba-memorys/).
• CUBA_JUDGE — cuba_juez backend selector: nli | mcp_sampling | claude_cli | heuristic | auto (default auto).
• CUBA_JUEZ_CLI — Subprocess CLI used by ClaudeCodeJudge (default 'claude').
• CUBA_JUEZ_MODEL — Model name passed to the judge backend (default 'claude-haiku-4-5').
• CUBA_REM_RELATION_BATCH — Isolated entities the REM cycle scans for relations per run (default 5, 0 disables).
• CUBA_RERANKER_PATH — Directory holding the bge-reranker ONNX model; enables cross-encoder reranking (+93% nDCG on GPU).
• CUBA_RERANK_FIXED_SHAPE — Pad reranker batches to a constant 512 tokens. Defaults on for GPU builds, off on CPU.

Package (pypi 1.27.0)

uvx memory-industry

Or add to your MCP client config:

{
  "mcpServers": {
    "memorys": {
      "command": "uvx",
      "args": [
        "memory-industry"
      ],
      "env": {
        "DATABASE_URL": "<YOUR_VALUE>"
      }
    }
  }
}

• DATABASE_URL required — PostgreSQL connection URL (e.g. postgresql://user:pass@localhost:5432/brain)

Package (npm 0.25.0)

npx -y [email protected]

Or add to your MCP client config:

{
  "mcpServers": {
    "memorys": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}

Package (pypi 1.27.0)

uvx cuba-memorys

Or add to your MCP client config:

{
  "mcpServers": {
    "memorys": {
      "command": "uvx",
      "args": [
        "cuba-memorys"
      ]
    }
  }
}