Home › Knowledge & Memory › michael-denyer/memory-mcp

michael-denyer/memory-mcp

Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.

Python Local macOSWindowsLinux

★ 15 stars Last pushed 2026-11-11 License: MIT

View repository →

Connect

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

uvx hot-memory-mcp

Or add to your MCP client config:

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

MEMORY_MCP_DB_PATH — Path to SQLite database file
MEMORY_MCP_EMBEDDING_MODEL — Embedding model to use (default: all-MiniLM-L6-v2)

Direct local file system access.

Up-to-date docs for AI agents

Hindsight: long-term memory for AI agents modeled on human memory.

Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.

Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, exportable to vector…

Local-first knowledge management with bi-directional LLM sync via Markdown files.

Data from the Official MCP Registry