Skip to main content
Glama
chatmcp_memory

chatmcp_memory

by vearne

chatmcp_memory

An MCP server able to give large language models the power to remember. Only supports daodao97/chatmcp

Principle

daodao97/chatmcp uses SQLite to store chat history between users and the LLM. Therefore, chatmcp_memory can directly query SQLite to retrieve previous conversations, achieving memory retrieval.

Related MCP server: llama-memory

Usage

chatmcp_memory will attempt to automatically discover the location of chatmcp.db. Of course, it can also be specified via environment variables.

export DB_FILE_PATH=/tmp/chatmcp.db

1. use with uvx

"mcpServers": {
    "chatmcp_memory": {
        "command": "uvx",
        "args": ["chatmcp_memory"]
    }
}

2.Install and Run

pip install chatmcp_memory

Method 1: Run with transport 'stdio'

python3 -m chatmcp_memory

Method 2: Run with transport 'streamable-http'

python3 -m chatmcp_memory --http --bind="127.0.0.1" --port=8090

Server URL: http://127.0.0.1:8090/mcp/

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Centralizes verbatim local AI conversation history into a SQLite database and exposes it via an MCP server, enabling tools like Claude Code and Codex to retrieve exact context from other tools.
      1 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides persistent history and semantic memory for llama-server, enabling cross-session recall and memory management through MCP tools.
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables MCP-capable AI clients to share one local SQLite-backed memory of preferences, decisions, tasks, and handoffs across sessions and models. It supports saving, searching, recalling, exporting, and restoring context through tools like remember, recall, get_context, and save_handoff.
      7
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables an AI assistant to keep every conversation verbatim in a local SQLite store and recall the most relevant past turns on demand, using hybrid keyword and embedding search plus time-awareness. Results are packed into a small token budget (2k–8k tokens) so long histories fit modest context windows, with secrets masked before storage.
      MIT