Loomal

Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).

36 starspypi: mnemex

About mnemex

mnemex is an MCP (Model Context Protocol) server published by simplemindedbot in the official MCP registry, listed under RAG Systems on Loomal. Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).

It ships as a Python package on PyPI (mnemex), so any MCP client that can launch a local process can run it.

Development happens in the open at github.com/simplemindedbot/mnemex, where the project has earned 36 GitHub stars.

Use mnemex with your agent

Claude Code · one command
claude mcp add mnemex -- uvx mnemex
Claude Desktop, Cursor & other MCP clients · config
{
  "mcpServers": {
    "mnemex": {
      "command": "uvx",
      "args": [
        "mnemex"
      ]
    }
  }
}
pypimnemex

Frequently asked questions

What is mnemex?
mnemex is an MCP (Model Context Protocol) server by simplemindedbot in the RAG Systems category. Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).
How do I connect mnemex to Claude, Cursor, or another MCP client?
Install mnemex from its pypi package (mnemex) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
Is mnemex open source?
Yes — the source code is public at github.com/simplemindedbot/mnemex, with 36 GitHub stars.
Can AI agents pay to use mnemex?
Not yet through Loomal — mnemex is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.

Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain mnemex? Claim this listing free by verifying GitHub ownership, or contact us.