Persistent AI memory with SQLite hybrid search (FTS5 + semantic). Built-in Qwen3 embedding, rclone sync across machines. Zero config, no cloud, no limits.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y mnemo-mcpAgent-CoreX intelligently routes which tools from n24q02m/mnemo-mcp your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"mnemo-mcp": {
"command": "npx",
"args": [
"-y",
"mnemo-mcp"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add mnemo-mcpAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use n24q02m/mnemo-mcp directly without routing
npx -y mnemo-mcpNew to Agent-CoreX? View setup guide →