Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"MemOS": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-MemOS"
]
}
}
}