memory_save
content, title?, scopeid?, tags?, layer?(deprecated), paths?
How to use it
memory_save is exposed by the Memem MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the memory_save tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Memem
pip install -e ".[dev]"Other tools in Memem (13)
query, taskmode?=None, scopeid?="", pathscontext?=None
CLI: python3 -m memem.server --assemble-context <query>
ids, scopeid?="default"
CLI: python3 -m memem.server graph neighbors <memoryid>
CLI: python3 -m memem.server graph audit
CLI: python3 -m memem.server graph rebuild [scope]
Python: memem.operations.memoryimport()
CLI: python3 -m memem.server --compact-index
Use memorysearch then memoryget
Python: memem.crossvault.searchacrossvaults()
query, limit?=10, scopeid?="default"
memoryid, depthbefore?=5, depthafter?=5, scopeid?="default"
query, limit?=5