claude-mem vs Memory (MCP reference server)

claude-mem

Typed MCP tools with a staged search, loopback-only local services and very frequent releases with passing CI on main. Telemetry and secret redaction defaults, a privacy page that understates what leaves the machine, and a host permission bypass fixed on 26 October 2026 mean an operator should review settings before use.

Memory (MCP reference server)

Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. read_graph returns everything and search_nodes every match.

claude-mem

1. Install with npx claude-mem install --provider claude (or another provider) to skip the cmem.ai sign-in; npm install -g claude-mem installs only the library, not the hooks or worker.
2. Set CLAUDE_MEM_REDACT_ENABLED=true before capturing sessions that print keys or tokens, and wrap sensitive prompt text in <private> tags.
3. Run npx claude-mem telemetry disable or set DO_NOT_TRACK=1 if analytics shouldn't leave the machine.
4. Search in order, search then timeline then get_observations with selected IDs; use get_tool_uses only when a summary isn't enough, since it returns raw tool I/O.
5. Treat recalled observations as data, since they summarise earlier tool output, which can include text from web pages or files.

Memory (MCP reference server)

1. Set MEMORY_FILE_PATH to an absolute path. The default sits inside the npx cache
2. Use search_nodes or open_nodes instead of read_graph once the graph has more than a few hundred entities
3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31
4. Create both entities before create_relations. A missing endpoint fails the whole batch
5. Keep observations short and factual. They come back verbatim in every later read