claude-mem vs LangMem
LangMem: LangChain's SDK for adding long-term memory to agents.
LangMem is LangChain's SDK for adding long-term memory to agents you build in code. cmem is the opposite ergonomic: instead of writing memory plumbing into an app, you install a plugin and a second model captures structured observations while your coding agent works. It is open source, local-first, and reachable from any MCP client through one private link.
Move without ripping anything out
Install the engine
Run npx claude-mem@latest install. The open-source engine wires into Claude Code natively and starts writing observations — nothing to migrate first.
Keep what you have
cmem speaks MCP, so it sits alongside LangMem rather than replacing it. Point any MCP client at your private link and both can read.
Recall everywhere
Once CMEM Cloud mirrors your DB, the same memory is reachable from every agent and machine through one private MCP link.
Memory that compounds, built in
Automatic capture
A second model writes structured notes out-of-band — no prompting, no slowdown.
Auto-categorization
Decision, bugfix, feature, discovery, security — every note lands in a taxonomy.
Search three ways
Semantic, keyword, and timeline search over everything your agents have done.
Causality threading
Before/after links connect why a change happened to what came next.
Local-first & private
Memory lives in local SQLite with privacy stripping; cloud sync is opt-in.
Smart-explore
Structural codebase exploration that is 6–12× cheaper than reading files in full.