Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Local-first memory engine for AI-agent teams: private/team/project ACL (a hard gate before ranking), associative recall, and federated sync where revocation propagates across nodes. SQLite + FTS5, no LLM required; MCP server + web console included. pip install 'agent-memory-os[mcp]'
Persistent, compounding memory for AI agents across sessions. Uses the Intelligent Distance Protocol to surface the most contextually relevant past memories. Five tools: sessionstart, remember, recall, check, sessionend. npx agent-recall-mcp