In-depth architectural comparison of the Lean Memory and Mnemos MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Lean Memory
Knowledge & Memory · Local stdio
Quality: 55/100 (Good) | Auth: No auth required
Mnemos
Knowledge & Memory · Local stdio
Quality: 59/100 (Good) | Auth: No auth required
Verdict Summary: Choose Lean Memory if you need specialized Knowledge & Memory tools running via a local process. Choose Mnemos if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Lean Memory when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
You have access to required keys: LM_DATA_ROOT, ANTHROPIC_API_KEY.
Primary tools included: Single SQLite file per namespace for isolated memory storage, Hybrid dense (embedding) and sparse (FTS5) search retrieval, Add-only memory history with point-in-time querying.
Lean Memory is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Mnemos belongs to Knowledge & Memory using local stdio subprocess. Select Lean Memory when you need capabilities focused on knowledge & memory and Mnemos when you require tools for knowledge & memory.
Embedded, local-first agent memory in a single SQLite file per namespace (vec0 + FTS5 hybrid retrieval). ADD-only history queryable as-of any past time; offline sleep-time maintenance stages dedupe/summarize/evict proposals a human reviews. No Docker, no server, no cloud key. pip install 'lean-memory[mcp]'
Persistent memory engine for AI coding agents. Stores architecture decisions, bug root causes, and project conventions across sessions. Single Go binary with embedded SQLite, FTS5 search, context assembly within token budgets, and autopilot setup for Claude Code, Kiro, and Cursor.