Shodh Memory vs Lean Memory — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Shodh Memory vs Lean Memory
In-depth architectural comparison of the Shodh Memory and Lean Memory 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
Shodh Memory
Knowledge & Memory · Local stdio
Quality: 55/100 (Good) | Auth: API Key required
Lean Memory
Knowledge & Memory · Local stdio
Quality: 45/100 (Fair) | Auth: No auth required
Verdict Summary: Choose Shodh Memory if you need specialized Knowledge & Memory tools running via a local process. Choose Lean Memory 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 Shodh Memory when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Free / Open Source).
You have access to required keys: SHODH_API_KEY, SHODH_CONFIG_PATH, SHODH_DATA_DIR.
Primary tools included: Zero LLM calls for storing or recalling memories, Hebbian learning with memory strengthening and decay, Local semantic search using MiniLM embeddings.
Cognitive memory for AI agents with Hebbian learning, 3-tier architecture, and knowledge graphs. Single 15MB binary, runs offline on edge devices.
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]'
Category & Scope
Tools & Capabilities Breakdown
Shodh Memory Tools (6)
Zero LLM calls for storing or recalling memories
Hebbian learning with memory strengthening and decay
Local semantic search using MiniLM embeddings
Named entity recognition and typed relation extraction
Causal lineage tracing via knowledge graph edges
Runs fully offline as a single ~17MB binary
Lean Memory Tools (6)
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Shodh Memory is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Lean Memory belongs to Knowledge & Memory using local stdio subprocess. Select Shodh Memory when you need capabilities focused on knowledge & memory and Lean Memory when you require tools for knowledge & memory.
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