In-depth architectural comparison of the Memex and Engram 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
Memex
Knowledge & Memory · Local stdio
Quality: 43/100 (Fair) | Auth: No auth required
Engram
Knowledge & Memory · Local stdio
Quality: 56/100 (Good) | Auth: No auth required
Verdict Summary: Choose Memex if you need specialized Knowledge & Memory tools running via a local process. Choose Engram 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 Memex 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: DB_MAX_POOL_SIZE.
Primary tools included: Semantic vector search with recency decay re-ranking, Local ONNX embedding model (BAAI/bge-small-en-v1.5) for zero API cost, PostgreSQL 16 with pgvector and ivfflat index for efficient vector queries.
Production-grade persistent memory service for AI agents. Semantic search with recency decay (configurable α blend), local ONNX embeddings (zero API cost), background memory summarisation, and Prometheus/Grafana observability. docker compose up — no cloud dependencies.
Local-first persistent memory for AI agents. SQLite + local embeddings (all-MiniLM-L6-v2), hybrid semantic + FTS5 recall, secret detection, and contradiction handling. 6 MCP tools (remember, recall, forget, feedback, context, status) over stdio. Zero cloud, no API keys, fully offline. Works with Claude Desktop/Code, Cursor, and Windsurf. npm install -g @hbarefoot/engram
Category & Scope
Tools & Capabilities Breakdown
Memex Tools (6)
Semantic vector search with recency decay re-ranking
Local ONNX embedding model (BAAI/bge-small-en-v1.5) for zero API cost
PostgreSQL 16 with pgvector and ivfflat index for efficient vector queries
Configurable recency decay blending factor (alpha) per request
Background memory summarization and Prometheus/Grafana observability
Docker Compose deployment with no external cloud dependencies
Engram 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).
Memex is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Engram belongs to Knowledge & Memory using local stdio subprocess. Select Memex when you need capabilities focused on knowledge & memory and Engram when you require tools for knowledge & memory.