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 persistent memory for AI coding agents. Captures facts, decisions, patterns, and architecture notes in SQLite (with optional cloud embeddings) to reduce repeated context across sessions.
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
Quality signal
48/100 (Fair)
53/100 (Fair)
Install path
npx · high
npx · high
Engagement
0 0 0 2
0 0 0 7
Tools
Local-first storage using SQLite with optional cloud embeddingsToken-aware context retrieval with progressive disclosureSupport for multiple MCP-compatible clients including Claude Code and CodexImport existing project memory files automaticallyTeam-scoped memory synchronization through gitWeb-based UI for inspection and management
Local SQLite database with all-MiniLM-L6-v2 embeddingsHybrid semantic and FTS5 full-text search recallAutomatic secret detection on every write operationSix MCP-native tools: remember, recall, forget, feedback, context, statusFully offline operation with zero external dependenciesIn-process integration with no separate server or IPC overhead
