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.
Enable AI assistants to conduct structured, persona-driven sessions including interview preparation, personal reflection, and coaching conversations. Built-in timer management and performance evaluation tools.
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
51/100 (Fair)
53/100 (Fair)
Install path
pip · high
npx · high
Engagement
0 0 0 12
0 0 0 7
Tools
Persona-driven sessions with detailed role profilesPre-defined and customizable session frameworksBuilt-in timer management with start, stop, and statusAdaptive session flow responding to conversation dynamicsSession evaluation providing detailed performance feedbackSecure file handling with path validation and error 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
