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 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
Penfield: persistent memory with hybrid search (BM25 + vector + graph), 24 relationship types for knowledge graphs, context checkpoints for cognitive handoff, artifact storage, and personality system. Works across Claude, Cursor, Windsurf, and any MCP client.
Quality signal
53/100 (Fair)
51/100 (Fair)
Install path
npx · high
npx · high
Engagement
0 0 0 7
0 0 0 6
Tools
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
17 tools for memory, knowledge graph, context, and artifact managementHybrid search combining BM25, vector embeddings, and graph connections24 relationship types for rich knowledge graph constructionContext checkpointing with awaken and reflect tools for session continuityCross-platform synchronization across multiple MCP clientsArtifact storage with save, retrieve, list, and delete capabilities