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
Privacy-first document search server running entirely locally. Supports semantic search over PDFs, DOCX, TXT, and Markdown files with LanceDB vector storage and local embeddings - no API keys or cloud services required.
Quality signal
53/100 (Fair)
56/100 (Good)
Install path
npx · high
npx · high
Engagement
0 0 0 7
1 0 0 360
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
Runs fully locally with no external API or cloud dependencySupports semantic search combined with keyword boosting for exact matchesIndexes PDF, DOCX, Markdown, and plain text filesSemantic chunking preserves topic boundaries and code blocksMCP protocol support for integration with AI tools and CLI usageFile sync and incremental indexing with status and control tools